Upload 70 files

.gitattributes

@@ -16,3 +16,4 @@ custom_nodes/ComfyUI-N-Nodes/libs/rifle/demo/I2_0.png filter=lfs diff=lfs merge=
 custom_nodes/ComfyUI-N-Nodes/libs/rifle/demo/I2_1.png filter=lfs diff=lfs merge=lfs -text
 custom_nodes/ComfyUI-N-Nodes/libs/rifle/demo/I2_slomo_clipped.gif filter=lfs diff=lfs merge=lfs -text
 custom_nodes/ComfyUI-N-Nodes/libs/rifle/train_log/flownet.pkl filter=lfs diff=lfs merge=lfs -text
+custom_nodes/ComfyUI-CogVideoXWrapper/example_workflows/noise_warp_example_input_video.mp4 filter=lfs diff=lfs merge=lfs -text

custom_nodes/ComfyUI-CogVideoXWrapper/.gitattributes

@@ -0,0 +1,2 @@
+# Auto detect text files and perform LF normalization
+* text=auto

custom_nodes/ComfyUI-CogVideoXWrapper/.github/FUNDING.yml

@@ -0,0 +1,2 @@
+github: [kijai]
+custom: ["https://www.paypal.me/kijaidesign"]

custom_nodes/ComfyUI-CogVideoXWrapper/.github/workflows/publish.yml

@@ -0,0 +1,24 @@
+name: Publish to Comfy registry
+on:
+  workflow_dispatch:
+  push:
+    branches:
+      - main
+      - master
+    paths:
+      - "pyproject.toml"
+
+jobs:
+  publish-node:
+    name: Publish Custom Node to registry
+    runs-on: ubuntu-latest
+    # if this is a forked repository. Skipping the workflow.
+    if: github.event.repository.fork == false 
+    steps:
+      - name: Check out code
+        uses: actions/checkout@v4
+      - name: Publish Custom Node
+        uses: Comfy-Org/publish-node-action@main
+        with:
+          ## Add your own personal access token to your Github Repository secrets and reference it here.
+          personal_access_token: ${{ secrets.REGISTRY_ACCESS_TOKEN }}

custom_nodes/ComfyUI-CogVideoXWrapper/.gitignore

@@ -0,0 +1,11 @@
+output/
+*__pycache__/
+samples*/
+runs/
+checkpoints/
+master_ip
+logs/
+*.DS_Store
+.idea
+*.pt
+tools/

custom_nodes/ComfyUI-CogVideoXWrapper/LICENSE

@@ -0,0 +1,201 @@
+                                 Apache License
+                           Version 2.0, January 2004
+                        http://www.apache.org/licenses/
+
+   TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
+
+   1. Definitions.
+
+      "License" shall mean the terms and conditions for use, reproduction,
+      and distribution as defined by Sections 1 through 9 of this document.
+
+      "Licensor" shall mean the copyright owner or entity authorized by
+      the copyright owner that is granting the License.
+
+      "Legal Entity" shall mean the union of the acting entity and all
+      other entities that control, are controlled by, or are under common
+      control with that entity. For the purposes of this definition,
+      "control" means (i) the power, direct or indirect, to cause the
+      direction or management of such entity, whether by contract or
+      otherwise, or (ii) ownership of fifty percent (50%) or more of the
+      outstanding shares, or (iii) beneficial ownership of such entity.
+
+      "You" (or "Your") shall mean an individual or Legal Entity
+      exercising permissions granted by this License.
+
+      "Source" form shall mean the preferred form for making modifications,
+      including but not limited to software source code, documentation
+      source, and configuration files.
+
+      "Object" form shall mean any form resulting from mechanical
+      transformation or translation of a Source form, including but
+      not limited to compiled object code, generated documentation,
+      and conversions to other media types.
+
+      "Work" shall mean the work of authorship, whether in Source or
+      Object form, made available under the License, as indicated by a
+      copyright notice that is included in or attached to the work
+      (an example is provided in the Appendix below).
+
+      "Derivative Works" shall mean any work, whether in Source or Object
+      form, that is based on (or derived from) the Work and for which the
+      editorial revisions, annotations, elaborations, or other modifications
+      represent, as a whole, an original work of authorship. For the purposes
+      of this License, Derivative Works shall not include works that remain
+      separable from, or merely link (or bind by name) to the interfaces of,
+      the Work and Derivative Works thereof.
+
+      "Contribution" shall mean any work of authorship, including
+      the original version of the Work and any modifications or additions
+      to that Work or Derivative Works thereof, that is intentionally
+      submitted to Licensor for inclusion in the Work by the copyright owner
+      or by an individual or Legal Entity authorized to submit on behalf of
+      the copyright owner. For the purposes of this definition, "submitted"
+      means any form of electronic, verbal, or written communication sent
+      to the Licensor or its representatives, including but not limited to
+      communication on electronic mailing lists, source code control systems,
+      and issue tracking systems that are managed by, or on behalf of, the
+      Licensor for the purpose of discussing and improving the Work, but
+      excluding communication that is conspicuously marked or otherwise
+      designated in writing by the copyright owner as "Not a Contribution."
+
+      "Contributor" shall mean Licensor and any individual or Legal Entity
+      on behalf of whom a Contribution has been received by Licensor and
+      subsequently incorporated within the Work.
+
+   2. Grant of Copyright License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      copyright license to reproduce, prepare Derivative Works of,
+      publicly display, publicly perform, sublicense, and distribute the
+      Work and such Derivative Works in Source or Object form.
+
+   3. Grant of Patent License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      (except as stated in this section) patent license to make, have made,
+      use, offer to sell, sell, import, and otherwise transfer the Work,
+      where such license applies only to those patent claims licensable
+      by such Contributor that are necessarily infringed by their
+      Contribution(s) alone or by combination of their Contribution(s)
+      with the Work to which such Contribution(s) was submitted. If You
+      institute patent litigation against any entity (including a
+      cross-claim or counterclaim in a lawsuit) alleging that the Work
+      or a Contribution incorporated within the Work constitutes direct
+      or contributory patent infringement, then any patent licenses
+      granted to You under this License for that Work shall terminate
+      as of the date such litigation is filed.
+
+   4. Redistribution. You may reproduce and distribute copies of the
+      Work or Derivative Works thereof in any medium, with or without
+      modifications, and in Source or Object form, provided that You
+      meet the following conditions:
+
+      (a) You must give any other recipients of the Work or
+          Derivative Works a copy of this License; and
+
+      (b) You must cause any modified files to carry prominent notices
+          stating that You changed the files; and
+
+      (c) You must retain, in the Source form of any Derivative Works
+          that You distribute, all copyright, patent, trademark, and
+          attribution notices from the Source form of the Work,
+          excluding those notices that do not pertain to any part of
+          the Derivative Works; and
+
+      (d) If the Work includes a "NOTICE" text file as part of its
+          distribution, then any Derivative Works that You distribute must
+          include a readable copy of the attribution notices contained
+          within such NOTICE file, excluding those notices that do not
+          pertain to any part of the Derivative Works, in at least one
+          of the following places: within a NOTICE text file distributed
+          as part of the Derivative Works; within the Source form or
+          documentation, if provided along with the Derivative Works; or,
+          within a display generated by the Derivative Works, if and
+          wherever such third-party notices normally appear. The contents
+          of the NOTICE file are for informational purposes only and
+          do not modify the License. You may add Your own attribution
+          notices within Derivative Works that You distribute, alongside
+          or as an addendum to the NOTICE text from the Work, provided
+          that such additional attribution notices cannot be construed
+          as modifying the License.
+
+      You may add Your own copyright statement to Your modifications and
+      may provide additional or different license terms and conditions
+      for use, reproduction, or distribution of Your modifications, or
+      for any such Derivative Works as a whole, provided Your use,
+      reproduction, and distribution of the Work otherwise complies with
+      the conditions stated in this License.
+
+   5. Submission of Contributions. Unless You explicitly state otherwise,
+      any Contribution intentionally submitted for inclusion in the Work
+      by You to the Licensor shall be under the terms and conditions of
+      this License, without any additional terms or conditions.
+      Notwithstanding the above, nothing herein shall supersede or modify
+      the terms of any separate license agreement you may have executed
+      with Licensor regarding such Contributions.
+
+   6. Trademarks. This License does not grant permission to use the trade
+      names, trademarks, service marks, or product names of the Licensor,
+      except as required for reasonable and customary use in describing the
+      origin of the Work and reproducing the content of the NOTICE file.
+
+   7. Disclaimer of Warranty. Unless required by applicable law or
+      agreed to in writing, Licensor provides the Work (and each
+      Contributor provides its Contributions) on an "AS IS" BASIS,
+      WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
+      implied, including, without limitation, any warranties or conditions
+      of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
+      PARTICULAR PURPOSE. You are solely responsible for determining the
+      appropriateness of using or redistributing the Work and assume any
+      risks associated with Your exercise of permissions under this License.
+
+   8. Limitation of Liability. In no event and under no legal theory,
+      whether in tort (including negligence), contract, or otherwise,
+      unless required by applicable law (such as deliberate and grossly
+      negligent acts) or agreed to in writing, shall any Contributor be
+      liable to You for damages, including any direct, indirect, special,
+      incidental, or consequential damages of any character arising as a
+      result of this License or out of the use or inability to use the
+      Work (including but not limited to damages for loss of goodwill,
+      work stoppage, computer failure or malfunction, or any and all
+      other commercial damages or losses), even if such Contributor
+      has been advised of the possibility of such damages.
+
+   9. Accepting Warranty or Additional Liability. While redistributing
+      the Work or Derivative Works thereof, You may choose to offer,
+      and charge a fee for, acceptance of support, warranty, indemnity,
+      or other liability obligations and/or rights consistent with this
+      License. However, in accepting such obligations, You may act only
+      on Your own behalf and on Your sole responsibility, not on behalf
+      of any other Contributor, and only if You agree to indemnify,
+      defend, and hold each Contributor harmless for any liability
+      incurred by, or claims asserted against, such Contributor by reason
+      of your accepting any such warranty or additional liability.
+
+   END OF TERMS AND CONDITIONS
+
+   APPENDIX: How to apply the Apache License to your work.
+
+      To apply the Apache License to your work, attach the following
+      boilerplate notice, with the fields enclosed by brackets "[]"
+      replaced with your own identifying information. (Don't include
+      the brackets!)  The text should be enclosed in the appropriate
+      comment syntax for the file format. We also recommend that a
+      file or class name and description of purpose be included on the
+      same "printed page" as the copyright notice for easier
+      identification within third-party archives.
+
+   Copyright [yyyy] [name of copyright owner]
+
+   Licensed under the Apache License, Version 2.0 (the "License");
+   you may not use this file except in compliance with the License.
+   You may obtain a copy of the License at
+
+       http://www.apache.org/licenses/LICENSE-2.0
+
+   Unless required by applicable law or agreed to in writing, software
+   distributed under the License is distributed on an "AS IS" BASIS,
+   WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+   See the License for the specific language governing permissions and
+   limitations under the License.

custom_nodes/ComfyUI-CogVideoXWrapper/__init__.py

@@ -0,0 +1,7 @@
+from .nodes import NODE_CLASS_MAPPINGS as NODES_CLASS, NODE_DISPLAY_NAME_MAPPINGS as NODES_DISPLAY
+from .model_loading import NODE_CLASS_MAPPINGS as MODEL_CLASS, NODE_DISPLAY_NAME_MAPPINGS as MODEL_DISPLAY
+
+NODE_CLASS_MAPPINGS = {**NODES_CLASS, **MODEL_CLASS}
+NODE_DISPLAY_NAME_MAPPINGS = {**NODES_DISPLAY, **MODEL_DISPLAY}
+
+__all__ = ["NODE_CLASS_MAPPINGS", "NODE_DISPLAY_NAME_MAPPINGS"]

custom_nodes/ComfyUI-CogVideoXWrapper/cogvideo_controlnet.py

@@ -0,0 +1,220 @@
+# https://github.com/TheDenk/cogvideox-controlnet/blob/main/cogvideo_controlnet.py
+from typing import Any, Dict, Optional, Tuple, Union
+
+import torch
+from torch import nn
+from einops import rearrange
+import torch.nn.functional as F
+from .custom_cogvideox_transformer_3d import Transformer2DModelOutput, CogVideoXBlock
+from diffusers.utils import is_torch_version
+from diffusers.loaders import  PeftAdapterMixin
+from diffusers.models.embeddings import CogVideoXPatchEmbed, TimestepEmbedding, Timesteps
+from diffusers.models.modeling_utils import ModelMixin
+from diffusers.configuration_utils import ConfigMixin, register_to_config
+
+
+class CogVideoXControlnet(ModelMixin, ConfigMixin, PeftAdapterMixin):
+    _supports_gradient_checkpointing = True
+    
+    @register_to_config
+    def __init__(
+        self,
+        num_attention_heads: int = 30,
+        attention_head_dim: int = 64,
+        vae_channels: int = 16,
+        in_channels: int = 3,
+        downscale_coef: int = 8,
+        flip_sin_to_cos: bool = True,
+        freq_shift: int = 0,
+        time_embed_dim: int = 512,
+        num_layers: int = 8,
+        dropout: float = 0.0,
+        attention_bias: bool = True,
+        sample_width: int = 90,
+        sample_height: int = 60,
+        sample_frames: int = 49,
+        patch_size: int = 2,
+        temporal_compression_ratio: int = 4,
+        max_text_seq_length: int = 226,
+        activation_fn: str = "gelu-approximate",
+        timestep_activation_fn: str = "silu",
+        norm_elementwise_affine: bool = True,
+        norm_eps: float = 1e-5,
+        spatial_interpolation_scale: float = 1.875,
+        temporal_interpolation_scale: float = 1.0,
+        use_rotary_positional_embeddings: bool = False,
+        use_learned_positional_embeddings: bool = False,
+        out_proj_dim = None,
+    ):
+        super().__init__()
+        inner_dim = num_attention_heads * attention_head_dim
+
+        if not use_rotary_positional_embeddings and use_learned_positional_embeddings:
+            raise ValueError(
+                "There are no CogVideoX checkpoints available with disable rotary embeddings and learned positional "
+                "embeddings. If you're using a custom model and/or believe this should be supported, please open an "
+                "issue at https://github.com/huggingface/diffusers/issues."
+            )
+            
+        start_channels = in_channels * (downscale_coef ** 2)
+        input_channels = [start_channels, start_channels // 2, start_channels // 4]
+        self.unshuffle = nn.PixelUnshuffle(downscale_coef)
+        
+        self.controlnet_encode_first = nn.Sequential(
+            nn.Conv2d(input_channels[0], input_channels[1], kernel_size=1, stride=1, padding=0),
+            nn.GroupNorm(2, input_channels[1]),
+            nn.ReLU(),
+        )
+
+        self.controlnet_encode_second = nn.Sequential(
+            nn.Conv2d(input_channels[1], input_channels[2], kernel_size=1, stride=1, padding=0),
+            nn.GroupNorm(2, input_channels[2]),
+            nn.ReLU(),
+        )
+        
+        # 1. Patch embedding
+        self.patch_embed = CogVideoXPatchEmbed(
+            patch_size=patch_size,
+            in_channels=vae_channels + input_channels[2],
+            embed_dim=inner_dim,
+            bias=True,
+            sample_width=sample_width,
+            sample_height=sample_height,
+            sample_frames=sample_frames,
+            temporal_compression_ratio=temporal_compression_ratio,
+            spatial_interpolation_scale=spatial_interpolation_scale,
+            temporal_interpolation_scale=temporal_interpolation_scale,
+            use_positional_embeddings=not use_rotary_positional_embeddings,
+            use_learned_positional_embeddings=use_learned_positional_embeddings,
+        )
+        
+        self.embedding_dropout = nn.Dropout(dropout)
+
+        # 2. Time embeddings
+        self.time_proj = Timesteps(inner_dim, flip_sin_to_cos, freq_shift)
+        self.time_embedding = TimestepEmbedding(inner_dim, time_embed_dim, timestep_activation_fn)
+
+        # 3. Define spatio-temporal transformers blocks
+        self.transformer_blocks = nn.ModuleList(
+            [
+                CogVideoXBlock(
+                    dim=inner_dim,
+                    num_attention_heads=num_attention_heads,
+                    attention_head_dim=attention_head_dim,
+                    time_embed_dim=time_embed_dim,
+                    dropout=dropout,
+                    activation_fn=activation_fn,
+                    attention_bias=attention_bias,
+                    norm_elementwise_affine=norm_elementwise_affine,
+                    norm_eps=norm_eps,
+                )
+                for _ in range(num_layers)
+            ]
+        )
+
+        self.out_projectors = None
+        if out_proj_dim is not None:
+            self.out_projectors = nn.ModuleList(
+                [nn.Linear(inner_dim, out_proj_dim) for _ in range(num_layers)]
+            )
+            
+        self.gradient_checkpointing = False
+        
+    def _set_gradient_checkpointing(self, module, value=False):
+        self.gradient_checkpointing = value
+
+    def compress_time(self, x, num_frames):
+        x = rearrange(x, '(b f) c h w -> b f c h w', f=num_frames)
+        batch_size, frames, channels, height, width = x.shape
+        x = rearrange(x, 'b f c h w -> (b h w) c f')
+        
+        if x.shape[-1] % 2 == 1:
+            x_first, x_rest = x[..., 0], x[..., 1:]
+            if x_rest.shape[-1] > 0:
+                x_rest = F.avg_pool1d(x_rest, kernel_size=2, stride=2)
+
+            x = torch.cat([x_first[..., None], x_rest], dim=-1)
+        else:
+            x = F.avg_pool1d(x, kernel_size=2, stride=2)
+        x = rearrange(x, '(b h w) c f -> (b f) c h w', b=batch_size, h=height, w=width)
+        return x
+        
+    def forward(
+        self,
+        hidden_states: torch.Tensor,
+        encoder_hidden_states: torch.Tensor,
+        controlnet_states: torch.Tensor,
+        timestep: Union[int, float, torch.LongTensor],
+        image_rotary_emb: Optional[Tuple[torch.Tensor, torch.Tensor]] = None,
+        timestep_cond: Optional[torch.Tensor] = None,
+        return_dict: bool = True,
+    ):
+        batch_size, num_frames, channels, height, width = controlnet_states.shape
+        # 0. Controlnet encoder
+        controlnet_states = rearrange(controlnet_states, 'b f c h w -> (b f) c h w')
+        controlnet_states = self.unshuffle(controlnet_states)
+        controlnet_states = self.controlnet_encode_first(controlnet_states)
+        controlnet_states = self.compress_time(controlnet_states, num_frames=num_frames) 
+        num_frames = controlnet_states.shape[0] // batch_size
+
+        controlnet_states = self.controlnet_encode_second(controlnet_states)
+        controlnet_states = self.compress_time(controlnet_states, num_frames=num_frames) 
+        controlnet_states = rearrange(controlnet_states, '(b f) c h w -> b f c h w', b=batch_size)
+
+        hidden_states = torch.cat([hidden_states, controlnet_states], dim=2)
+        # controlnet_states = self.controlnext_encoder(controlnet_states, timestep=timestep)
+        # 1. Time embedding
+        timesteps = timestep
+        t_emb = self.time_proj(timesteps)
+
+        # timesteps does not contain any weights and will always return f32 tensors
+        # but time_embedding might actually be running in fp16. so we need to cast here.
+        # there might be better ways to encapsulate this.
+        t_emb = t_emb.to(dtype=hidden_states.dtype)
+        emb = self.time_embedding(t_emb, timestep_cond)
+        
+        hidden_states = self.patch_embed(encoder_hidden_states, hidden_states)
+        hidden_states = self.embedding_dropout(hidden_states)
+
+
+        text_seq_length = encoder_hidden_states.shape[1]
+        encoder_hidden_states = hidden_states[:, :text_seq_length]
+        hidden_states = hidden_states[:, text_seq_length:]
+
+        
+        controlnet_hidden_states = ()
+        # 3. Transformer blocks
+        for i, block in enumerate(self.transformer_blocks):
+            if self.training and self.gradient_checkpointing:
+
+                def create_custom_forward(module):
+                    def custom_forward(*inputs):
+                        return module(*inputs)
+
+                    return custom_forward
+
+                ckpt_kwargs: Dict[str, Any] = {"use_reentrant": False} if is_torch_version(">=", "1.11.0") else {}
+                hidden_states, encoder_hidden_states = torch.utils.checkpoint.checkpoint(
+                    create_custom_forward(block),
+                    hidden_states,
+                    encoder_hidden_states,
+                    emb,
+                    image_rotary_emb,
+                    **ckpt_kwargs,
+                )
+            else:
+                hidden_states, encoder_hidden_states = block(
+                    hidden_states=hidden_states,
+                    encoder_hidden_states=encoder_hidden_states,
+                    temb=emb,
+                    image_rotary_emb=image_rotary_emb,
+                )
+                
+            if self.out_projectors is not None:
+                controlnet_hidden_states += (self.out_projectors[i](hidden_states),)
+            else:
+                controlnet_hidden_states += (hidden_states,)
+            
+        if not return_dict:
+            return (controlnet_hidden_states,)
+        return Transformer2DModelOutput(sample=controlnet_hidden_states)

custom_nodes/ComfyUI-CogVideoXWrapper/cogvideox_fun/utils.py

@@ -0,0 +1,43 @@
+import numpy as np
+from PIL import Image
+
+ASPECT_RATIO_512 = {
+    '0.25': [256.0, 1024.0], '0.26': [256.0, 992.0], '0.27': [256.0, 960.0], '0.28': [256.0, 928.0],
+    '0.32': [288.0, 896.0], '0.33': [288.0, 864.0], '0.35': [288.0, 832.0], '0.4': [320.0, 800.0],
+    '0.42': [320.0, 768.0], '0.48': [352.0, 736.0], '0.5': [352.0, 704.0], '0.52': [352.0, 672.0],
+    '0.57': [384.0, 672.0], '0.6': [384.0, 640.0], '0.68': [416.0, 608.0], '0.72': [416.0, 576.0],
+    '0.78': [448.0, 576.0], '0.82': [448.0, 544.0], '0.88': [480.0, 544.0], '0.94': [480.0, 512.0],
+    '1.0': [512.0, 512.0], '1.07': [512.0, 480.0], '1.13': [544.0, 480.0], '1.21': [544.0, 448.0],
+    '1.29': [576.0, 448.0], '1.38': [576.0, 416.0], '1.46': [608.0, 416.0], '1.67': [640.0, 384.0],
+    '1.75': [672.0, 384.0], '2.0': [704.0, 352.0], '2.09': [736.0, 352.0], '2.4': [768.0, 320.0],
+    '2.5': [800.0, 320.0], '2.89': [832.0, 288.0], '3.0': [864.0, 288.0], '3.11': [896.0, 288.0],
+    '3.62': [928.0, 256.0], '3.75': [960.0, 256.0], '3.88': [992.0, 256.0], '4.0': [1024.0, 256.0]
+}
+ASPECT_RATIO_RANDOM_CROP_512 = {
+    '0.42': [320.0, 768.0], '0.5': [352.0, 704.0], 
+    '0.57': [384.0, 672.0], '0.68': [416.0, 608.0], '0.78': [448.0, 576.0], '0.88': [480.0, 544.0], 
+    '0.94': [480.0, 512.0], '1.0': [512.0, 512.0], '1.07': [512.0, 480.0], 
+    '1.13': [544.0, 480.0], '1.29': [576.0, 448.0], '1.46': [608.0, 416.0], '1.75': [672.0, 384.0], 
+    '2.0': [704.0, 352.0],  '2.4': [768.0, 320.0]
+}
+ASPECT_RATIO_RANDOM_CROP_PROB = [
+    1, 2,
+    4, 4, 4, 4,
+    8, 8, 8,
+    4, 4, 4, 4,
+    2, 1
+]
+ASPECT_RATIO_RANDOM_CROP_PROB = np.array(ASPECT_RATIO_RANDOM_CROP_PROB) / sum(ASPECT_RATIO_RANDOM_CROP_PROB)
+
+def get_closest_ratio(height: float, width: float, ratios: dict = ASPECT_RATIO_512):
+    aspect_ratio = height / width
+    closest_ratio = min(ratios.keys(), key=lambda ratio: abs(float(ratio) - aspect_ratio))
+    return ratios[closest_ratio], float(closest_ratio)
+
+def get_width_and_height_from_image_and_base_resolution(image, base_resolution):
+    target_pixels = int(base_resolution) * int(base_resolution)
+    original_width, original_height = Image.open(image).size
+    ratio = (target_pixels / (original_width * original_height)) ** 0.5
+    width_slider = round(original_width * ratio)
+    height_slider = round(original_height * ratio)
+    return height_slider, width_slider

custom_nodes/ComfyUI-CogVideoXWrapper/configs/scheduler_config_2b.json

@@ -0,0 +1,18 @@
+{
+  "_class_name": "CogVideoXDDIMScheduler",
+  "_diffusers_version": "0.30.0.dev0",
+  "beta_end": 0.012,
+  "beta_schedule": "scaled_linear",
+  "beta_start": 0.00085,
+  "clip_sample": false,
+  "clip_sample_range": 1.0,
+  "num_train_timesteps": 1000,
+  "prediction_type": "v_prediction",
+  "rescale_betas_zero_snr": true,
+  "sample_max_value": 1.0,
+  "set_alpha_to_one": true,
+  "snr_shift_scale": 3.0,
+  "steps_offset": 0,
+  "timestep_spacing": "trailing",
+  "trained_betas": null
+}

custom_nodes/ComfyUI-CogVideoXWrapper/configs/scheduler_config_5b.json

@@ -0,0 +1,18 @@
+{
+  "_class_name": "CogVideoXDDIMScheduler",
+  "_diffusers_version": "0.31.0.dev0",
+  "beta_end": 0.012,
+  "beta_schedule": "scaled_linear",
+  "beta_start": 0.00085,
+  "clip_sample": false,
+  "clip_sample_range": 1.0,
+  "num_train_timesteps": 1000,
+  "prediction_type": "v_prediction",
+  "rescale_betas_zero_snr": true,
+  "sample_max_value": 1.0,
+  "set_alpha_to_one": true,
+  "snr_shift_scale": 1.0,
+  "steps_offset": 0,
+  "timestep_spacing": "trailing",
+  "trained_betas": null
+}

custom_nodes/ComfyUI-CogVideoXWrapper/configs/transformer_config_2b.json

@@ -0,0 +1,26 @@
+{
+    "activation_fn": "gelu-approximate",
+    "attention_bias": true,
+    "attention_head_dim": 64,
+    "dropout": 0.0,
+    "flip_sin_to_cos": true,
+    "freq_shift": 0,
+    "in_channels": 16,
+    "max_text_seq_length": 226,
+    "norm_elementwise_affine": true,
+    "norm_eps": 1e-05,
+    "num_attention_heads": 30,
+    "num_layers": 30,
+    "out_channels": 16,
+    "patch_size": 2,
+    "sample_frames": 49,
+    "sample_height": 60,
+    "sample_width": 90,
+    "spatial_interpolation_scale": 1.875,
+    "temporal_compression_ratio": 4,
+    "temporal_interpolation_scale": 1.0,
+    "text_embed_dim": 4096,
+    "time_embed_dim": 512,
+    "timestep_activation_fn": "silu",
+    "use_rotary_positional_embeddings": false
+  }

custom_nodes/ComfyUI-CogVideoXWrapper/configs/transformer_config_5b.json

@@ -0,0 +1,26 @@
+{
+    "activation_fn": "gelu-approximate",
+    "attention_bias": true,
+    "attention_head_dim": 64,
+    "dropout": 0.0,
+    "flip_sin_to_cos": true,
+    "freq_shift": 0,
+    "in_channels": 16,
+    "max_text_seq_length": 226,
+    "norm_elementwise_affine": true,
+    "norm_eps": 1e-05,
+    "num_attention_heads": 48,
+    "num_layers": 42,
+    "out_channels": 16,
+    "patch_size": 2,
+    "sample_frames": 49,
+    "sample_height": 60,
+    "sample_width": 90,
+    "spatial_interpolation_scale": 1.875,
+    "temporal_compression_ratio": 4,
+    "temporal_interpolation_scale": 1.0,
+    "text_embed_dim": 4096,
+    "time_embed_dim": 512,
+    "timestep_activation_fn": "silu",
+    "use_rotary_positional_embeddings": true
+  }

custom_nodes/ComfyUI-CogVideoXWrapper/configs/transformer_config_I2V_5b.json

@@ -0,0 +1,27 @@
+{
+    "activation_fn": "gelu-approximate",
+    "attention_bias": true,
+    "attention_head_dim": 64,
+    "dropout": 0.0,
+    "flip_sin_to_cos": true,
+    "freq_shift": 0,
+    "in_channels": 32,
+    "max_text_seq_length": 226,
+    "norm_elementwise_affine": true,
+    "norm_eps": 1e-05,
+    "num_attention_heads": 48,
+    "num_layers": 42,
+    "out_channels": 16,
+    "patch_size": 2,
+    "sample_frames": 49,
+    "sample_height": 60,
+    "sample_width": 90,
+    "spatial_interpolation_scale": 1.875,
+    "temporal_compression_ratio": 4,
+    "temporal_interpolation_scale": 1.0,
+    "text_embed_dim": 4096,
+    "time_embed_dim": 512,
+    "timestep_activation_fn": "silu",
+    "use_learned_positional_embeddings": true,
+    "use_rotary_positional_embeddings": true
+  }

custom_nodes/ComfyUI-CogVideoXWrapper/configs/vae_config.json

@@ -0,0 +1,39 @@
+{
+  "_class_name": "AutoencoderKLCogVideoX",
+  "_diffusers_version": "0.31.0.dev0",
+  "act_fn": "silu",
+  "block_out_channels": [
+    128,
+    256,
+    256,
+    512
+  ],
+  "down_block_types": [
+    "CogVideoXDownBlock3D",
+    "CogVideoXDownBlock3D",
+    "CogVideoXDownBlock3D",
+    "CogVideoXDownBlock3D"
+  ],
+  "force_upcast": true,
+  "in_channels": 3,
+  "latent_channels": 16,
+  "latents_mean": null,
+  "latents_std": null,
+  "layers_per_block": 3,
+  "norm_eps": 1e-06,
+  "norm_num_groups": 32,
+  "out_channels": 3,
+  "sample_height": 480,
+  "sample_width": 720,
+  "scaling_factor": 0.7,
+  "shift_factor": null,
+  "temporal_compression_ratio": 4,
+  "up_block_types": [
+    "CogVideoXUpBlock3D",
+    "CogVideoXUpBlock3D",
+    "CogVideoXUpBlock3D",
+    "CogVideoXUpBlock3D"
+  ],
+  "use_post_quant_conv": false,
+  "use_quant_conv": false
+}

custom_nodes/ComfyUI-CogVideoXWrapper/context.py

@@ -0,0 +1,184 @@
+import numpy as np
+from typing import Callable, Optional, List
+
+
+def ordered_halving(val):
+    bin_str = f"{val:064b}"
+    bin_flip = bin_str[::-1]
+    as_int = int(bin_flip, 2)
+
+    return as_int / (1 << 64)
+
+def does_window_roll_over(window: list[int], num_frames: int) -> tuple[bool, int]:
+    prev_val = -1
+    for i, val in enumerate(window):
+        val = val % num_frames
+        if val < prev_val:
+            return True, i
+        prev_val = val
+    return False, -1
+
+def shift_window_to_start(window: list[int], num_frames: int):
+    start_val = window[0]
+    for i in range(len(window)):
+        # 1) subtract each element by start_val to move vals relative to the start of all frames
+        # 2) add num_frames and take modulus to get adjusted vals
+        window[i] = ((window[i] - start_val) + num_frames) % num_frames
+
+def shift_window_to_end(window: list[int], num_frames: int):
+    # 1) shift window to start
+    shift_window_to_start(window, num_frames)
+    end_val = window[-1]
+    end_delta = num_frames - end_val - 1
+    for i in range(len(window)):
+        # 2) add end_delta to each val to slide windows to end
+        window[i] = window[i] + end_delta
+
+def get_missing_indexes(windows: list[list[int]], num_frames: int) -> list[int]:
+    all_indexes = list(range(num_frames))
+    for w in windows:
+        for val in w:
+            try:
+                all_indexes.remove(val)
+            except ValueError:
+                pass
+    return all_indexes
+
+def uniform_looped(
+    step: int = ...,
+    num_steps: Optional[int] = None,
+    num_frames: int = ...,
+    context_size: Optional[int] = None,
+    context_stride: int = 3,
+    context_overlap: int = 4,
+    closed_loop: bool = True,
+):
+    if num_frames <= context_size:
+        yield list(range(num_frames))
+        return
+
+    context_stride = min(context_stride, int(np.ceil(np.log2(num_frames / context_size))) + 1)
+
+    for context_step in 1 << np.arange(context_stride):
+        pad = int(round(num_frames * ordered_halving(step)))
+        for j in range(
+            int(ordered_halving(step) * context_step) + pad,
+            num_frames + pad + (0 if closed_loop else -context_overlap),
+            (context_size * context_step - context_overlap),
+        ):
+            yield [e % num_frames for e in range(j, j + context_size * context_step, context_step)]
+
+#from AnimateDiff-Evolved by Kosinkadink (https://github.com/Kosinkadink/ComfyUI-AnimateDiff-Evolved)
+def uniform_standard(
+    step: int = ...,
+    num_steps: Optional[int] = None,
+    num_frames: int = ...,
+    context_size: Optional[int] = None,
+    context_stride: int = 3,
+    context_overlap: int = 4,
+    closed_loop: bool = True,
+):
+    windows = []
+    if num_frames <= context_size:
+        windows.append(list(range(num_frames)))
+        return windows
+
+    context_stride = min(context_stride, int(np.ceil(np.log2(num_frames / context_size))) + 1)
+
+    for context_step in 1 << np.arange(context_stride):
+        pad = int(round(num_frames * ordered_halving(step)))
+        for j in range(
+            int(ordered_halving(step) * context_step) + pad,
+            num_frames + pad + (0 if closed_loop else -context_overlap),
+            (context_size * context_step - context_overlap),
+        ):
+            windows.append([e % num_frames for e in range(j, j + context_size * context_step, context_step)])
+
+    # now that windows are created, shift any windows that loop, and delete duplicate windows
+    delete_idxs = []
+    win_i = 0
+    while win_i < len(windows):
+        # if window is rolls over itself, need to shift it
+        is_roll, roll_idx = does_window_roll_over(windows[win_i], num_frames)
+        if is_roll:
+            roll_val = windows[win_i][roll_idx]  # roll_val might not be 0 for windows of higher strides
+            shift_window_to_end(windows[win_i], num_frames=num_frames)
+            # check if next window (cyclical) is missing roll_val
+            if roll_val not in windows[(win_i+1) % len(windows)]:
+                # need to insert new window here - just insert window starting at roll_val
+                windows.insert(win_i+1, list(range(roll_val, roll_val + context_size)))
+        # delete window if it's not unique
+        for pre_i in range(0, win_i):
+            if windows[win_i] == windows[pre_i]:
+                delete_idxs.append(win_i)
+                break
+        win_i += 1
+
+    # reverse delete_idxs so that they will be deleted in an order that doesn't break idx correlation
+    delete_idxs.reverse()
+    for i in delete_idxs:
+        windows.pop(i)
+    return windows
+
+def static_standard(
+    step: int = ...,
+    num_steps: Optional[int] = None,
+    num_frames: int = ...,
+    context_size: Optional[int] = None,
+    context_stride: int = 3,
+    context_overlap: int = 4,
+    closed_loop: bool = True,
+):
+    windows = []
+    if num_frames <= context_size:
+        windows.append(list(range(num_frames)))
+        return windows
+    # always return the same set of windows
+    delta = context_size - context_overlap
+    for start_idx in range(0, num_frames, delta):
+        # if past the end of frames, move start_idx back to allow same context_length
+        ending = start_idx + context_size
+        if ending >= num_frames:
+            final_delta = ending - num_frames
+            final_start_idx = start_idx - final_delta
+            windows.append(list(range(final_start_idx, final_start_idx + context_size)))
+            break
+        windows.append(list(range(start_idx, start_idx + context_size)))
+    return windows
+
+def get_context_scheduler(name: str) -> Callable:
+    if name == "uniform_looped":
+        return uniform_looped
+    elif name == "uniform_standard":
+        return uniform_standard
+    elif name == "static_standard":
+        return static_standard
+    else:
+        raise ValueError(f"Unknown context_overlap policy {name}")
+
+
+def get_total_steps(
+    scheduler,
+    timesteps: List[int],
+    num_steps: Optional[int] = None,
+    num_frames: int = ...,
+    context_size: Optional[int] = None,
+    context_stride: int = 3,
+    context_overlap: int = 4,
+    closed_loop: bool = True,
+):
+    return sum(
+        len(
+            list(
+                scheduler(
+                    i,
+                    num_steps,
+                    num_frames,
+                    context_size,
+                    context_stride,
+                    context_overlap,
+                )
+            )
+        )
+        for i in range(len(timesteps))
+    )

custom_nodes/ComfyUI-CogVideoXWrapper/custom_cogvideox_transformer_3d.py

@@ -0,0 +1,779 @@
+# Copyright 2024 The CogVideoX team, Tsinghua University & ZhipuAI and The HuggingFace Team.
+# All rights reserved.
+#
+# Licensed under the Apache License, Version 2.0 (the "License");
+# you may not use this file except in compliance with the License.
+# You may obtain a copy of the License at
+#
+#     http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+
+from typing import Any, Dict, Optional, Tuple, Union
+
+import torch
+from torch import nn
+import torch.nn.functional as F
+
+import numpy as np
+from einops import rearrange
+
+from diffusers.configuration_utils import ConfigMixin, register_to_config
+from diffusers.utils import logging
+from diffusers.utils.torch_utils import maybe_allow_in_graph
+from diffusers.models.attention import Attention, FeedForward
+from diffusers.models.attention_processor import AttentionProcessor
+from diffusers.models.embeddings import TimestepEmbedding, Timesteps
+from diffusers.models.modeling_outputs import Transformer2DModelOutput
+from diffusers.models.modeling_utils import ModelMixin
+from diffusers.models.normalization import AdaLayerNorm, CogVideoXLayerNormZero
+from diffusers.loaders import PeftAdapterMixin
+from diffusers.models.embeddings import apply_rotary_emb
+from .embeddings import CogVideoXPatchEmbed
+
+from .enhance_a_video.enhance import get_feta_scores
+from .enhance_a_video.globals import is_enhance_enabled, set_num_frames
+
+
+logger = logging.get_logger(__name__)  # pylint: disable=invalid-name
+
+try:
+    from sageattention import sageattn
+    SAGEATTN_IS_AVAILABLE = True
+except:
+    SAGEATTN_IS_AVAILABLE = False
+
+from comfy.ldm.modules.attention import optimized_attention
+
+
+def set_attention_func(attention_mode, heads):
+    if attention_mode == "sdpa" or attention_mode == "fused_sdpa":
+        def func(q, k, v, is_causal=False, attn_mask=None):
+            return F.scaled_dot_product_attention(q, k, v, attn_mask=attn_mask, dropout_p=0.0, is_causal=is_causal)
+        return func
+    elif attention_mode == "comfy":
+        def func(q, k, v, is_causal=False, attn_mask=None):
+            return optimized_attention(q, k, v, mask=attn_mask, heads=heads, skip_reshape=True)
+        return func
+
+    elif attention_mode == "sageattn" or attention_mode == "fused_sageattn":
+        @torch.compiler.disable()
+        def func(q, k, v, is_causal=False, attn_mask=None):
+            return sageattn(q.to(v), k.to(v), v, is_causal=is_causal, attn_mask=attn_mask)
+        return func
+    elif attention_mode == "sageattn_qk_int8_pv_fp16_cuda":
+        from sageattention import sageattn_qk_int8_pv_fp16_cuda
+        @torch.compiler.disable()
+        def func(q, k, v, is_causal=False, attn_mask=None):
+            return sageattn_qk_int8_pv_fp16_cuda(q.to(v), k.to(v), v, is_causal=is_causal, attn_mask=attn_mask, pv_accum_dtype="fp32")
+        return func
+    elif attention_mode == "sageattn_qk_int8_pv_fp16_triton":
+        from sageattention import sageattn_qk_int8_pv_fp16_triton
+        @torch.compiler.disable()
+        def func(q, k, v, is_causal=False, attn_mask=None):
+            return sageattn_qk_int8_pv_fp16_triton(q.to(v), k.to(v), v, is_causal=is_causal, attn_mask=attn_mask)
+        return func
+    elif attention_mode == "sageattn_qk_int8_pv_fp8_cuda":
+        from sageattention import sageattn_qk_int8_pv_fp8_cuda
+        @torch.compiler.disable()
+        def func(q, k, v, is_causal=False, attn_mask=None):
+            return sageattn_qk_int8_pv_fp8_cuda(q.to(v), k.to(v), v, is_causal=is_causal, attn_mask=attn_mask, pv_accum_dtype="fp32+fp32")
+        return func
+
+#for fastercache
+def fft(tensor):
+    tensor_fft = torch.fft.fft2(tensor)
+    tensor_fft_shifted = torch.fft.fftshift(tensor_fft)
+    B, C, H, W = tensor.size()
+    radius = min(H, W) // 5
+            
+    Y, X = torch.meshgrid(torch.arange(H), torch.arange(W))
+    center_x, center_y = W // 2, H // 2
+    mask = (X - center_x) ** 2 + (Y - center_y) ** 2 <= radius ** 2
+    low_freq_mask = mask.unsqueeze(0).unsqueeze(0).to(tensor.device)
+    high_freq_mask = ~low_freq_mask
+            
+    low_freq_fft = tensor_fft_shifted * low_freq_mask
+    high_freq_fft = tensor_fft_shifted * high_freq_mask
+
+    return low_freq_fft, high_freq_fft
+
+#for teacache
+def poly1d(coefficients, x):
+    result = torch.zeros_like(x)
+    for i, coeff in enumerate(coefficients):
+        result += coeff * (x ** (len(coefficients) - 1 - i))
+    return result.abs()
+
+#region Attention
+class CogVideoXAttnProcessor2_0:
+    r"""
+    Processor for implementing scaled dot-product attention for the CogVideoX model. It applies a rotary embedding on
+    query and key vectors, but does not include spatial normalization.
+    """
+
+    def __init__(self, attn_func, attention_mode: Optional[str] = None):
+        if not hasattr(F, "scaled_dot_product_attention"):
+            raise ImportError("CogVideoXAttnProcessor requires PyTorch 2.0, to use it, please upgrade PyTorch to 2.0.")
+        self.attention_mode = attention_mode
+        self.attn_func = attn_func
+    def __call__(
+        self,
+        attn: Attention,
+        hidden_states: torch.Tensor,
+        encoder_hidden_states: torch.Tensor,
+        attention_mask: Optional[torch.Tensor] = None,
+        image_rotary_emb: Optional[torch.Tensor] = None,
+    ) -> torch.Tensor:
+        text_seq_length = encoder_hidden_states.size(1)
+
+        hidden_states = torch.cat([encoder_hidden_states, hidden_states], dim=1)
+
+        batch_size, sequence_length, _ = (
+            hidden_states.shape if encoder_hidden_states is None else encoder_hidden_states.shape
+        )
+
+        if attention_mask is not None:
+            attention_mask = attn.prepare_attention_mask(attention_mask, sequence_length, batch_size)
+            attention_mask = attention_mask.view(batch_size, attn.heads, -1, attention_mask.shape[-1])
+
+        if attn.to_q.weight.dtype == torch.float16 or attn.to_q.weight.dtype == torch.bfloat16:
+            hidden_states = hidden_states.to(attn.to_q.weight.dtype)
+
+        if not "fused" in self.attention_mode:
+            query = attn.to_q(hidden_states)
+            key = attn.to_k(hidden_states)
+            value = attn.to_v(hidden_states)
+        else:
+            qkv = attn.to_qkv(hidden_states)
+            split_size = qkv.shape[-1] // 3
+            query, key, value = torch.split(qkv, split_size, dim=-1)
+
+        inner_dim = key.shape[-1]
+        head_dim = inner_dim // attn.heads
+
+        query = query.view(batch_size, -1, attn.heads, head_dim).transpose(1, 2)
+        key = key.view(batch_size, -1, attn.heads, head_dim).transpose(1, 2)
+        value = value.view(batch_size, -1, attn.heads, head_dim).transpose(1, 2)
+
+        if attn.norm_q is not None:
+            query = attn.norm_q(query)
+        if attn.norm_k is not None:
+            key = attn.norm_k(key)
+
+        # Apply RoPE if needed
+        if image_rotary_emb is not None:
+            query[:, :, text_seq_length:] = apply_rotary_emb(query[:, :, text_seq_length:], image_rotary_emb)
+            if not attn.is_cross_attention:
+                key[:, :, text_seq_length:] = apply_rotary_emb(key[:, :, text_seq_length:], image_rotary_emb)
+
+        #feta
+        if is_enhance_enabled():
+            feta_scores = get_feta_scores(attn, query, key, head_dim, text_seq_length)
+                
+        hidden_states = self.attn_func(query, key, value, attn_mask=attention_mask, is_causal=False)
+       
+        if self.attention_mode != "comfy":
+            hidden_states = hidden_states.transpose(1, 2).reshape(batch_size, -1, attn.heads * head_dim)
+
+        # linear proj
+        hidden_states = attn.to_out[0](hidden_states)
+        # dropout
+        hidden_states = attn.to_out[1](hidden_states)
+
+        encoder_hidden_states, hidden_states = hidden_states.split(
+            [text_seq_length, hidden_states.size(1) - text_seq_length], dim=1
+        )
+
+        if is_enhance_enabled():
+            hidden_states *= feta_scores
+
+        return hidden_states, encoder_hidden_states
+
+#region Blocks
+@maybe_allow_in_graph
+class CogVideoXBlock(nn.Module):
+    
+    r"""
+    Transformer block used in [CogVideoX](https://github.com/THUDM/CogVideo) model.
+
+    Parameters:
+        dim (`int`):
+            The number of channels in the input and output.
+        num_attention_heads (`int`):
+            The number of heads to use for multi-head attention.
+        attention_head_dim (`int`):
+            The number of channels in each head.
+        time_embed_dim (`int`):
+            The number of channels in timestep embedding.
+        dropout (`float`, defaults to `0.0`):
+            The dropout probability to use.
+        activation_fn (`str`, defaults to `"gelu-approximate"`):
+            Activation function to be used in feed-forward.
+        attention_bias (`bool`, defaults to `False`):
+            Whether or not to use bias in attention projection layers.
+        qk_norm (`bool`, defaults to `True`):
+            Whether or not to use normalization after query and key projections in Attention.
+        norm_elementwise_affine (`bool`, defaults to `True`):
+            Whether to use learnable elementwise affine parameters for normalization.
+        norm_eps (`float`, defaults to `1e-5`):
+            Epsilon value for normalization layers.
+        final_dropout (`bool` defaults to `False`):
+            Whether to apply a final dropout after the last feed-forward layer.
+        ff_inner_dim (`int`, *optional*, defaults to `None`):
+            Custom hidden dimension of Feed-forward layer. If not provided, `4 * dim` is used.
+        ff_bias (`bool`, defaults to `True`):
+            Whether or not to use bias in Feed-forward layer.
+        attention_out_bias (`bool`, defaults to `True`):
+            Whether or not to use bias in Attention output projection layer.
+    """
+
+    def __init__(
+        self,
+        dim: int,
+        num_attention_heads: int,
+        attention_head_dim: int,
+        time_embed_dim: int,
+        dropout: float = 0.0,
+        activation_fn: str = "gelu-approximate",
+        attention_bias: bool = False,
+        qk_norm: bool = True,
+        norm_elementwise_affine: bool = True,
+        norm_eps: float = 1e-5,
+        final_dropout: bool = True,
+        ff_inner_dim: Optional[int] = None,
+        ff_bias: bool = True,
+        attention_out_bias: bool = True,
+        attention_mode: Optional[str] = "sdpa",
+    ):
+        super().__init__()
+
+        # 1. Self Attention
+        self.norm1 = CogVideoXLayerNormZero(time_embed_dim, dim, norm_elementwise_affine, norm_eps, bias=True)
+
+        attn_func = set_attention_func(attention_mode, num_attention_heads)
+       
+        self.attn1 = Attention(
+            query_dim=dim,
+            dim_head=attention_head_dim,
+            heads=num_attention_heads,
+            qk_norm="layer_norm" if qk_norm else None,
+            eps=1e-6,
+            bias=attention_bias,
+            out_bias=attention_out_bias,
+            processor=CogVideoXAttnProcessor2_0(attn_func, attention_mode=attention_mode),
+        )
+
+        # 2. Feed Forward
+        self.norm2 = CogVideoXLayerNormZero(time_embed_dim, dim, norm_elementwise_affine, norm_eps, bias=True)
+
+        self.ff = FeedForward(
+            dim,
+            dropout=dropout,
+            activation_fn=activation_fn,
+            final_dropout=final_dropout,
+            inner_dim=ff_inner_dim,
+            bias=ff_bias,
+        )
+        self.cached_hidden_states = []
+        self.cached_encoder_hidden_states = []
+        
+    def forward(
+        self,
+        hidden_states: torch.Tensor,
+        encoder_hidden_states: torch.Tensor,
+        temb: torch.Tensor,
+        image_rotary_emb: Optional[Tuple[torch.Tensor, torch.Tensor]] = None,
+        video_flow_feature: Optional[torch.Tensor] = None,
+        fuser=None,
+        block_use_fastercache=False,
+        fastercache_counter=0,
+        fastercache_start_step=15,
+        fastercache_device="cuda:0",
+    ) -> torch.Tensor:
+        #print("hidden_states in block: ", hidden_states.shape) #1.5: torch.Size([2, 3200, 3072]) 10.: torch.Size([2, 6400, 3072])
+        text_seq_length = encoder_hidden_states.size(1)
+
+        # norm & modulate
+        norm_hidden_states, norm_encoder_hidden_states, gate_msa, enc_gate_msa = self.norm1(
+            hidden_states, encoder_hidden_states, temb
+        )
+        #print("norm_hidden_states in block: ", norm_hidden_states.shape) #torch.Size([2, 3200, 3072])
+      
+        # Tora Motion-guidance Fuser
+        if video_flow_feature is not None:
+            H, W = video_flow_feature.shape[-2:]
+            T = norm_hidden_states.shape[1] // H // W
+            h = rearrange(norm_hidden_states, "B (T H W) C -> (B T) C H W", H=H, W=W)
+            h = fuser(h, video_flow_feature.to(h), T=T)
+            norm_hidden_states = rearrange(h, "(B T) C H W ->  B (T H W) C", T=T)
+            del h, fuser        
+        
+        #region fastercache
+        if block_use_fastercache:
+            B = norm_hidden_states.shape[0]
+            if fastercache_counter >= fastercache_start_step + 3 and fastercache_counter%3!=0 and self.cached_hidden_states[-1].shape[0] >= B:
+                attn_hidden_states = (
+                    self.cached_hidden_states[1][:B] + 
+                    (self.cached_hidden_states[1][:B] - self.cached_hidden_states[0][:B]) 
+                    * 0.3
+                    ).to(norm_hidden_states.device, non_blocking=True)
+                attn_encoder_hidden_states = (
+                    self.cached_encoder_hidden_states[1][:B] + 
+                    (self.cached_encoder_hidden_states[1][:B] - self.cached_encoder_hidden_states[0][:B])
+                    * 0.3
+                    ).to(norm_hidden_states.device, non_blocking=True)
+            else:
+                attn_hidden_states, attn_encoder_hidden_states = self.attn1(
+                    hidden_states=norm_hidden_states,
+                    encoder_hidden_states=norm_encoder_hidden_states,
+                    image_rotary_emb=image_rotary_emb,
+                )
+                if fastercache_counter == fastercache_start_step:
+                    self.cached_hidden_states = [attn_hidden_states.to(fastercache_device), attn_hidden_states.to(fastercache_device)]
+                    self.cached_encoder_hidden_states = [attn_encoder_hidden_states.to(fastercache_device), attn_encoder_hidden_states.to(fastercache_device)]
+                elif fastercache_counter > fastercache_start_step:
+                    self.cached_hidden_states[-1].copy_(attn_hidden_states.to(fastercache_device))
+                    self.cached_encoder_hidden_states[-1].copy_(attn_encoder_hidden_states.to(fastercache_device))
+        else:
+            attn_hidden_states, attn_encoder_hidden_states = self.attn1(
+                hidden_states=norm_hidden_states,
+                encoder_hidden_states=norm_encoder_hidden_states,
+                image_rotary_emb=image_rotary_emb
+            )
+        
+        hidden_states = hidden_states + gate_msa * attn_hidden_states
+        encoder_hidden_states = encoder_hidden_states + enc_gate_msa * attn_encoder_hidden_states
+
+        # norm & modulate
+       
+        norm_hidden_states, norm_encoder_hidden_states, gate_ff, enc_gate_ff = self.norm2(
+            hidden_states, encoder_hidden_states, temb
+        )
+
+        # feed-forward
+        norm_hidden_states = torch.cat([norm_encoder_hidden_states, norm_hidden_states], dim=1)
+        ff_output = self.ff(norm_hidden_states)
+
+        hidden_states = hidden_states + gate_ff * ff_output[:, text_seq_length:]
+        encoder_hidden_states = encoder_hidden_states + enc_gate_ff * ff_output[:, :text_seq_length]
+
+        return hidden_states, encoder_hidden_states
+
+#region Transformer
+class CogVideoXTransformer3DModel(ModelMixin, ConfigMixin, PeftAdapterMixin):
+    """
+    A Transformer model for video-like data in [CogVideoX](https://github.com/THUDM/CogVideo).
+
+    Parameters:
+        num_attention_heads (`int`, defaults to `30`):
+            The number of heads to use for multi-head attention.
+        attention_head_dim (`int`, defaults to `64`):
+            The number of channels in each head.
+        in_channels (`int`, defaults to `16`):
+            The number of channels in the input.
+        out_channels (`int`, *optional*, defaults to `16`):
+            The number of channels in the output.
+        flip_sin_to_cos (`bool`, defaults to `True`):
+            Whether to flip the sin to cos in the time embedding.
+        time_embed_dim (`int`, defaults to `512`):
+            Output dimension of timestep embeddings.
+        text_embed_dim (`int`, defaults to `4096`):
+            Input dimension of text embeddings from the text encoder.
+        num_layers (`int`, defaults to `30`):
+            The number of layers of Transformer blocks to use.
+        dropout (`float`, defaults to `0.0`):
+            The dropout probability to use.
+        attention_bias (`bool`, defaults to `True`):
+            Whether or not to use bias in the attention projection layers.
+        sample_width (`int`, defaults to `90`):
+            The width of the input latents.
+        sample_height (`int`, defaults to `60`):
+            The height of the input latents.
+        sample_frames (`int`, defaults to `49`):
+            The number of frames in the input latents. Note that this parameter was incorrectly initialized to 49
+            instead of 13 because CogVideoX processed 13 latent frames at once in its default and recommended settings,
+            but cannot be changed to the correct value to ensure backwards compatibility. To create a transformer with
+            K latent frames, the correct value to pass here would be: ((K - 1) * temporal_compression_ratio + 1).
+        patch_size (`int`, defaults to `2`):
+            The size of the patches to use in the patch embedding layer.
+        temporal_compression_ratio (`int`, defaults to `4`):
+            The compression ratio across the temporal dimension. See documentation for `sample_frames`.
+        max_text_seq_length (`int`, defaults to `226`):
+            The maximum sequence length of the input text embeddings.
+        activation_fn (`str`, defaults to `"gelu-approximate"`):
+            Activation function to use in feed-forward.
+        timestep_activation_fn (`str`, defaults to `"silu"`):
+            Activation function to use when generating the timestep embeddings.
+        norm_elementwise_affine (`bool`, defaults to `True`):
+            Whether or not to use elementwise affine in normalization layers.
+        norm_eps (`float`, defaults to `1e-5`):
+            The epsilon value to use in normalization layers.
+        spatial_interpolation_scale (`float`, defaults to `1.875`):
+            Scaling factor to apply in 3D positional embeddings across spatial dimensions.
+        temporal_interpolation_scale (`float`, defaults to `1.0`):
+            Scaling factor to apply in 3D positional embeddings across temporal dimensions.
+    """
+
+    _supports_gradient_checkpointing = True
+
+    @register_to_config
+    def __init__(
+        self,
+        num_attention_heads: int = 30,
+        attention_head_dim: int = 64,
+        in_channels: int = 16,
+        out_channels: Optional[int] = 16,
+        flip_sin_to_cos: bool = True,
+        freq_shift: int = 0,
+        time_embed_dim: int = 512,
+        ofs_embed_dim: Optional[int] = None,
+        text_embed_dim: int = 4096,
+        num_layers: int = 30,
+        dropout: float = 0.0,
+        attention_bias: bool = True,
+        sample_width: int = 90,
+        sample_height: int = 60,
+        sample_frames: int = 49,
+        patch_size: int = 2,
+        patch_size_t: int = None,
+        temporal_compression_ratio: int = 4,
+        max_text_seq_length: int = 226,
+        activation_fn: str = "gelu-approximate",
+        timestep_activation_fn: str = "silu",
+        norm_elementwise_affine: bool = True,
+        norm_eps: float = 1e-5,
+        spatial_interpolation_scale: float = 1.875,
+        temporal_interpolation_scale: float = 1.0,
+        use_rotary_positional_embeddings: bool = False,
+        use_learned_positional_embeddings: bool = False,
+        patch_bias: bool = True,
+        attention_mode: Optional[str] = "sdpa",
+    ):
+        super().__init__()
+        inner_dim = num_attention_heads * attention_head_dim
+
+        if not use_rotary_positional_embeddings and use_learned_positional_embeddings:
+            raise ValueError(
+                "There are no CogVideoX checkpoints available with disable rotary embeddings and learned positional "
+                "embeddings. If you're using a custom model and/or believe this should be supported, please open an "
+                "issue at https://github.com/huggingface/diffusers/issues."
+            )
+
+        # 1. Patch embedding
+        self.patch_embed = CogVideoXPatchEmbed(
+            patch_size=patch_size,
+            patch_size_t=patch_size_t,
+            in_channels=in_channels,
+            embed_dim=inner_dim,
+            text_embed_dim=text_embed_dim,
+            bias=patch_bias,
+            sample_width=sample_width,
+            sample_height=sample_height,
+            sample_frames=sample_frames,
+            temporal_compression_ratio=temporal_compression_ratio,
+            max_text_seq_length=max_text_seq_length,
+            spatial_interpolation_scale=spatial_interpolation_scale,
+            temporal_interpolation_scale=temporal_interpolation_scale,
+            use_positional_embeddings=not use_rotary_positional_embeddings,
+            use_learned_positional_embeddings=use_learned_positional_embeddings,
+        )
+        self.embedding_dropout = nn.Dropout(dropout)
+
+        # 2. Time embeddings
+        self.time_proj = Timesteps(inner_dim, flip_sin_to_cos, freq_shift)
+        self.time_embedding = TimestepEmbedding(inner_dim, time_embed_dim, timestep_activation_fn)
+
+        self.ofs_proj = None
+        self.ofs_embedding = None
+
+        if ofs_embed_dim:
+            self.ofs_proj = Timesteps(ofs_embed_dim, flip_sin_to_cos, freq_shift)
+            self.ofs_embedding = TimestepEmbedding(ofs_embed_dim, ofs_embed_dim, timestep_activation_fn) # same as time embeddings, for ofs
+
+        # 3. Define spatio-temporal transformers blocks
+        self.transformer_blocks = nn.ModuleList(
+            [
+                CogVideoXBlock(
+                    dim=inner_dim,
+                    num_attention_heads=num_attention_heads,
+                    attention_head_dim=attention_head_dim,
+                    time_embed_dim=time_embed_dim,
+                    dropout=dropout,
+                    activation_fn=activation_fn,
+                    attention_bias=attention_bias,
+                    attention_mode=attention_mode,
+                    norm_elementwise_affine=norm_elementwise_affine,
+                    norm_eps=norm_eps,
+                )
+                for _ in range(num_layers)
+            ]
+        )
+        self.norm_final = nn.LayerNorm(inner_dim, norm_eps, norm_elementwise_affine)
+
+        # 4. Output blocks
+        self.norm_out = AdaLayerNorm(
+            embedding_dim=time_embed_dim,
+            output_dim=2 * inner_dim,
+            norm_elementwise_affine=norm_elementwise_affine,
+            norm_eps=norm_eps,
+            chunk_dim=1,
+        )
+        if patch_size_t is None:
+            # For CogVideox 1.0
+            output_dim = patch_size * patch_size * out_channels
+        else:
+            # For CogVideoX 1.5
+            output_dim = patch_size * patch_size * patch_size_t * out_channels
+
+        self.proj_out = nn.Linear(inner_dim, output_dim)
+
+        self.gradient_checkpointing = False
+
+        self.attention_mode = attention_mode
+
+        #tora
+        self.fuser_list = None
+
+        #fastercache
+        self.use_fastercache = False
+        self.fastercache_counter = 0
+        self.fastercache_start_step = 15
+        self.fastercache_lf_step = 40
+        self.fastercache_hf_step = 30
+        self.fastercache_device = "cuda"
+        self.fastercache_num_blocks_to_cache = len(self.transformer_blocks)
+        
+        #teacache
+        self.use_teacache = False
+        self.teacache_rel_l1_thresh = 0.0
+        if not self.config.use_rotary_positional_embeddings:
+            #CogVideoX-2B
+            self.teacache_coefficients = [-3.10658903e+01, 2.54732368e+01, -5.92380459e+00, 1.75769064e+00, -3.61568434e-03]
+        else:
+            #CogVideoX-5B
+            self.teacache_coefficients = [-1.53880483e+03, 8.43202495e+02, -1.34363087e+02, 7.97131516e+00, -5.23162339e-02]
+        
+
+    def _set_gradient_checkpointing(self, module, value=False):
+        self.gradient_checkpointing = value
+    #region forward
+    def forward(
+        self,
+        hidden_states: torch.Tensor,
+        encoder_hidden_states: torch.Tensor,
+        timestep: Union[int, float, torch.LongTensor],
+        timestep_cond: Optional[torch.Tensor] = None,
+        ofs: Optional[Union[int, float, torch.LongTensor]] = None,
+        image_rotary_emb: Optional[Tuple[torch.Tensor, torch.Tensor]] = None,
+        controlnet_states: torch.Tensor = None,
+        controlnet_weights: Optional[Union[float, int, list, np.ndarray, torch.FloatTensor]] = 1.0,
+        video_flow_features: Optional[torch.Tensor] = None,
+        return_dict: bool = True,
+    ):
+        batch_size, num_frames, channels, height, width = hidden_states.shape
+
+        set_num_frames(num_frames) #enhance a video global
+   
+        # 1. Time embedding
+        timesteps = timestep
+        t_emb = self.time_proj(timesteps)
+
+        # timesteps does not contain any weights and will always return f32 tensors
+        # but time_embedding might actually be running in fp16. so we need to cast here.
+        # there might be better ways to encapsulate this.
+        t_emb = t_emb.to(dtype=hidden_states.dtype)
+
+        emb = self.time_embedding(t_emb, timestep_cond)
+        if self.ofs_embedding is not None: #1.5 I2V
+            ofs_emb = self.ofs_proj(ofs)
+            ofs_emb = ofs_emb.to(dtype=hidden_states.dtype)
+            ofs_emb = self.ofs_embedding(ofs_emb)
+            emb = emb + ofs_emb
+
+        # 2. Patch embedding
+        p = self.config.patch_size
+        p_t = self.config.patch_size_t
+
+        #print("hidden_states before patch_embedding", hidden_states.shape) #torch.Size([2, 4, 16, 60, 90])
+        
+        hidden_states = self.patch_embed(encoder_hidden_states, hidden_states)
+        #print("hidden_states after patch_embedding", hidden_states.shape) #1.5: torch.Size([2, 2926, 3072]) #1.0: torch.Size([2, 5626, 3072])
+        hidden_states = self.embedding_dropout(hidden_states)
+
+        text_seq_length = encoder_hidden_states.shape[1]
+        encoder_hidden_states = hidden_states[:, :text_seq_length]
+        hidden_states = hidden_states[:, text_seq_length:]
+        #print("hidden_states after split", hidden_states.shape) #1.5: torch.Size([2, 2700, 3072]) #1.0: torch.Size([2, 5400, 3072])
+      
+        if self.use_fastercache:
+            self.fastercache_counter+=1
+        if self.fastercache_counter >= self.fastercache_start_step + 3 and self.fastercache_counter % 5 !=0:
+            # 3. Transformer blocks
+            for i, block in enumerate(self.transformer_blocks):
+                hidden_states, encoder_hidden_states = block(
+                    hidden_states=hidden_states[:1],
+                    encoder_hidden_states=encoder_hidden_states[:1],
+                    temb=emb[:1],
+                    image_rotary_emb=image_rotary_emb,
+                    video_flow_feature=video_flow_features[i][:1] if video_flow_features is not None else None,
+                    fuser = self.fuser_list[i] if self.fuser_list is not None else None,
+                    block_use_fastercache = i <= self.fastercache_num_blocks_to_cache,
+                    fastercache_counter = self.fastercache_counter,
+                    fastercache_start_step = self.fastercache_start_step,
+                    fastercache_device = self.fastercache_device
+                )
+
+                if (controlnet_states is not None) and (i < len(controlnet_states)):
+                    controlnet_states_block = controlnet_states[i]
+                    controlnet_block_weight = 1.0
+                    if isinstance(controlnet_weights, (list, np.ndarray)) or torch.is_tensor(controlnet_weights):
+                        controlnet_block_weight = controlnet_weights[i]
+                    elif isinstance(controlnet_weights, (float, int)):
+                        controlnet_block_weight = controlnet_weights
+                    
+                    hidden_states = hidden_states + controlnet_states_block * controlnet_block_weight
+                    
+            if not self.config.use_rotary_positional_embeddings:
+                # CogVideoX-2B
+                hidden_states = self.norm_final(hidden_states)
+            else:
+                # CogVideoX-5B
+                hidden_states = torch.cat([encoder_hidden_states, hidden_states], dim=1)
+                hidden_states = self.norm_final(hidden_states)
+                hidden_states = hidden_states[:, text_seq_length:]
+
+            # 4. Final block
+            hidden_states = self.norm_out(hidden_states, temb=emb[:1])
+            hidden_states = self.proj_out(hidden_states)
+
+            # 5. Unpatchify
+            # Note: we use `-1` instead of `channels`:
+            #   - It is okay to `channels` use for CogVideoX-2b and CogVideoX-5b (number of input channels is equal to output channels)
+            #   - However, for CogVideoX-5b-I2V also takes concatenated input image latents (number of input channels is twice the output channels)
+            
+            if p_t is None:
+                output = hidden_states.reshape(1, num_frames, height // p, width // p, -1, p, p)
+                output = output.permute(0, 1, 4, 2, 5, 3, 6).flatten(5, 6).flatten(3, 4)
+            else:
+                output = hidden_states.reshape(
+                    1, (num_frames + p_t - 1) // p_t, height // p, width // p, -1, p_t, p, p
+                )
+                output = output.permute(0, 1, 5, 4, 2, 6, 3, 7).flatten(6, 7).flatten(4, 5).flatten(1, 2)
+            
+            (bb, tt, cc, hh, ww) = output.shape
+            cond = rearrange(output, "B T C H W -> (B T) C H W", B=bb, C=cc, T=tt, H=hh, W=ww)
+            lf_c, hf_c = fft(cond.float())
+            #lf_step = 40
+            #hf_step = 30
+            if self.fastercache_counter <= self.fastercache_lf_step:
+                self.delta_lf = self.delta_lf * 1.1
+            if self.fastercache_counter >= self.fastercache_hf_step:
+                self.delta_hf = self.delta_hf * 1.1
+   
+            new_hf_uc = self.delta_hf + hf_c
+            new_lf_uc = self.delta_lf + lf_c
+
+            combine_uc = new_lf_uc + new_hf_uc
+            combined_fft = torch.fft.ifftshift(combine_uc)
+            recovered_uncond = torch.fft.ifft2(combined_fft).real
+            recovered_uncond = rearrange(recovered_uncond.to(output.dtype), "(B T) C H W -> B T C H W", B=bb, C=cc, T=tt, H=hh, W=ww)
+            output = torch.cat([output, recovered_uncond])
+        else:
+            if self.use_teacache:
+                if not hasattr(self, 'accumulated_rel_l1_distance'):
+                    should_calc = True
+                    self.accumulated_rel_l1_distance = 0
+                else:                    
+                    self.accumulated_rel_l1_distance += poly1d(self.teacache_coefficients, ((emb-self.previous_modulated_input).abs().mean() / self.previous_modulated_input.abs().mean()))
+                    if self.accumulated_rel_l1_distance < self.teacache_rel_l1_thresh:
+                        should_calc = False
+                        self.teacache_counter += 1
+                    else:
+                        should_calc = True
+                        self.accumulated_rel_l1_distance = 0
+                #print("self.accumulated_rel_l1_distance ", self.accumulated_rel_l1_distance)
+                self.previous_modulated_input = emb
+                if not should_calc:
+                    hidden_states += self.previous_residual
+                    encoder_hidden_states += self.previous_residual_encoder
+                    
+            if not self.use_teacache or (self.use_teacache and should_calc):
+                if self.use_teacache:
+                    ori_hidden_states = hidden_states.clone()
+                    ori_encoder_hidden_states = encoder_hidden_states.clone()
+                for i, block in enumerate(self.transformer_blocks):
+                    hidden_states, encoder_hidden_states = block(
+                        hidden_states=hidden_states,
+                        encoder_hidden_states=encoder_hidden_states,
+                        temb=emb,
+                        image_rotary_emb=image_rotary_emb,
+                        video_flow_feature=video_flow_features[i] if video_flow_features is not None else None,
+                        fuser = self.fuser_list[i] if self.fuser_list is not None else None,
+                        block_use_fastercache = i <= self.fastercache_num_blocks_to_cache,
+                        fastercache_counter = self.fastercache_counter,
+                        fastercache_start_step = self.fastercache_start_step,
+                        fastercache_device = self.fastercache_device
+                    )
+
+                    #controlnet
+                    if (controlnet_states is not None) and (i < len(controlnet_states)):
+                        controlnet_states_block = controlnet_states[i]
+                        controlnet_block_weight = 1.0
+                        if isinstance(controlnet_weights, (list, np.ndarray)) or torch.is_tensor(controlnet_weights):
+                            controlnet_block_weight = controlnet_weights[i]
+                            print(controlnet_block_weight)
+                        elif isinstance(controlnet_weights, (float, int)):
+                            controlnet_block_weight = controlnet_weights                    
+                        hidden_states = hidden_states + controlnet_states_block * controlnet_block_weight
+
+                if self.use_teacache:
+                    self.previous_residual = hidden_states - ori_hidden_states
+                    self.previous_residual_encoder = encoder_hidden_states - ori_encoder_hidden_states
+                    
+            if not self.config.use_rotary_positional_embeddings:
+                # CogVideoX-2B
+                hidden_states = self.norm_final(hidden_states)
+            else:
+                # CogVideoX-5B
+                hidden_states = torch.cat([encoder_hidden_states, hidden_states], dim=1)
+                hidden_states = self.norm_final(hidden_states)
+                hidden_states = hidden_states[:, text_seq_length:]
+
+            # 4. Final block
+            hidden_states = self.norm_out(hidden_states, temb=emb)
+            hidden_states = self.proj_out(hidden_states)
+
+            # 5. Unpatchify
+            # Note: we use `-1` instead of `channels`:
+            #   - It is okay to `channels` use for CogVideoX-2b and CogVideoX-5b (number of input channels is equal to output channels)
+            #   - However, for CogVideoX-5b-I2V also takes concatenated input image latents (number of input channels is twice the output channels)
+           
+            if p_t is None:
+                output = hidden_states.reshape(batch_size, num_frames, height // p, width // p, -1, p, p)
+                output = output.permute(0, 1, 4, 2, 5, 3, 6).flatten(5, 6).flatten(3, 4)
+            else:
+                output = hidden_states.reshape(
+                    batch_size, (num_frames + p_t - 1) // p_t, height // p, width // p, -1, p_t, p, p
+                )
+                output = output.permute(0, 1, 5, 4, 2, 6, 3, 7).flatten(6, 7).flatten(4, 5).flatten(1, 2)
+
+            if self.fastercache_counter >= self.fastercache_start_step + 1: 
+                (bb, tt, cc, hh, ww) = output.shape
+                cond = rearrange(output[0:1].float(), "B T C H W -> (B T) C H W", B=bb//2, C=cc, T=tt, H=hh, W=ww)
+                uncond = rearrange(output[1:2].float(), "B T C H W -> (B T) C H W", B=bb//2, C=cc, T=tt, H=hh, W=ww)
+
+                lf_c, hf_c = fft(cond)
+                lf_uc, hf_uc = fft(uncond)
+
+                self.delta_lf = lf_uc - lf_c
+                self.delta_hf = hf_uc - hf_c
+
+        if not return_dict:
+            return (output,)
+        return Transformer2DModelOutput(sample=output)
+    

custom_nodes/ComfyUI-CogVideoXWrapper/embeddings.py

@@ -0,0 +1,226 @@
+import torch
+import torch.nn as nn
+import numpy as np
+from typing import Tuple, Union, Optional
+from diffusers.models.embeddings import get_3d_sincos_pos_embed, get_1d_rotary_pos_embed
+
+
+class CogVideoXPatchEmbed(nn.Module):
+    def __init__(
+        self,
+        patch_size: int = 2,
+        patch_size_t: Optional[int] = None,
+        in_channels: int = 16,
+        embed_dim: int = 1920,
+        text_embed_dim: int = 4096,
+        bias: bool = True,
+        sample_width: int = 90,
+        sample_height: int = 60,
+        sample_frames: int = 49,
+        temporal_compression_ratio: int = 4,
+        max_text_seq_length: int = 226,
+        spatial_interpolation_scale: float = 1.875,
+        temporal_interpolation_scale: float = 1.0,
+        use_positional_embeddings: bool = True,
+        use_learned_positional_embeddings: bool = True,
+    ) -> None:
+        super().__init__()
+
+        self.patch_size = patch_size
+        self.patch_size_t = patch_size_t
+        self.embed_dim = embed_dim
+        self.sample_height = sample_height
+        self.sample_width = sample_width
+        self.sample_frames = sample_frames
+        self.temporal_compression_ratio = temporal_compression_ratio
+        self.max_text_seq_length = max_text_seq_length
+        self.spatial_interpolation_scale = spatial_interpolation_scale
+        self.temporal_interpolation_scale = temporal_interpolation_scale
+        self.use_positional_embeddings = use_positional_embeddings
+        self.use_learned_positional_embeddings = use_learned_positional_embeddings
+
+        if patch_size_t is None:
+            # CogVideoX 1.0 checkpoints
+            self.proj = nn.Conv2d(
+                in_channels, embed_dim, kernel_size=(patch_size, patch_size), stride=patch_size, bias=bias
+            )
+        else:
+            # CogVideoX 1.5 checkpoints
+            self.proj = nn.Linear(in_channels * patch_size * patch_size * patch_size_t, embed_dim)
+
+        self.text_proj = nn.Linear(text_embed_dim, embed_dim)
+
+        if use_positional_embeddings or use_learned_positional_embeddings:
+            persistent = use_learned_positional_embeddings
+            pos_embedding = self._get_positional_embeddings(sample_height, sample_width, sample_frames)
+            self.register_buffer("pos_embedding", pos_embedding, persistent=persistent)
+
+    def _get_positional_embeddings(self, sample_height: int, sample_width: int, sample_frames: int) -> torch.Tensor:
+        post_patch_height = sample_height // self.patch_size
+        post_patch_width = sample_width // self.patch_size
+        post_time_compression_frames = (sample_frames - 1) // self.temporal_compression_ratio + 1
+        num_patches = post_patch_height * post_patch_width * post_time_compression_frames
+
+        pos_embedding = get_3d_sincos_pos_embed(
+            self.embed_dim,
+            (post_patch_width, post_patch_height),
+            post_time_compression_frames,
+            self.spatial_interpolation_scale,
+            self.temporal_interpolation_scale,
+        )
+        pos_embedding = torch.from_numpy(pos_embedding).flatten(0, 1)
+        joint_pos_embedding = torch.zeros(
+            1, self.max_text_seq_length + num_patches, self.embed_dim, requires_grad=False
+        )
+        joint_pos_embedding.data[:, self.max_text_seq_length :].copy_(pos_embedding)
+
+        return joint_pos_embedding
+
+    def forward(self, text_embeds: torch.Tensor, image_embeds: torch.Tensor):
+        r"""
+        Args:
+            text_embeds (`torch.Tensor`):
+                Input text embeddings. Expected shape: (batch_size, seq_length, embedding_dim).
+            image_embeds (`torch.Tensor`):
+                Input image embeddings. Expected shape: (batch_size, num_frames, channels, height, width).
+        """
+        text_embeds = self.text_proj(text_embeds)
+
+        batch_size, num_frames, channels, height, width = image_embeds.shape
+
+        if self.patch_size_t is None:
+            image_embeds = image_embeds.reshape(-1, channels, height, width)
+            image_embeds = self.proj(image_embeds)
+            image_embeds = image_embeds.view(batch_size, num_frames, *image_embeds.shape[1:])
+            image_embeds = image_embeds.flatten(3).transpose(2, 3)  # [batch, num_frames, height x width, channels]
+            image_embeds = image_embeds.flatten(1, 2)  # [batch, num_frames x height x width, channels]
+        else:
+            p = self.patch_size
+            p_t = self.patch_size_t
+
+            image_embeds = image_embeds.permute(0, 1, 3, 4, 2)
+            image_embeds = image_embeds.reshape(
+                batch_size, num_frames // p_t, p_t, height // p, p, width // p, p, channels
+            )
+            image_embeds = image_embeds.permute(0, 1, 3, 5, 7, 2, 4, 6).flatten(4, 7).flatten(1, 3)
+            image_embeds = self.proj(image_embeds)
+
+        embeds = torch.cat(
+            [text_embeds, image_embeds], dim=1
+        ).contiguous()  # [batch, seq_length + num_frames x height x width, channels]
+
+        if self.use_positional_embeddings or self.use_learned_positional_embeddings:
+            if self.use_learned_positional_embeddings and (self.sample_width != width or self.sample_height != height):
+                raise ValueError(
+                    "It is currently not possible to generate videos at a different resolution that the defaults. This should only be the case with 'THUDM/CogVideoX-5b-I2V'."
+                    "If you think this is incorrect, please open an issue at https://github.com/huggingface/diffusers/issues."
+                )
+
+            pre_time_compression_frames = (num_frames - 1) * self.temporal_compression_ratio + 1
+
+            if (
+                self.sample_height != height
+                or self.sample_width != width
+                or self.sample_frames != pre_time_compression_frames
+            ):
+                pos_embedding = self._get_positional_embeddings(height, width, pre_time_compression_frames)
+                pos_embedding = pos_embedding.to(embeds.device, dtype=embeds.dtype)
+            else:
+                pos_embedding = self.pos_embedding
+
+            embeds = embeds + pos_embedding
+
+        return embeds
+
+def get_3d_rotary_pos_embed(
+    embed_dim,
+    crops_coords,
+    grid_size,
+    temporal_size,
+    theta: int = 10000,
+    use_real: bool = True,
+    grid_type: str = "linspace",
+    max_size: Optional[Tuple[int, int]] = None,
+) -> Union[torch.Tensor, Tuple[torch.Tensor, torch.Tensor]]:
+    """
+    RoPE for video tokens with 3D structure.
+
+    Args:
+    embed_dim: (`int`):
+        The embedding dimension size, corresponding to hidden_size_head.
+    crops_coords (`Tuple[int]`):
+        The top-left and bottom-right coordinates of the crop.
+    grid_size (`Tuple[int]`):
+        The grid size of the spatial positional embedding (height, width).
+    temporal_size (`int`):
+        The size of the temporal dimension.
+    theta (`float`):
+        Scaling factor for frequency computation.
+    grid_type (`str`):
+        Whether to use "linspace" or "slice" to compute grids.
+
+    Returns:
+        `torch.Tensor`: positional embedding with shape `(temporal_size * grid_size[0] * grid_size[1], embed_dim/2)`.
+    """
+    if use_real is not True:
+        raise ValueError(" `use_real = False` is not currently supported for get_3d_rotary_pos_embed")
+
+    if grid_type == "linspace":
+        start, stop = crops_coords
+        grid_size_h, grid_size_w = grid_size
+        grid_h = np.linspace(start[0], stop[0], grid_size_h, endpoint=False, dtype=np.float32)
+        grid_w = np.linspace(start[1], stop[1], grid_size_w, endpoint=False, dtype=np.float32)
+        grid_t = np.arange(temporal_size, dtype=np.float32)
+        grid_t = np.linspace(0, temporal_size, temporal_size, endpoint=False, dtype=np.float32)
+    elif grid_type == "slice":
+        max_h, max_w = max_size
+        grid_size_h, grid_size_w = grid_size
+        grid_h = np.arange(max_h, dtype=np.float32)
+        grid_w = np.arange(max_w, dtype=np.float32)
+        grid_t = np.arange(temporal_size, dtype=np.float32)
+    else:
+        raise ValueError("Invalid value passed for `grid_type`.")
+
+    # Compute dimensions for each axis
+    dim_t = embed_dim // 4
+    dim_h = embed_dim // 8 * 3
+    dim_w = embed_dim // 8 * 3
+
+    # Temporal frequencies
+    freqs_t = get_1d_rotary_pos_embed(dim_t, grid_t, use_real=True)
+    # Spatial frequencies for height and width
+    freqs_h = get_1d_rotary_pos_embed(dim_h, grid_h, use_real=True)
+    freqs_w = get_1d_rotary_pos_embed(dim_w, grid_w, use_real=True)
+
+    # BroadCast and concatenate temporal and spaial frequencie (height and width) into a 3d tensor
+    def combine_time_height_width(freqs_t, freqs_h, freqs_w):
+        freqs_t = freqs_t[:, None, None, :].expand(
+            -1, grid_size_h, grid_size_w, -1
+        )  # temporal_size, grid_size_h, grid_size_w, dim_t
+        freqs_h = freqs_h[None, :, None, :].expand(
+            temporal_size, -1, grid_size_w, -1
+        )  # temporal_size, grid_size_h, grid_size_2, dim_h
+        freqs_w = freqs_w[None, None, :, :].expand(
+            temporal_size, grid_size_h, -1, -1
+        )  # temporal_size, grid_size_h, grid_size_2, dim_w
+
+        freqs = torch.cat(
+            [freqs_t, freqs_h, freqs_w], dim=-1
+        )  # temporal_size, grid_size_h, grid_size_w, (dim_t + dim_h + dim_w)
+        freqs = freqs.view(
+            temporal_size * grid_size_h * grid_size_w, -1
+        )  # (temporal_size * grid_size_h * grid_size_w), (dim_t + dim_h + dim_w)
+        return freqs
+
+    t_cos, t_sin = freqs_t  # both t_cos and t_sin has shape: temporal_size, dim_t
+    h_cos, h_sin = freqs_h  # both h_cos and h_sin has shape: grid_size_h, dim_h
+    w_cos, w_sin = freqs_w  # both w_cos and w_sin has shape: grid_size_w, dim_w
+
+    if grid_type == "slice":
+        t_cos, t_sin = t_cos[:temporal_size], t_sin[:temporal_size]
+        h_cos, h_sin = h_cos[:grid_size_h], h_sin[:grid_size_h]
+        w_cos, w_sin = w_cos[:grid_size_w], w_sin[:grid_size_w]
+
+    cos = combine_time_height_width(t_cos, h_cos, w_cos)
+    sin = combine_time_height_width(t_sin, h_sin, w_sin)
+    return cos, sin

custom_nodes/ComfyUI-CogVideoXWrapper/enhance_a_video/enhance.py

@@ -0,0 +1,82 @@
+import torch
+from einops import rearrange
+from diffusers.models.attention import Attention
+from .globals import get_enhance_weight, get_num_frames
+
+# def get_feta_scores(query, key):
+#     img_q, img_k = query, key
+   
+#     num_frames = get_num_frames()
+    
+#     B, S, N, C = img_q.shape
+
+#     # Calculate spatial dimension
+#     spatial_dim = S // num_frames
+    
+#     # Add time dimension between spatial and head dims
+#     query_image = img_q.reshape(B, spatial_dim, num_frames, N, C)
+#     key_image = img_k.reshape(B, spatial_dim, num_frames, N, C)
+    
+#     # Expand time dimension
+#     query_image = query_image.expand(-1, -1, num_frames, -1, -1)  # [B, S, T, N, C]
+#     key_image = key_image.expand(-1, -1, num_frames, -1, -1)      # [B, S, T, N, C]
+    
+#     # Reshape to match feta_score input format: [(B S) N T C]
+#     query_image = rearrange(query_image, "b s t n c -> (b s) n t c")  #torch.Size([3200, 24, 5, 128])
+#     key_image = rearrange(key_image, "b s t n c -> (b s) n t c")
+    
+#     return feta_score(query_image, key_image, C, num_frames)
+ 
+def get_feta_scores(
+        attn: Attention,
+        query: torch.Tensor,
+        key: torch.Tensor,
+        head_dim: int,
+        text_seq_length: int,
+    ) -> torch.Tensor:
+        num_frames = get_num_frames()
+        spatial_dim = int((query.shape[2] - text_seq_length) / num_frames)
+
+        query_image = rearrange(
+            query[:, :, text_seq_length:],
+            "B N (T S) C -> (B S) N T C",
+            N=attn.heads,
+            T=num_frames,
+            S=spatial_dim,
+            C=head_dim,
+        )
+        key_image = rearrange(
+            key[:, :, text_seq_length:],
+            "B N (T S) C -> (B S) N T C",
+            N=attn.heads,
+            T=num_frames,
+            S=spatial_dim,
+            C=head_dim,
+        )
+        return feta_score(query_image, key_image, head_dim, num_frames)
+
+def feta_score(query_image, key_image, head_dim, num_frames):
+    scale = head_dim**-0.5
+    query_image = query_image * scale
+    attn_temp = query_image @ key_image.transpose(-2, -1)  # translate attn to float32
+    attn_temp = attn_temp.to(torch.float32)
+    attn_temp = attn_temp.softmax(dim=-1)
+
+    # Reshape to [batch_size * num_tokens, num_frames, num_frames]
+    attn_temp = attn_temp.reshape(-1, num_frames, num_frames)
+
+    # Create a mask for diagonal elements
+    diag_mask = torch.eye(num_frames, device=attn_temp.device).bool()
+    diag_mask = diag_mask.unsqueeze(0).expand(attn_temp.shape[0], -1, -1)
+
+    # Zero out diagonal elements
+    attn_wo_diag = attn_temp.masked_fill(diag_mask, 0)
+
+    # Calculate mean for each token's attention matrix
+    # Number of off-diagonal elements per matrix is n*n - n
+    num_off_diag = num_frames * num_frames - num_frames
+    mean_scores = attn_wo_diag.sum(dim=(1, 2)) / num_off_diag
+
+    enhance_scores = mean_scores.mean() * (num_frames + get_enhance_weight())
+    enhance_scores = enhance_scores.clamp(min=1)
+    return enhance_scores

custom_nodes/ComfyUI-CogVideoXWrapper/enhance_a_video/globals.py

@@ -0,0 +1,31 @@
+NUM_FRAMES = None
+FETA_WEIGHT = None
+ENABLE_FETA = False
+
+def set_num_frames(num_frames: int):
+    global NUM_FRAMES
+    NUM_FRAMES = num_frames
+
+
+def get_num_frames() -> int:
+    return NUM_FRAMES
+
+
+def enable_enhance():
+    global ENABLE_FETA
+    ENABLE_FETA = True
+
+def disable_enhance():
+    global ENABLE_FETA
+    ENABLE_FETA = False
+
+def is_enhance_enabled() -> bool:
+    return ENABLE_FETA
+
+def set_enhance_weight(feta_weight: float):
+    global FETA_WEIGHT
+    FETA_WEIGHT = feta_weight
+
+
+def get_enhance_weight() -> float:
+    return FETA_WEIGHT

custom_nodes/ComfyUI-CogVideoXWrapper/example_workflows/cogvideox_1.0_5b_vid2vid_02.json

@@ -0,0 +1,1061 @@
+{
+  "last_node_id": 78,
+  "last_link_id": 218,
+  "nodes": [
+    {
+      "id": 20,
+      "type": "CLIPLoader",
+      "pos": {
+        "0": -29,
+        "1": 407
+      },
+      "size": {
+        "0": 451.30548095703125,
+        "1": 82
+      },
+      "flags": {},
+      "order": 0,
+      "mode": 0,
+      "inputs": [],
+      "outputs": [
+        {
+          "name": "CLIP",
+          "type": "CLIP",
+          "links": [
+            54
+          ],
+          "slot_index": 0,
+          "shape": 3
+        }
+      ],
+      "properties": {
+        "Node name for S&R": "CLIPLoader"
+      },
+      "widgets_values": [
+        "t5\\google_t5-v1_1-xxl_encoderonly-fp8_e4m3fn.safetensors",
+        "sd3"
+      ]
+    },
+    {
+      "id": 41,
+      "type": "ImageResizeKJ",
+      "pos": {
+        "0": 206,
+        "1": -69
+      },
+      "size": {
+        "0": 315,
+        "1": 242
+      },
+      "flags": {},
+      "order": 7,
+      "mode": 0,
+      "inputs": [
+        {
+          "name": "image",
+          "type": "IMAGE",
+          "link": 180
+        },
+        {
+          "name": "get_image_size",
+          "type": "IMAGE",
+          "link": null,
+          "shape": 7
+        },
+        {
+          "name": "width_input",
+          "type": "INT",
+          "link": null,
+          "widget": {
+            "name": "width_input"
+          }
+        },
+        {
+          "name": "height_input",
+          "type": "INT",
+          "link": null,
+          "widget": {
+            "name": "height_input"
+          }
+        }
+      ],
+      "outputs": [
+        {
+          "name": "IMAGE",
+          "type": "IMAGE",
+          "links": [
+            126
+          ],
+          "slot_index": 0,
+          "shape": 3
+        },
+        {
+          "name": "width",
+          "type": "INT",
+          "links": null,
+          "shape": 3
+        },
+        {
+          "name": "height",
+          "type": "INT",
+          "links": null,
+          "shape": 3
+        }
+      ],
+      "properties": {
+        "Node name for S&R": "ImageResizeKJ"
+      },
+      "widgets_values": [
+        720,
+        480,
+        "lanczos",
+        false,
+        2,
+        0,
+        0,
+        "disabled"
+      ]
+    },
+    {
+      "id": 45,
+      "type": "VHS_LoadVideo",
+      "pos": {
+        "0": -93,
+        "1": -153
+      },
+      "size": [
+        247.455078125,
+        365.7275390625
+      ],
+      "flags": {},
+      "order": 4,
+      "mode": 0,
+      "inputs": [
+        {
+          "name": "meta_batch",
+          "type": "VHS_BatchManager",
+          "link": null,
+          "shape": 7
+        },
+        {
+          "name": "vae",
+          "type": "VAE",
+          "link": null,
+          "shape": 7
+        },
+        {
+          "name": "frame_load_cap",
+          "type": "INT",
+          "link": 177,
+          "widget": {
+            "name": "frame_load_cap"
+          }
+        }
+      ],
+      "outputs": [
+        {
+          "name": "IMAGE",
+          "type": "IMAGE",
+          "links": [
+            179
+          ],
+          "slot_index": 0,
+          "shape": 3
+        },
+        {
+          "name": "frame_count",
+          "type": "INT",
+          "links": null,
+          "shape": 3
+        },
+        {
+          "name": "audio",
+          "type": "AUDIO",
+          "links": null,
+          "shape": 3
+        },
+        {
+          "name": "video_info",
+          "type": "VHS_VIDEOINFO",
+          "links": null,
+          "shape": 3
+        }
+      ],
+      "properties": {
+        "Node name for S&R": "VHS_LoadVideo"
+      },
+      "widgets_values": {
+        "video": "jeep.mp4",
+        "force_rate": 0,
+        "force_size": "Disabled",
+        "custom_width": 512,
+        "custom_height": 512,
+        "frame_load_cap": 20,
+        "skip_first_frames": 0,
+        "select_every_nth": 1,
+        "choose video to upload": "image",
+        "videopreview": {
+          "hidden": false,
+          "paused": false,
+          "params": {
+            "frame_load_cap": 20,
+            "skip_first_frames": 0,
+            "force_rate": 0,
+            "filename": "jeep.mp4",
+            "type": "input",
+            "format": "video/mp4",
+            "select_every_nth": 1
+          }
+        }
+      }
+    },
+    {
+      "id": 70,
+      "type": "GetImageSizeAndCount",
+      "pos": {
+        "0": 214,
+        "1": -234
+      },
+      "size": {
+        "0": 202.2143096923828,
+        "1": 99.23601531982422
+      },
+      "flags": {},
+      "order": 6,
+      "mode": 0,
+      "inputs": [
+        {
+          "name": "image",
+          "type": "IMAGE",
+          "link": 179,
+          "slot_index": 0
+        }
+      ],
+      "outputs": [
+        {
+          "name": "image",
+          "type": "IMAGE",
+          "links": [
+            180
+          ],
+          "slot_index": 0,
+          "shape": 3
+        },
+        {
+          "name": "512 width",
+          "type": "INT",
+          "links": [],
+          "slot_index": 1,
+          "shape": 3
+        },
+        {
+          "name": "256 height",
+          "type": "INT",
+          "links": [],
+          "slot_index": 2,
+          "shape": 3
+        },
+        {
+          "name": "33 count",
+          "type": "INT",
+          "links": [],
+          "slot_index": 3,
+          "shape": 3
+        }
+      ],
+      "properties": {
+        "Node name for S&R": "GetImageSizeAndCount"
+      },
+      "widgets_values": []
+    },
+    {
+      "id": 69,
+      "type": "INTConstant",
+      "pos": {
+        "0": -90,
+        "1": -305
+      },
+      "size": {
+        "0": 210,
+        "1": 58
+      },
+      "flags": {},
+      "order": 1,
+      "mode": 0,
+      "inputs": [],
+      "outputs": [
+        {
+          "name": "value",
+          "type": "INT",
+          "links": [
+            177
+          ],
+          "shape": 3
+        }
+      ],
+      "title": "Frames to load",
+      "properties": {
+        "Node name for S&R": "INTConstant"
+      },
+      "widgets_values": [
+        33
+      ],
+      "color": "#1b4669",
+      "bgcolor": "#29699c"
+    },
+    {
+      "id": 58,
+      "type": "ImageConcanate",
+      "pos": {
+        "0": 1594,
+        "1": 230
+      },
+      "size": {
+        "0": 315,
+        "1": 102
+      },
+      "flags": {},
+      "order": 13,
+      "mode": 0,
+      "inputs": [
+        {
+          "name": "image1",
+          "type": "IMAGE",
+          "link": 191
+        },
+        {
+          "name": "image2",
+          "type": "IMAGE",
+          "link": 170
+        }
+      ],
+      "outputs": [
+        {
+          "name": "IMAGE",
+          "type": "IMAGE",
+          "links": [
+            132
+          ],
+          "slot_index": 0,
+          "shape": 3
+        }
+      ],
+      "properties": {
+        "Node name for S&R": "ImageConcanate"
+      },
+      "widgets_values": [
+        "right",
+        false
+      ]
+    },
+    {
+      "id": 55,
+      "type": "GetImageSizeAndCount",
+      "pos": {
+        "0": 1654,
+        "1": 77
+      },
+      "size": {
+        "0": 210,
+        "1": 86
+      },
+      "flags": {},
+      "order": 12,
+      "mode": 0,
+      "inputs": [
+        {
+          "name": "image",
+          "type": "IMAGE",
+          "link": 208,
+          "slot_index": 0
+        }
+      ],
+      "outputs": [
+        {
+          "name": "image",
+          "type": "IMAGE",
+          "links": [
+            170
+          ],
+          "slot_index": 0,
+          "shape": 3
+        },
+        {
+          "name": "720 width",
+          "type": "INT",
+          "links": null,
+          "shape": 3
+        },
+        {
+          "name": "480 height",
+          "type": "INT",
+          "links": null,
+          "shape": 3
+        },
+        {
+          "name": "33 count",
+          "type": "INT",
+          "links": [],
+          "slot_index": 3,
+          "shape": 3
+        }
+      ],
+      "properties": {
+        "Node name for S&R": "GetImageSizeAndCount"
+      },
+      "widgets_values": []
+    },
+    {
+      "id": 77,
+      "type": "CogVideoImageEncode",
+      "pos": {
+        "0": 952,
+        "1": -118
+      },
+      "size": {
+        "0": 315,
+        "1": 122
+      },
+      "flags": {},
+      "order": 9,
+      "mode": 0,
+      "inputs": [
+        {
+          "name": "vae",
+          "type": "VAE",
+          "link": 209
+        },
+        {
+          "name": "start_image",
+          "type": "IMAGE",
+          "link": 210
+        },
+        {
+          "name": "end_image",
+          "type": "IMAGE",
+          "link": null,
+          "shape": 7
+        }
+      ],
+      "outputs": [
+        {
+          "name": "samples",
+          "type": "LATENT",
+          "links": [
+            215
+          ]
+        }
+      ],
+      "properties": {
+        "Node name for S&R": "CogVideoImageEncode"
+      },
+      "widgets_values": [
+        false,
+        0
+      ]
+    },
+    {
+      "id": 76,
+      "type": "CogVideoDecode",
+      "pos": {
+        "0": 1335,
+        "1": -123
+      },
+      "size": {
+        "0": 315,
+        "1": 198
+      },
+      "flags": {},
+      "order": 11,
+      "mode": 0,
+      "inputs": [
+        {
+          "name": "vae",
+          "type": "VAE",
+          "link": 206
+        },
+        {
+          "name": "samples",
+          "type": "LATENT",
+          "link": 216
+        }
+      ],
+      "outputs": [
+        {
+          "name": "images",
+          "type": "IMAGE",
+          "links": [
+            208
+          ]
+        }
+      ],
+      "properties": {
+        "Node name for S&R": "CogVideoDecode"
+      },
+      "widgets_values": [
+        true,
+        240,
+        360,
+        0.2,
+        0.2,
+        true
+      ]
+    },
+    {
+      "id": 30,
+      "type": "CogVideoTextEncode",
+      "pos": {
+        "0": 491,
+        "1": 372
+      },
+      "size": [
+        478.6890949595422,
+        215.66308749666905
+      ],
+      "flags": {},
+      "order": 3,
+      "mode": 0,
+      "inputs": [
+        {
+          "name": "clip",
+          "type": "CLIP",
+          "link": 54
+        }
+      ],
+      "outputs": [
+        {
+          "name": "conditioning",
+          "type": "CONDITIONING",
+          "links": [
+            213
+          ],
+          "slot_index": 0,
+          "shape": 3
+        },
+        {
+          "name": "clip",
+          "type": "CLIP",
+          "links": [
+            217
+          ],
+          "slot_index": 1
+        }
+      ],
+      "properties": {
+        "Node name for S&R": "CogVideoTextEncode"
+      },
+      "widgets_values": [
+        "A high-definition nature video showcasing a brown bear as it gracefully runs down a crystal-clear stream, surrounded by the serene ambiance of a dense, verdant forest. The sunlight filters through the canopy of tall trees, casting dappled light on the forest floor, while the gentle sound of flowing water and rustling leaves creates a peaceful atmosphere. The brown bear's fur glistens in the sunlight, highlighting its striking red and white markings as it navigates the stream with agility and playfulness.",
+        1,
+        false
+      ]
+    },
+    {
+      "id": 31,
+      "type": "CogVideoTextEncode",
+      "pos": {
+        "0": 504,
+        "1": 651
+      },
+      "size": {
+        "0": 463.01251220703125,
+        "1": 144
+      },
+      "flags": {},
+      "order": 5,
+      "mode": 0,
+      "inputs": [
+        {
+          "name": "clip",
+          "type": "CLIP",
+          "link": 217
+        }
+      ],
+      "outputs": [
+        {
+          "name": "conditioning",
+          "type": "CONDITIONING",
+          "links": [
+            214
+          ],
+          "slot_index": 0,
+          "shape": 3
+        },
+        {
+          "name": "clip",
+          "type": "CLIP",
+          "links": null
+        }
+      ],
+      "properties": {
+        "Node name for S&R": "CogVideoTextEncode"
+      },
+      "widgets_values": [
+        "",
+        1,
+        true
+      ]
+    },
+    {
+      "id": 78,
+      "type": "CogVideoSampler",
+      "pos": {
+        "0": 1083,
+        "1": 255
+      },
+      "size": [
+        330,
+        574
+      ],
+      "flags": {},
+      "order": 10,
+      "mode": 0,
+      "inputs": [
+        {
+          "name": "model",
+          "type": "COGVIDEOMODEL",
+          "link": 212
+        },
+        {
+          "name": "positive",
+          "type": "CONDITIONING",
+          "link": 213
+        },
+        {
+          "name": "negative",
+          "type": "CONDITIONING",
+          "link": 214
+        },
+        {
+          "name": "samples",
+          "type": "LATENT",
+          "link": 215,
+          "shape": 7
+        },
+        {
+          "name": "image_cond_latents",
+          "type": "LATENT",
+          "link": null,
+          "shape": 7
+        },
+        {
+          "name": "context_options",
+          "type": "COGCONTEXT",
+          "link": null,
+          "shape": 7
+        },
+        {
+          "name": "controlnet",
+          "type": "COGVIDECONTROLNET",
+          "link": null,
+          "shape": 7
+        },
+        {
+          "name": "tora_trajectory",
+          "type": "TORAFEATURES",
+          "link": null,
+          "shape": 7
+        },
+        {
+          "name": "fastercache",
+          "type": "FASTERCACHEARGS",
+          "link": null,
+          "shape": 7
+        },
+        {
+          "name": "num_frames",
+          "type": "INT",
+          "link": 218,
+          "widget": {
+            "name": "num_frames"
+          }
+        }
+      ],
+      "outputs": [
+        {
+          "name": "samples",
+          "type": "LATENT",
+          "links": [
+            216
+          ]
+        }
+      ],
+      "properties": {
+        "Node name for S&R": "CogVideoSampler"
+      },
+      "widgets_values": [
+        49,
+        25,
+        6,
+        0,
+        "fixed",
+        "CogVideoXDDIM",
+        0.8
+      ]
+    },
+    {
+      "id": 57,
+      "type": "GetImageSizeAndCount",
+      "pos": {
+        "0": 595,
+        "1": -79
+      },
+      "size": {
+        "0": 202.2143096923828,
+        "1": 99.23601531982422
+      },
+      "flags": {},
+      "order": 8,
+      "mode": 0,
+      "inputs": [
+        {
+          "name": "image",
+          "type": "IMAGE",
+          "link": 126,
+          "slot_index": 0
+        }
+      ],
+      "outputs": [
+        {
+          "name": "image",
+          "type": "IMAGE",
+          "links": [
+            191,
+            210
+          ],
+          "slot_index": 0,
+          "shape": 3
+        },
+        {
+          "name": "720 width",
+          "type": "INT",
+          "links": [],
+          "slot_index": 1,
+          "shape": 3
+        },
+        {
+          "name": "480 height",
+          "type": "INT",
+          "links": [],
+          "slot_index": 2,
+          "shape": 3
+        },
+        {
+          "name": "33 count",
+          "type": "INT",
+          "links": [
+            218
+          ],
+          "slot_index": 3,
+          "shape": 3
+        }
+      ],
+      "properties": {
+        "Node name for S&R": "GetImageSizeAndCount"
+      },
+      "widgets_values": []
+    },
+    {
+      "id": 75,
+      "type": "DownloadAndLoadCogVideoModel",
+      "pos": {
+        "0": 606,
+        "1": 85
+      },
+      "size": {
+        "0": 315,
+        "1": 218
+      },
+      "flags": {},
+      "order": 2,
+      "mode": 0,
+      "inputs": [
+        {
+          "name": "block_edit",
+          "type": "TRANSFORMERBLOCKS",
+          "link": null,
+          "shape": 7
+        },
+        {
+          "name": "lora",
+          "type": "COGLORA",
+          "link": null,
+          "shape": 7
+        },
+        {
+          "name": "compile_args",
+          "type": "COMPILEARGS",
+          "link": null,
+          "shape": 7
+        }
+      ],
+      "outputs": [
+        {
+          "name": "model",
+          "type": "COGVIDEOMODEL",
+          "links": [
+            212
+          ]
+        },
+        {
+          "name": "vae",
+          "type": "VAE",
+          "links": [
+            206,
+            209
+          ]
+        }
+      ],
+      "properties": {
+        "Node name for S&R": "DownloadAndLoadCogVideoModel"
+      },
+      "widgets_values": [
+        "THUDM/CogVideoX-5b",
+        "bf16",
+        "disabled",
+        false,
+        "sdpa",
+        "main_device"
+      ]
+    },
+    {
+      "id": 47,
+      "type": "VHS_VideoCombine",
+      "pos": {
+        "0": 1946,
+        "1": -172
+      },
+      "size": [
+        1110,
+        687.3333333333333
+      ],
+      "flags": {},
+      "order": 14,
+      "mode": 0,
+      "inputs": [
+        {
+          "name": "images",
+          "type": "IMAGE",
+          "link": 132
+        },
+        {
+          "name": "audio",
+          "type": "AUDIO",
+          "link": null,
+          "shape": 7
+        },
+        {
+          "name": "meta_batch",
+          "type": "VHS_BatchManager",
+          "link": null,
+          "shape": 7
+        },
+        {
+          "name": "vae",
+          "type": "VAE",
+          "link": null,
+          "shape": 7
+        }
+      ],
+      "outputs": [
+        {
+          "name": "Filenames",
+          "type": "VHS_FILENAMES",
+          "links": null,
+          "shape": 3
+        }
+      ],
+      "properties": {
+        "Node name for S&R": "VHS_VideoCombine"
+      },
+      "widgets_values": {
+        "frame_rate": 8,
+        "loop_count": 0,
+        "filename_prefix": "CogVideoX_vid2vid",
+        "format": "video/h264-mp4",
+        "pix_fmt": "yuv420p",
+        "crf": 19,
+        "save_metadata": true,
+        "pingpong": false,
+        "save_output": true,
+        "videopreview": {
+          "hidden": false,
+          "paused": false,
+          "params": {
+            "filename": "CogVideoX_vid2vid_00003.mp4",
+            "subfolder": "",
+            "type": "temp",
+            "format": "video/h264-mp4",
+            "frame_rate": 8
+          }
+        }
+      }
+    }
+  ],
+  "links": [
+    [
+      54,
+      20,
+      0,
+      30,
+      0,
+      "CLIP"
+    ],
+    [
+      126,
+      41,
+      0,
+      57,
+      0,
+      "IMAGE"
+    ],
+    [
+      132,
+      58,
+      0,
+      47,
+      0,
+      "IMAGE"
+    ],
+    [
+      170,
+      55,
+      0,
+      58,
+      1,
+      "IMAGE"
+    ],
+    [
+      177,
+      69,
+      0,
+      45,
+      2,
+      "INT"
+    ],
+    [
+      179,
+      45,
+      0,
+      70,
+      0,
+      "IMAGE"
+    ],
+    [
+      180,
+      70,
+      0,
+      41,
+      0,
+      "IMAGE"
+    ],
+    [
+      191,
+      57,
+      0,
+      58,
+      0,
+      "IMAGE"
+    ],
+    [
+      206,
+      75,
+      1,
+      76,
+      0,
+      "VAE"
+    ],
+    [
+      208,
+      76,
+      0,
+      55,
+      0,
+      "IMAGE"
+    ],
+    [
+      209,
+      75,
+      1,
+      77,
+      0,
+      "VAE"
+    ],
+    [
+      210,
+      57,
+      0,
+      77,
+      1,
+      "IMAGE"
+    ],
+    [
+      212,
+      75,
+      0,
+      78,
+      0,
+      "COGVIDEOMODEL"
+    ],
+    [
+      213,
+      30,
+      0,
+      78,
+      1,
+      "CONDITIONING"
+    ],
+    [
+      214,
+      31,
+      0,
+      78,
+      2,
+      "CONDITIONING"
+    ],
+    [
+      215,
+      77,
+      0,
+      78,
+      3,
+      "LATENT"
+    ],
+    [
+      216,
+      78,
+      0,
+      76,
+      1,
+      "LATENT"
+    ],
+    [
+      217,
+      30,
+      1,
+      31,
+      0,
+      "CLIP"
+    ],
+    [
+      218,
+      57,
+      3,
+      78,
+      9,
+      "INT"
+    ]
+  ],
+  "groups": [],
+  "config": {},
+  "extra": {
+    "ds": {
+      "scale": 0.8390545288825798,
+      "offset": [
+        -318.82552550589344,
+        331.70430573737934
+      ]
+    }
+  },
+  "version": 0.4
+}

custom_nodes/ComfyUI-CogVideoXWrapper/example_workflows/cogvideox_1_0_2b_controlnet_02.json

@@ -0,0 +1,1003 @@
+{
+  "last_node_id": 48,
+  "last_link_id": 90,
+  "nodes": [
+    {
+      "id": 41,
+      "type": "HEDPreprocessor",
+      "pos": {
+        "0": -570,
+        "1": -76
+      },
+      "size": {
+        "0": 315,
+        "1": 82
+      },
+      "flags": {},
+      "order": 4,
+      "mode": 0,
+      "inputs": [
+        {
+          "name": "image",
+          "type": "IMAGE",
+          "link": 73
+        }
+      ],
+      "outputs": [
+        {
+          "name": "IMAGE",
+          "type": "IMAGE",
+          "links": [
+            74
+          ],
+          "slot_index": 0
+        }
+      ],
+      "properties": {
+        "Node name for S&R": "HEDPreprocessor"
+      },
+      "widgets_values": [
+        "enable",
+        768
+      ]
+    },
+    {
+      "id": 38,
+      "type": "VHS_LoadVideo",
+      "pos": {
+        "0": -847,
+        "1": -78
+      },
+      "size": [
+        247.455078125,
+        427.63671875
+      ],
+      "flags": {},
+      "order": 0,
+      "mode": 0,
+      "inputs": [
+        {
+          "name": "meta_batch",
+          "type": "VHS_BatchManager",
+          "link": null,
+          "shape": 7
+        },
+        {
+          "name": "vae",
+          "type": "VAE",
+          "link": null,
+          "shape": 7
+        }
+      ],
+      "outputs": [
+        {
+          "name": "IMAGE",
+          "type": "IMAGE",
+          "links": [
+            73
+          ],
+          "slot_index": 0
+        },
+        {
+          "name": "frame_count",
+          "type": "INT",
+          "links": null
+        },
+        {
+          "name": "audio",
+          "type": "AUDIO",
+          "links": null
+        },
+        {
+          "name": "video_info",
+          "type": "VHS_VIDEOINFO",
+          "links": null
+        }
+      ],
+      "properties": {
+        "Node name for S&R": "VHS_LoadVideo"
+      },
+      "widgets_values": {
+        "video": "car.mp4",
+        "force_rate": 0,
+        "force_size": "Disabled",
+        "custom_width": 512,
+        "custom_height": 512,
+        "frame_load_cap": 49,
+        "skip_first_frames": 0,
+        "select_every_nth": 1,
+        "choose video to upload": "image",
+        "videopreview": {
+          "hidden": false,
+          "paused": false,
+          "params": {
+            "frame_load_cap": 49,
+            "skip_first_frames": 0,
+            "force_rate": 0,
+            "filename": "car.mp4",
+            "type": "input",
+            "format": "video/mp4",
+            "select_every_nth": 1
+          },
+          "muted": false
+        }
+      }
+    },
+    {
+      "id": 39,
+      "type": "ImageResizeKJ",
+      "pos": {
+        "0": -563,
+        "1": 63
+      },
+      "size": {
+        "0": 315,
+        "1": 266
+      },
+      "flags": {},
+      "order": 6,
+      "mode": 0,
+      "inputs": [
+        {
+          "name": "image",
+          "type": "IMAGE",
+          "link": 74
+        },
+        {
+          "name": "get_image_size",
+          "type": "IMAGE",
+          "link": null,
+          "shape": 7
+        },
+        {
+          "name": "width_input",
+          "type": "INT",
+          "link": null,
+          "widget": {
+            "name": "width_input"
+          },
+          "shape": 7
+        },
+        {
+          "name": "height_input",
+          "type": "INT",
+          "link": null,
+          "widget": {
+            "name": "height_input"
+          },
+          "shape": 7
+        }
+      ],
+      "outputs": [
+        {
+          "name": "IMAGE",
+          "type": "IMAGE",
+          "links": [
+            71
+          ],
+          "slot_index": 0
+        },
+        {
+          "name": "width",
+          "type": "INT",
+          "links": null
+        },
+        {
+          "name": "height",
+          "type": "INT",
+          "links": null
+        }
+      ],
+      "properties": {
+        "Node name for S&R": "ImageResizeKJ"
+      },
+      "widgets_values": [
+        720,
+        480,
+        "lanczos",
+        false,
+        2,
+        0,
+        0,
+        "disabled"
+      ]
+    },
+    {
+      "id": 30,
+      "type": "CogVideoTextEncode",
+      "pos": {
+        "0": 130,
+        "1": 350
+      },
+      "size": {
+        "0": 475.7875061035156,
+        "1": 231.29896545410156
+      },
+      "flags": {},
+      "order": 5,
+      "mode": 0,
+      "inputs": [
+        {
+          "name": "clip",
+          "type": "CLIP",
+          "link": 54
+        }
+      ],
+      "outputs": [
+        {
+          "name": "conditioning",
+          "type": "CONDITIONING",
+          "links": [
+            84
+          ],
+          "slot_index": 0,
+          "shape": 3
+        },
+        {
+          "name": "clip",
+          "type": "CLIP",
+          "links": [
+            78
+          ],
+          "slot_index": 1
+        }
+      ],
+      "properties": {
+        "Node name for S&R": "CogVideoTextEncode"
+      },
+      "widgets_values": [
+        "car is moving among mountains",
+        1,
+        false
+      ]
+    },
+    {
+      "id": 31,
+      "type": "CogVideoTextEncode",
+      "pos": {
+        "0": 139,
+        "1": 643
+      },
+      "size": {
+        "0": 463.01251220703125,
+        "1": 144
+      },
+      "flags": {},
+      "order": 7,
+      "mode": 0,
+      "inputs": [
+        {
+          "name": "clip",
+          "type": "CLIP",
+          "link": 78
+        }
+      ],
+      "outputs": [
+        {
+          "name": "conditioning",
+          "type": "CONDITIONING",
+          "links": [
+            85
+          ],
+          "slot_index": 0,
+          "shape": 3
+        },
+        {
+          "name": "clip",
+          "type": "CLIP",
+          "links": null
+        }
+      ],
+      "properties": {
+        "Node name for S&R": "CogVideoTextEncode"
+      },
+      "widgets_values": [
+        "",
+        1,
+        true
+      ]
+    },
+    {
+      "id": 44,
+      "type": "DownloadAndLoadCogVideoModel",
+      "pos": {
+        "0": 326,
+        "1": -319
+      },
+      "size": {
+        "0": 315,
+        "1": 218
+      },
+      "flags": {},
+      "order": 1,
+      "mode": 0,
+      "inputs": [
+        {
+          "name": "block_edit",
+          "type": "TRANSFORMERBLOCKS",
+          "link": null,
+          "shape": 7
+        },
+        {
+          "name": "lora",
+          "type": "COGLORA",
+          "link": null,
+          "shape": 7
+        },
+        {
+          "name": "compile_args",
+          "type": "COMPILEARGS",
+          "link": null,
+          "shape": 7
+        }
+      ],
+      "outputs": [
+        {
+          "name": "model",
+          "type": "COGVIDEOMODEL",
+          "links": [
+            83
+          ]
+        },
+        {
+          "name": "vae",
+          "type": "VAE",
+          "links": [
+            82
+          ],
+          "slot_index": 1
+        }
+      ],
+      "properties": {
+        "Node name for S&R": "DownloadAndLoadCogVideoModel"
+      },
+      "widgets_values": [
+        "THUDM/CogVideoX-2b",
+        "bf16",
+        "disabled",
+        false,
+        "sdpa",
+        "main_device"
+      ]
+    },
+    {
+      "id": 20,
+      "type": "CLIPLoader",
+      "pos": {
+        "0": -175,
+        "1": -317
+      },
+      "size": {
+        "0": 452.912353515625,
+        "1": 82
+      },
+      "flags": {},
+      "order": 2,
+      "mode": 0,
+      "inputs": [],
+      "outputs": [
+        {
+          "name": "CLIP",
+          "type": "CLIP",
+          "links": [
+            54
+          ],
+          "slot_index": 0,
+          "shape": 3
+        }
+      ],
+      "properties": {
+        "Node name for S&R": "CLIPLoader"
+      },
+      "widgets_values": [
+        "t5\\google_t5-v1_1-xxl_encoderonly-fp8_e4m3fn.safetensors",
+        "sd3"
+      ]
+    },
+    {
+      "id": 35,
+      "type": "DownloadAndLoadCogVideoControlNet",
+      "pos": {
+        "0": -105,
+        "1": -182
+      },
+      "size": {
+        "0": 378,
+        "1": 58
+      },
+      "flags": {},
+      "order": 3,
+      "mode": 0,
+      "inputs": [],
+      "outputs": [
+        {
+          "name": "cogvideo_controlnet",
+          "type": "COGVIDECONTROLNETMODEL",
+          "links": [
+            67
+          ]
+        }
+      ],
+      "properties": {
+        "Node name for S&R": "DownloadAndLoadCogVideoControlNet"
+      },
+      "widgets_values": [
+        "TheDenk/cogvideox-2b-controlnet-hed-v1"
+      ]
+    },
+    {
+      "id": 37,
+      "type": "CogVideoControlNet",
+      "pos": {
+        "0": 220,
+        "1": 155
+      },
+      "size": {
+        "0": 367.79998779296875,
+        "1": 126
+      },
+      "flags": {},
+      "order": 9,
+      "mode": 0,
+      "inputs": [
+        {
+          "name": "controlnet",
+          "type": "COGVIDECONTROLNETMODEL",
+          "link": 67
+        },
+        {
+          "name": "images",
+          "type": "IMAGE",
+          "link": 72
+        }
+      ],
+      "outputs": [
+        {
+          "name": "cogvideo_controlnet",
+          "type": "COGVIDECONTROLNET",
+          "links": [
+            86
+          ],
+          "slot_index": 0
+        }
+      ],
+      "properties": {
+        "Node name for S&R": "CogVideoControlNet"
+      },
+      "widgets_values": [
+        1,
+        0,
+        1
+      ]
+    },
+    {
+      "id": 40,
+      "type": "GetImageSizeAndCount",
+      "pos": {
+        "0": -123,
+        "1": -34
+      },
+      "size": {
+        "0": 277.20001220703125,
+        "1": 86
+      },
+      "flags": {},
+      "order": 8,
+      "mode": 0,
+      "inputs": [
+        {
+          "name": "image",
+          "type": "IMAGE",
+          "link": 71
+        }
+      ],
+      "outputs": [
+        {
+          "name": "image",
+          "type": "IMAGE",
+          "links": [
+            72,
+            75
+          ],
+          "slot_index": 0
+        },
+        {
+          "name": "720 width",
+          "type": "INT",
+          "links": [
+            89
+          ]
+        },
+        {
+          "name": "480 height",
+          "type": "INT",
+          "links": [
+            90
+          ],
+          "slot_index": 2
+        },
+        {
+          "name": "49 count",
+          "type": "INT",
+          "links": null
+        }
+      ],
+      "properties": {
+        "Node name for S&R": "GetImageSizeAndCount"
+      },
+      "widgets_values": []
+    },
+    {
+      "id": 47,
+      "type": "EmptyLatentImage",
+      "pos": {
+        "0": 409,
+        "1": 77
+      },
+      "size": {
+        "0": 315,
+        "1": 106
+      },
+      "flags": {
+        "collapsed": true
+      },
+      "order": 10,
+      "mode": 0,
+      "inputs": [
+        {
+          "name": "width",
+          "type": "INT",
+          "link": 89,
+          "widget": {
+            "name": "width"
+          }
+        },
+        {
+          "name": "height",
+          "type": "INT",
+          "link": 90,
+          "widget": {
+            "name": "height"
+          }
+        }
+      ],
+      "outputs": [
+        {
+          "name": "LATENT",
+          "type": "LATENT",
+          "links": [
+            88
+          ]
+        }
+      ],
+      "properties": {
+        "Node name for S&R": "EmptyLatentImage"
+      },
+      "widgets_values": [
+        720,
+        480,
+        1
+      ]
+    },
+    {
+      "id": 46,
+      "type": "CogVideoSampler",
+      "pos": {
+        "0": 743,
+        "1": 49
+      },
+      "size": {
+        "0": 330,
+        "1": 574
+      },
+      "flags": {},
+      "order": 11,
+      "mode": 0,
+      "inputs": [
+        {
+          "name": "model",
+          "type": "COGVIDEOMODEL",
+          "link": 83
+        },
+        {
+          "name": "positive",
+          "type": "CONDITIONING",
+          "link": 84
+        },
+        {
+          "name": "negative",
+          "type": "CONDITIONING",
+          "link": 85
+        },
+        {
+          "name": "samples",
+          "type": "LATENT",
+          "link": 88,
+          "shape": 7
+        },
+        {
+          "name": "image_cond_latents",
+          "type": "LATENT",
+          "link": null,
+          "shape": 7
+        },
+        {
+          "name": "context_options",
+          "type": "COGCONTEXT",
+          "link": null,
+          "shape": 7
+        },
+        {
+          "name": "controlnet",
+          "type": "COGVIDECONTROLNET",
+          "link": 86,
+          "shape": 7
+        },
+        {
+          "name": "tora_trajectory",
+          "type": "TORAFEATURES",
+          "link": null,
+          "shape": 7
+        },
+        {
+          "name": "fastercache",
+          "type": "FASTERCACHEARGS",
+          "link": null,
+          "shape": 7
+        }
+      ],
+      "outputs": [
+        {
+          "name": "samples",
+          "type": "LATENT",
+          "links": [
+            87
+          ]
+        }
+      ],
+      "properties": {
+        "Node name for S&R": "CogVideoSampler"
+      },
+      "widgets_values": [
+        49,
+        40,
+        6,
+        0,
+        "fixed",
+        "CogVideoXDDIM",
+        1
+      ]
+    },
+    {
+      "id": 45,
+      "type": "CogVideoDecode",
+      "pos": {
+        "0": 758,
+        "1": 685
+      },
+      "size": {
+        "0": 315,
+        "1": 198
+      },
+      "flags": {},
+      "order": 12,
+      "mode": 0,
+      "inputs": [
+        {
+          "name": "vae",
+          "type": "VAE",
+          "link": 82
+        },
+        {
+          "name": "samples",
+          "type": "LATENT",
+          "link": 87
+        }
+      ],
+      "outputs": [
+        {
+          "name": "images",
+          "type": "IMAGE",
+          "links": [
+            81
+          ]
+        }
+      ],
+      "properties": {
+        "Node name for S&R": "CogVideoDecode"
+      },
+      "widgets_values": [
+        true,
+        240,
+        360,
+        0.2,
+        0.2,
+        true
+      ]
+    },
+    {
+      "id": 42,
+      "type": "ImageConcatMulti",
+      "pos": {
+        "0": 1145,
+        "1": -24
+      },
+      "size": {
+        "0": 210,
+        "1": 150
+      },
+      "flags": {},
+      "order": 13,
+      "mode": 0,
+      "inputs": [
+        {
+          "name": "image_1",
+          "type": "IMAGE",
+          "link": 75
+        },
+        {
+          "name": "image_2",
+          "type": "IMAGE",
+          "link": 81
+        }
+      ],
+      "outputs": [
+        {
+          "name": "images",
+          "type": "IMAGE",
+          "links": [
+            77
+          ],
+          "slot_index": 0
+        }
+      ],
+      "properties": {},
+      "widgets_values": [
+        2,
+        "right",
+        false,
+        null
+      ]
+    },
+    {
+      "id": 43,
+      "type": "VHS_VideoCombine",
+      "pos": {
+        "0": 1154,
+        "1": 202
+      },
+      "size": [
+        778.7022705078125,
+        576.9007568359375
+      ],
+      "flags": {},
+      "order": 14,
+      "mode": 0,
+      "inputs": [
+        {
+          "name": "images",
+          "type": "IMAGE",
+          "link": 77
+        },
+        {
+          "name": "audio",
+          "type": "AUDIO",
+          "link": null,
+          "shape": 7
+        },
+        {
+          "name": "meta_batch",
+          "type": "VHS_BatchManager",
+          "link": null,
+          "shape": 7
+        },
+        {
+          "name": "vae",
+          "type": "VAE",
+          "link": null,
+          "shape": 7
+        }
+      ],
+      "outputs": [
+        {
+          "name": "Filenames",
+          "type": "VHS_FILENAMES",
+          "links": null,
+          "shape": 3
+        }
+      ],
+      "properties": {
+        "Node name for S&R": "VHS_VideoCombine"
+      },
+      "widgets_values": {
+        "frame_rate": 8,
+        "loop_count": 0,
+        "filename_prefix": "CogVideoX_2b_controlnet",
+        "format": "video/h264-mp4",
+        "pix_fmt": "yuv420p",
+        "crf": 19,
+        "save_metadata": true,
+        "pingpong": false,
+        "save_output": true,
+        "videopreview": {
+          "hidden": false,
+          "paused": false,
+          "params": {
+            "filename": "CogVideoX2B_controlnet_00003.mp4",
+            "subfolder": "",
+            "type": "temp",
+            "format": "video/h264-mp4",
+            "frame_rate": 8
+          },
+          "muted": false
+        }
+      }
+    }
+  ],
+  "links": [
+    [
+      54,
+      20,
+      0,
+      30,
+      0,
+      "CLIP"
+    ],
+    [
+      67,
+      35,
+      0,
+      37,
+      0,
+      "COGVIDECONTROLNETMODEL"
+    ],
+    [
+      71,
+      39,
+      0,
+      40,
+      0,
+      "IMAGE"
+    ],
+    [
+      72,
+      40,
+      0,
+      37,
+      1,
+      "IMAGE"
+    ],
+    [
+      73,
+      38,
+      0,
+      41,
+      0,
+      "IMAGE"
+    ],
+    [
+      74,
+      41,
+      0,
+      39,
+      0,
+      "IMAGE"
+    ],
+    [
+      75,
+      40,
+      0,
+      42,
+      0,
+      "IMAGE"
+    ],
+    [
+      77,
+      42,
+      0,
+      43,
+      0,
+      "IMAGE"
+    ],
+    [
+      78,
+      30,
+      1,
+      31,
+      0,
+      "CLIP"
+    ],
+    [
+      81,
+      45,
+      0,
+      42,
+      1,
+      "IMAGE"
+    ],
+    [
+      82,
+      44,
+      1,
+      45,
+      0,
+      "VAE"
+    ],
+    [
+      83,
+      44,
+      0,
+      46,
+      0,
+      "COGVIDEOMODEL"
+    ],
+    [
+      84,
+      30,
+      0,
+      46,
+      1,
+      "CONDITIONING"
+    ],
+    [
+      85,
+      31,
+      0,
+      46,
+      2,
+      "CONDITIONING"
+    ],
+    [
+      86,
+      37,
+      0,
+      46,
+      6,
+      "COGVIDECONTROLNET"
+    ],
+    [
+      87,
+      46,
+      0,
+      45,
+      1,
+      "LATENT"
+    ],
+    [
+      88,
+      47,
+      0,
+      46,
+      3,
+      "LATENT"
+    ],
+    [
+      89,
+      40,
+      1,
+      47,
+      0,
+      "INT"
+    ],
+    [
+      90,
+      40,
+      2,
+      47,
+      1,
+      "INT"
+    ]
+  ],
+  "groups": [],
+  "config": {},
+  "extra": {
+    "ds": {
+      "scale": 0.7627768444387069,
+      "offset": [
+        1075.4957551311677,
+        398.4420252790512
+      ]
+    }
+  },
+  "version": 0.4
+}

custom_nodes/ComfyUI-CogVideoXWrapper/example_workflows/cogvideox_1_0_5b_I2V_02.json

@@ -0,0 +1,688 @@
+{
+  "last_node_id": 63,
+  "last_link_id": 149,
+  "nodes": [
+    {
+      "id": 31,
+      "type": "CogVideoTextEncode",
+      "pos": {
+        "0": 497,
+        "1": 520
+      },
+      "size": {
+        "0": 463.01251220703125,
+        "1": 144
+      },
+      "flags": {},
+      "order": 6,
+      "mode": 0,
+      "inputs": [
+        {
+          "name": "clip",
+          "type": "CLIP",
+          "link": 149
+        }
+      ],
+      "outputs": [
+        {
+          "name": "conditioning",
+          "type": "CONDITIONING",
+          "links": [
+            146
+          ],
+          "slot_index": 0,
+          "shape": 3
+        },
+        {
+          "name": "clip",
+          "type": "CLIP",
+          "links": null
+        }
+      ],
+      "properties": {
+        "Node name for S&R": "CogVideoTextEncode"
+      },
+      "widgets_values": [
+        "The video is not of a high quality, it has a low resolution. Watermark present in each frame. Strange motion trajectory. ",
+        1,
+        true
+      ]
+    },
+    {
+      "id": 63,
+      "type": "CogVideoSampler",
+      "pos": {
+        "0": 1142,
+        "1": 74
+      },
+      "size": [
+        330,
+        574
+      ],
+      "flags": {},
+      "order": 7,
+      "mode": 0,
+      "inputs": [
+        {
+          "name": "model",
+          "type": "COGVIDEOMODEL",
+          "link": 144
+        },
+        {
+          "name": "positive",
+          "type": "CONDITIONING",
+          "link": 145
+        },
+        {
+          "name": "negative",
+          "type": "CONDITIONING",
+          "link": 146
+        },
+        {
+          "name": "samples",
+          "type": "LATENT",
+          "link": null,
+          "shape": 7
+        },
+        {
+          "name": "image_cond_latents",
+          "type": "LATENT",
+          "link": 147,
+          "shape": 7
+        },
+        {
+          "name": "context_options",
+          "type": "COGCONTEXT",
+          "link": null,
+          "shape": 7
+        },
+        {
+          "name": "controlnet",
+          "type": "COGVIDECONTROLNET",
+          "link": null,
+          "shape": 7
+        },
+        {
+          "name": "tora_trajectory",
+          "type": "TORAFEATURES",
+          "link": null,
+          "shape": 7
+        },
+        {
+          "name": "fastercache",
+          "type": "FASTERCACHEARGS",
+          "link": null,
+          "shape": 7
+        }
+      ],
+      "outputs": [
+        {
+          "name": "samples",
+          "type": "LATENT",
+          "links": [
+            148
+          ]
+        }
+      ],
+      "properties": {
+        "Node name for S&R": "CogVideoSampler"
+      },
+      "widgets_values": [
+        49,
+        25,
+        6,
+        0,
+        "fixed",
+        "CogVideoXDDIM",
+        1
+      ]
+    },
+    {
+      "id": 62,
+      "type": "CogVideoImageEncode",
+      "pos": {
+        "0": 1149,
+        "1": 711
+      },
+      "size": {
+        "0": 315,
+        "1": 122
+      },
+      "flags": {},
+      "order": 5,
+      "mode": 0,
+      "inputs": [
+        {
+          "name": "vae",
+          "type": "VAE",
+          "link": 141
+        },
+        {
+          "name": "start_image",
+          "type": "IMAGE",
+          "link": 142
+        },
+        {
+          "name": "end_image",
+          "type": "IMAGE",
+          "link": null,
+          "shape": 7
+        }
+      ],
+      "outputs": [
+        {
+          "name": "samples",
+          "type": "LATENT",
+          "links": [
+            147
+          ]
+        }
+      ],
+      "properties": {
+        "Node name for S&R": "CogVideoImageEncode"
+      },
+      "widgets_values": [
+        false,
+        0
+      ]
+    },
+    {
+      "id": 59,
+      "type": "DownloadAndLoadCogVideoModel",
+      "pos": {
+        "0": 622,
+        "1": -25
+      },
+      "size": {
+        "0": 315,
+        "1": 218
+      },
+      "flags": {},
+      "order": 0,
+      "mode": 0,
+      "inputs": [
+        {
+          "name": "block_edit",
+          "type": "TRANSFORMERBLOCKS",
+          "link": null,
+          "shape": 7
+        },
+        {
+          "name": "lora",
+          "type": "COGLORA",
+          "link": null,
+          "shape": 7
+        },
+        {
+          "name": "compile_args",
+          "type": "COMPILEARGS",
+          "link": null,
+          "shape": 7
+        }
+      ],
+      "outputs": [
+        {
+          "name": "model",
+          "type": "COGVIDEOMODEL",
+          "links": [
+            144
+          ]
+        },
+        {
+          "name": "vae",
+          "type": "VAE",
+          "links": [
+            132,
+            141
+          ],
+          "slot_index": 1
+        }
+      ],
+      "properties": {
+        "Node name for S&R": "DownloadAndLoadCogVideoModel"
+      },
+      "widgets_values": [
+        "THUDM/CogVideoX-5b-I2V",
+        "bf16",
+        "disabled",
+        false,
+        "sdpa",
+        "main_device"
+      ]
+    },
+    {
+      "id": 30,
+      "type": "CogVideoTextEncode",
+      "pos": {
+        "0": 493,
+        "1": 303
+      },
+      "size": {
+        "0": 471.90142822265625,
+        "1": 168.08047485351562
+      },
+      "flags": {},
+      "order": 4,
+      "mode": 0,
+      "inputs": [
+        {
+          "name": "clip",
+          "type": "CLIP",
+          "link": 54
+        }
+      ],
+      "outputs": [
+        {
+          "name": "conditioning",
+          "type": "CONDITIONING",
+          "links": [
+            145
+          ],
+          "slot_index": 0,
+          "shape": 3
+        },
+        {
+          "name": "clip",
+          "type": "CLIP",
+          "links": [
+            149
+          ],
+          "slot_index": 1
+        }
+      ],
+      "properties": {
+        "Node name for S&R": "CogVideoTextEncode"
+      },
+      "widgets_values": [
+        "a majestic stag is grazing in an enhanced forest, basking in the setting sun filtered by the trees",
+        1,
+        false
+      ]
+    },
+    {
+      "id": 37,
+      "type": "ImageResizeKJ",
+      "pos": {
+        "0": 784,
+        "1": 731
+      },
+      "size": {
+        "0": 315,
+        "1": 266
+      },
+      "flags": {},
+      "order": 3,
+      "mode": 0,
+      "inputs": [
+        {
+          "name": "image",
+          "type": "IMAGE",
+          "link": 71
+        },
+        {
+          "name": "get_image_size",
+          "type": "IMAGE",
+          "link": null,
+          "shape": 7
+        },
+        {
+          "name": "width_input",
+          "type": "INT",
+          "link": null,
+          "widget": {
+            "name": "width_input"
+          }
+        },
+        {
+          "name": "height_input",
+          "type": "INT",
+          "link": null,
+          "widget": {
+            "name": "height_input"
+          }
+        }
+      ],
+      "outputs": [
+        {
+          "name": "IMAGE",
+          "type": "IMAGE",
+          "links": [
+            142
+          ],
+          "slot_index": 0,
+          "shape": 3
+        },
+        {
+          "name": "width",
+          "type": "INT",
+          "links": null,
+          "shape": 3
+        },
+        {
+          "name": "height",
+          "type": "INT",
+          "links": null,
+          "shape": 3
+        }
+      ],
+      "properties": {
+        "Node name for S&R": "ImageResizeKJ"
+      },
+      "widgets_values": [
+        720,
+        480,
+        "lanczos",
+        false,
+        16,
+        0,
+        0,
+        "disabled"
+      ]
+    },
+    {
+      "id": 36,
+      "type": "LoadImage",
+      "pos": {
+        "0": 335,
+        "1": 731
+      },
+      "size": {
+        "0": 402.06353759765625,
+        "1": 396.6225891113281
+      },
+      "flags": {},
+      "order": 1,
+      "mode": 0,
+      "inputs": [],
+      "outputs": [
+        {
+          "name": "IMAGE",
+          "type": "IMAGE",
+          "links": [
+            71
+          ],
+          "slot_index": 0,
+          "shape": 3
+        },
+        {
+          "name": "MASK",
+          "type": "MASK",
+          "links": null,
+          "shape": 3
+        }
+      ],
+      "properties": {
+        "Node name for S&R": "LoadImage"
+      },
+      "widgets_values": [
+        "sd3stag.png",
+        "image"
+      ]
+    },
+    {
+      "id": 20,
+      "type": "CLIPLoader",
+      "pos": {
+        "0": -2,
+        "1": 304
+      },
+      "size": {
+        "0": 451.30548095703125,
+        "1": 82
+      },
+      "flags": {},
+      "order": 2,
+      "mode": 0,
+      "inputs": [],
+      "outputs": [
+        {
+          "name": "CLIP",
+          "type": "CLIP",
+          "links": [
+            54
+          ],
+          "slot_index": 0,
+          "shape": 3
+        }
+      ],
+      "properties": {
+        "Node name for S&R": "CLIPLoader"
+      },
+      "widgets_values": [
+        "t5\\google_t5-v1_1-xxl_encoderonly-fp8_e4m3fn.safetensors",
+        "sd3"
+      ]
+    },
+    {
+      "id": 60,
+      "type": "CogVideoDecode",
+      "pos": {
+        "0": 1523,
+        "1": -6
+      },
+      "size": {
+        "0": 315,
+        "1": 198
+      },
+      "flags": {},
+      "order": 8,
+      "mode": 0,
+      "inputs": [
+        {
+          "name": "vae",
+          "type": "VAE",
+          "link": 132
+        },
+        {
+          "name": "samples",
+          "type": "LATENT",
+          "link": 148
+        }
+      ],
+      "outputs": [
+        {
+          "name": "images",
+          "type": "IMAGE",
+          "links": [
+            134
+          ]
+        }
+      ],
+      "properties": {
+        "Node name for S&R": "CogVideoDecode"
+      },
+      "widgets_values": [
+        true,
+        240,
+        360,
+        0.2,
+        0.2,
+        true
+      ]
+    },
+    {
+      "id": 44,
+      "type": "VHS_VideoCombine",
+      "pos": {
+        "0": 1884,
+        "1": -6
+      },
+      "size": [
+        605.3909912109375,
+        714.2606608072917
+      ],
+      "flags": {},
+      "order": 9,
+      "mode": 0,
+      "inputs": [
+        {
+          "name": "images",
+          "type": "IMAGE",
+          "link": 134
+        },
+        {
+          "name": "audio",
+          "type": "AUDIO",
+          "link": null,
+          "shape": 7
+        },
+        {
+          "name": "meta_batch",
+          "type": "VHS_BatchManager",
+          "link": null,
+          "shape": 7
+        },
+        {
+          "name": "vae",
+          "type": "VAE",
+          "link": null,
+          "shape": 7
+        }
+      ],
+      "outputs": [
+        {
+          "name": "Filenames",
+          "type": "VHS_FILENAMES",
+          "links": null,
+          "shape": 3
+        }
+      ],
+      "properties": {
+        "Node name for S&R": "VHS_VideoCombine"
+      },
+      "widgets_values": {
+        "frame_rate": 8,
+        "loop_count": 0,
+        "filename_prefix": "CogVideoX-I2V",
+        "format": "video/h264-mp4",
+        "pix_fmt": "yuv420p",
+        "crf": 19,
+        "save_metadata": true,
+        "pingpong": false,
+        "save_output": true,
+        "videopreview": {
+          "hidden": false,
+          "paused": false,
+          "params": {
+            "filename": "CogVideoX-I2V_00001.mp4",
+            "subfolder": "",
+            "type": "temp",
+            "format": "video/h264-mp4",
+            "frame_rate": 8
+          },
+          "muted": false
+        }
+      }
+    }
+  ],
+  "links": [
+    [
+      54,
+      20,
+      0,
+      30,
+      0,
+      "CLIP"
+    ],
+    [
+      71,
+      36,
+      0,
+      37,
+      0,
+      "IMAGE"
+    ],
+    [
+      132,
+      59,
+      1,
+      60,
+      0,
+      "VAE"
+    ],
+    [
+      134,
+      60,
+      0,
+      44,
+      0,
+      "IMAGE"
+    ],
+    [
+      141,
+      59,
+      1,
+      62,
+      0,
+      "VAE"
+    ],
+    [
+      142,
+      37,
+      0,
+      62,
+      1,
+      "IMAGE"
+    ],
+    [
+      144,
+      59,
+      0,
+      63,
+      0,
+      "COGVIDEOMODEL"
+    ],
+    [
+      145,
+      30,
+      0,
+      63,
+      1,
+      "CONDITIONING"
+    ],
+    [
+      146,
+      31,
+      0,
+      63,
+      2,
+      "CONDITIONING"
+    ],
+    [
+      147,
+      62,
+      0,
+      63,
+      4,
+      "LATENT"
+    ],
+    [
+      148,
+      63,
+      0,
+      60,
+      1,
+      "LATENT"
+    ],
+    [
+      149,
+      30,
+      1,
+      31,
+      0,
+      "CLIP"
+    ]
+  ],
+  "groups": [],
+  "config": {},
+  "extra": {
+    "ds": {
+      "scale": 0.7627768444387059,
+      "offset": [
+        648.7113591814891,
+        185.9907078691075
+      ]
+    }
+  },
+  "version": 0.4
+}

custom_nodes/ComfyUI-CogVideoXWrapper/example_workflows/cogvideox_1_0_5b_I2V_noise_warp_01.json

@@ -0,0 +1,1291 @@
+{
+  "last_node_id": 84,
+  "last_link_id": 190,
+  "nodes": [
+    {
+      "id": 31,
+      "type": "CogVideoTextEncode",
+      "pos": [
+        497,
+        520
+      ],
+      "size": [
+        463.01251220703125,
+        144
+      ],
+      "flags": {},
+      "order": 10,
+      "mode": 0,
+      "inputs": [
+        {
+          "name": "clip",
+          "type": "CLIP",
+          "link": 149
+        }
+      ],
+      "outputs": [
+        {
+          "name": "conditioning",
+          "type": "CONDITIONING",
+          "links": [
+            146
+          ],
+          "slot_index": 0,
+          "shape": 3
+        },
+        {
+          "name": "clip",
+          "type": "CLIP",
+          "links": null
+        }
+      ],
+      "properties": {
+        "Node name for S&R": "CogVideoTextEncode"
+      },
+      "widgets_values": [
+        "The video is not of a high quality, it has a low resolution. Watermark present in each frame. Strange motion trajectory. ",
+        1,
+        true
+      ]
+    },
+    {
+      "id": 20,
+      "type": "CLIPLoader",
+      "pos": [
+        -2,
+        304
+      ],
+      "size": [
+        451.30548095703125,
+        82
+      ],
+      "flags": {},
+      "order": 0,
+      "mode": 0,
+      "inputs": [],
+      "outputs": [
+        {
+          "name": "CLIP",
+          "type": "CLIP",
+          "links": [
+            54
+          ],
+          "slot_index": 0,
+          "shape": 3
+        }
+      ],
+      "properties": {
+        "Node name for S&R": "CLIPLoader"
+      },
+      "widgets_values": [
+        "t5\\google_t5-v1_1-xxl_encoderonly-fp8_e4m3fn.safetensors",
+        "sd3",
+        "default"
+      ]
+    },
+    {
+      "id": 74,
+      "type": "ImageConcatMulti",
+      "pos": [
+        1787.351318359375,
+        513.0852661132812
+      ],
+      "size": [
+        210,
+        150
+      ],
+      "flags": {},
+      "order": 19,
+      "mode": 0,
+      "inputs": [
+        {
+          "name": "image_1",
+          "type": "IMAGE",
+          "link": 171
+        },
+        {
+          "name": "image_2",
+          "type": "IMAGE",
+          "link": 184
+        }
+      ],
+      "outputs": [
+        {
+          "name": "images",
+          "type": "IMAGE",
+          "links": [
+            170
+          ],
+          "slot_index": 0
+        }
+      ],
+      "properties": {},
+      "widgets_values": [
+        2,
+        "right",
+        false,
+        null
+      ]
+    },
+    {
+      "id": 60,
+      "type": "CogVideoDecode",
+      "pos": [
+        1518.4959716796875,
+        -16.81044578552246
+      ],
+      "size": [
+        315,
+        198
+      ],
+      "flags": {},
+      "order": 18,
+      "mode": 0,
+      "inputs": [
+        {
+          "name": "vae",
+          "type": "VAE",
+          "link": 132
+        },
+        {
+          "name": "samples",
+          "type": "LATENT",
+          "link": 148
+        }
+      ],
+      "outputs": [
+        {
+          "name": "images",
+          "type": "IMAGE",
+          "links": [
+            184
+          ],
+          "slot_index": 0
+        }
+      ],
+      "properties": {
+        "Node name for S&R": "CogVideoDecode"
+      },
+      "widgets_values": [
+        true,
+        240,
+        360,
+        0.2,
+        0.2,
+        true
+      ]
+    },
+    {
+      "id": 72,
+      "type": "CogVideoLoraSelect",
+      "pos": [
+        149.58236694335938,
+        -19.5003604888916
+      ],
+      "size": [
+        429.9602355957031,
+        108.1800765991211
+      ],
+      "flags": {},
+      "order": 1,
+      "mode": 0,
+      "inputs": [
+        {
+          "name": "prev_lora",
+          "type": "COGLORA",
+          "link": null,
+          "shape": 7
+        }
+      ],
+      "outputs": [
+        {
+          "name": "lora",
+          "type": "COGLORA",
+          "links": [
+            174
+          ],
+          "slot_index": 0
+        }
+      ],
+      "properties": {
+        "Node name for S&R": "CogVideoLoraSelect"
+      },
+      "widgets_values": [
+        "I2V5B_final_i30000_lora_weights.safetensors",
+        1,
+        false
+      ]
+    },
+    {
+      "id": 59,
+      "type": "DownloadAndLoadCogVideoModel",
+      "pos": [
+        620.1983032226562,
+        -39.41391372680664
+      ],
+      "size": [
+        315,
+        218
+      ],
+      "flags": {},
+      "order": 8,
+      "mode": 0,
+      "inputs": [
+        {
+          "name": "block_edit",
+          "type": "TRANSFORMERBLOCKS",
+          "link": null,
+          "shape": 7
+        },
+        {
+          "name": "lora",
+          "type": "COGLORA",
+          "link": 174,
+          "shape": 7
+        },
+        {
+          "name": "compile_args",
+          "type": "COMPILEARGS",
+          "link": null,
+          "shape": 7
+        }
+      ],
+      "outputs": [
+        {
+          "name": "model",
+          "type": "COGVIDEOMODEL",
+          "links": [
+            144
+          ]
+        },
+        {
+          "name": "vae",
+          "type": "VAE",
+          "links": [
+            132,
+            141,
+            165
+          ],
+          "slot_index": 1
+        }
+      ],
+      "properties": {
+        "Node name for S&R": "DownloadAndLoadCogVideoModel"
+      },
+      "widgets_values": [
+        "THUDM/CogVideoX-5b-I2V",
+        "bf16",
+        "disabled",
+        false,
+        "sageattn",
+        "main_device"
+      ]
+    },
+    {
+      "id": 30,
+      "type": "CogVideoTextEncode",
+      "pos": [
+        493,
+        303
+      ],
+      "size": [
+        471.90142822265625,
+        168.08047485351562
+      ],
+      "flags": {},
+      "order": 7,
+      "mode": 0,
+      "inputs": [
+        {
+          "name": "clip",
+          "type": "CLIP",
+          "link": 54
+        }
+      ],
+      "outputs": [
+        {
+          "name": "conditioning",
+          "type": "CONDITIONING",
+          "links": [
+            145
+          ],
+          "slot_index": 0,
+          "shape": 3
+        },
+        {
+          "name": "clip",
+          "type": "CLIP",
+          "links": [
+            149
+          ],
+          "slot_index": 1
+        }
+      ],
+      "properties": {
+        "Node name for S&R": "CogVideoTextEncode"
+      },
+      "widgets_values": [
+        "mouse knight walking in a forest",
+        1,
+        false
+      ]
+    },
+    {
+      "id": 63,
+      "type": "CogVideoSampler",
+      "pos": [
+        1144.7025146484375,
+        55.98257064819336
+      ],
+      "size": [
+        330,
+        594
+      ],
+      "flags": {},
+      "order": 17,
+      "mode": 0,
+      "inputs": [
+        {
+          "name": "model",
+          "type": "COGVIDEOMODEL",
+          "link": 144
+        },
+        {
+          "name": "positive",
+          "type": "CONDITIONING",
+          "link": 145
+        },
+        {
+          "name": "negative",
+          "type": "CONDITIONING",
+          "link": 146
+        },
+        {
+          "name": "samples",
+          "type": "LATENT",
+          "link": 164,
+          "shape": 7
+        },
+        {
+          "name": "image_cond_latents",
+          "type": "LATENT",
+          "link": 147,
+          "shape": 7
+        },
+        {
+          "name": "context_options",
+          "type": "COGCONTEXT",
+          "link": null,
+          "shape": 7
+        },
+        {
+          "name": "controlnet",
+          "type": "COGVIDECONTROLNET",
+          "link": null,
+          "shape": 7
+        },
+        {
+          "name": "tora_trajectory",
+          "type": "TORAFEATURES",
+          "link": null,
+          "shape": 7
+        },
+        {
+          "name": "fastercache",
+          "type": "FASTERCACHEARGS",
+          "link": null,
+          "shape": 7
+        },
+        {
+          "name": "feta_args",
+          "type": "FETAARGS",
+          "link": null,
+          "shape": 7
+        }
+      ],
+      "outputs": [
+        {
+          "name": "samples",
+          "type": "LATENT",
+          "links": [
+            148
+          ]
+        }
+      ],
+      "properties": {
+        "Node name for S&R": "CogVideoSampler"
+      },
+      "widgets_values": [
+        49,
+        25,
+        6,
+        0,
+        "fixed",
+        "CogVideoXDDIM",
+        1
+      ]
+    },
+    {
+      "id": 79,
+      "type": "Note",
+      "pos": [
+        141.44003295898438,
+        -129.33815002441406
+      ],
+      "size": [
+        436.1673889160156,
+        58
+      ],
+      "flags": {},
+      "order": 2,
+      "mode": 0,
+      "inputs": [],
+      "outputs": [],
+      "properties": {},
+      "widgets_values": [
+        "https://huggingface.co/VGenAI-Netflix-Eyeline-Research/Go-with-the-Flow/blob/main/I2V5B_final_i38800_nearest_lora_weights.safetensors"
+      ],
+      "color": "#432",
+      "bgcolor": "#653"
+    },
+    {
+      "id": 76,
+      "type": "VHS_VideoCombine",
+      "pos": [
+        1955.22119140625,
+        841.7718505859375
+      ],
+      "size": [
+        1141.2095947265625,
+        1095.4730224609375
+      ],
+      "flags": {},
+      "order": 16,
+      "mode": 2,
+      "inputs": [
+        {
+          "name": "images",
+          "type": "IMAGE",
+          "link": 185
+        },
+        {
+          "name": "audio",
+          "type": "AUDIO",
+          "link": null,
+          "shape": 7
+        },
+        {
+          "name": "meta_batch",
+          "type": "VHS_BatchManager",
+          "link": null,
+          "shape": 7
+        },
+        {
+          "name": "vae",
+          "type": "VAE",
+          "link": null,
+          "shape": 7
+        }
+      ],
+      "outputs": [
+        {
+          "name": "Filenames",
+          "type": "VHS_FILENAMES",
+          "links": null,
+          "shape": 3
+        }
+      ],
+      "properties": {
+        "Node name for S&R": "VHS_VideoCombine"
+      },
+      "widgets_values": {
+        "frame_rate": 8,
+        "loop_count": 0,
+        "filename_prefix": "CogVideoX-I2V",
+        "format": "video/h264-mp4",
+        "pix_fmt": "yuv420p",
+        "crf": 19,
+        "save_metadata": true,
+        "trim_to_audio": false,
+        "pingpong": false,
+        "save_output": false,
+        "videopreview": {
+          "hidden": false,
+          "paused": false,
+          "params": {
+            "filename": "CogVideoX-I2V_00001.mp4",
+            "subfolder": "",
+            "type": "temp",
+            "format": "video/h264-mp4",
+            "frame_rate": 8,
+            "workflow": "CogVideoX-I2V_00001.png",
+            "fullpath": "N:\\AI\\ComfyUI\\temp\\CogVideoX-I2V_00001.mp4"
+          },
+          "muted": false
+        }
+      }
+    },
+    {
+      "id": 80,
+      "type": "Note",
+      "pos": [
+        1648.847900390625,
+        1100.5545654296875
+      ],
+      "size": [
+        249.00543212890625,
+        58
+      ],
+      "flags": {},
+      "order": 3,
+      "mode": 0,
+      "inputs": [],
+      "outputs": [],
+      "properties": {},
+      "widgets_values": [
+        "This is just for testing the noise"
+      ],
+      "color": "#432",
+      "bgcolor": "#653"
+    },
+    {
+      "id": 73,
+      "type": "CogVideoDecode",
+      "pos": [
+        1567.16064453125,
+        842.2813110351562
+      ],
+      "size": [
+        315,
+        198
+      ],
+      "flags": {},
+      "order": 14,
+      "mode": 2,
+      "inputs": [
+        {
+          "name": "vae",
+          "type": "VAE",
+          "link": 165
+        },
+        {
+          "name": "samples",
+          "type": "LATENT",
+          "link": 167
+        }
+      ],
+      "outputs": [
+        {
+          "name": "images",
+          "type": "IMAGE",
+          "links": [
+            185
+          ],
+          "slot_index": 0
+        }
+      ],
+      "properties": {
+        "Node name for S&R": "CogVideoDecode"
+      },
+      "widgets_values": [
+        true,
+        240,
+        360,
+        0.2,
+        0.2,
+        true
+      ]
+    },
+    {
+      "id": 68,
+      "type": "GetImageSizeAndCount",
+      "pos": [
+        -195.5599822998047,
+        1273.8702392578125
+      ],
+      "size": [
+        277.20001220703125,
+        86
+      ],
+      "flags": {},
+      "order": 9,
+      "mode": 0,
+      "inputs": [
+        {
+          "name": "image",
+          "type": "IMAGE",
+          "link": 181
+        }
+      ],
+      "outputs": [
+        {
+          "name": "image",
+          "type": "IMAGE",
+          "links": [
+            178
+          ],
+          "slot_index": 0
+        },
+        {
+          "name": "1024 width",
+          "type": "INT",
+          "links": null
+        },
+        {
+          "name": "768 height",
+          "type": "INT",
+          "links": null
+        },
+        {
+          "name": "49 count",
+          "type": "INT",
+          "links": null
+        }
+      ],
+      "properties": {
+        "Node name for S&R": "GetImageSizeAndCount"
+      }
+    },
+    {
+      "id": 62,
+      "type": "CogVideoImageEncode",
+      "pos": [
+        612.8922729492188,
+        751.6295776367188
+      ],
+      "size": [
+        315,
+        194
+      ],
+      "flags": {},
+      "order": 15,
+      "mode": 0,
+      "inputs": [
+        {
+          "name": "vae",
+          "type": "VAE",
+          "link": 141
+        },
+        {
+          "name": "start_image",
+          "type": "IMAGE",
+          "link": 190
+        },
+        {
+          "name": "end_image",
+          "type": "IMAGE",
+          "link": null,
+          "shape": 7
+        }
+      ],
+      "outputs": [
+        {
+          "name": "samples",
+          "type": "LATENT",
+          "links": [
+            147
+          ]
+        }
+      ],
+      "properties": {
+        "Node name for S&R": "CogVideoImageEncode"
+      },
+      "widgets_values": [
+        false,
+        0,
+        1,
+        0,
+        1
+      ]
+    },
+    {
+      "id": 82,
+      "type": "Note",
+      "pos": [
+        -533.0764770507812,
+        1158.188232421875
+      ],
+      "size": [
+        364.71002197265625,
+        58
+      ],
+      "flags": {},
+      "order": 4,
+      "mode": 0,
+      "inputs": [],
+      "outputs": [],
+      "properties": {},
+      "widgets_values": [
+        "Input video that's used to create the noise"
+      ],
+      "color": "#432",
+      "bgcolor": "#653"
+    },
+    {
+      "id": 64,
+      "type": "GetWarpedNoiseFromVideo",
+      "pos": [
+        674.1111450195312,
+        1289.6090087890625
+      ],
+      "size": [
+        315,
+        222
+      ],
+      "flags": {},
+      "order": 12,
+      "mode": 0,
+      "inputs": [
+        {
+          "name": "images",
+          "type": "IMAGE",
+          "link": 161
+        }
+      ],
+      "outputs": [
+        {
+          "name": "noise",
+          "type": "LATENT",
+          "links": [
+            164,
+            167
+          ],
+          "slot_index": 0
+        },
+        {
+          "name": "visualization",
+          "type": "IMAGE",
+          "links": null
+        }
+      ],
+      "properties": {
+        "Node name for S&R": "GetWarpedNoiseFromVideo"
+      },
+      "widgets_values": [
+        16,
+        "nearest",
+        13,
+        0.5,
+        "BCTHW",
+        99026504067718,
+        "fixed"
+      ]
+    },
+    {
+      "id": 83,
+      "type": "Note",
+      "pos": [
+        679.4560546875,
+        1179.797607421875
+      ],
+      "size": [
+        293.1480407714844,
+        58
+      ],
+      "flags": {},
+      "order": 5,
+      "mode": 0,
+      "inputs": [],
+      "outputs": [],
+      "properties": {},
+      "widgets_values": [
+        "https://github.com/kijai/ComfyUI-VideoNoiseWarp"
+      ],
+      "color": "#432",
+      "bgcolor": "#653"
+    },
+    {
+      "id": 69,
+      "type": "VHS_LoadVideo",
+      "pos": [
+        -536.2808837890625,
+        1265.4254150390625
+      ],
+      "size": [
+        247.455078125,
+        446.3408203125
+      ],
+      "flags": {},
+      "order": 6,
+      "mode": 0,
+      "inputs": [
+        {
+          "name": "meta_batch",
+          "type": "VHS_BatchManager",
+          "link": null,
+          "shape": 7
+        },
+        {
+          "name": "vae",
+          "type": "VAE",
+          "link": null,
+          "shape": 7
+        }
+      ],
+      "outputs": [
+        {
+          "name": "IMAGE",
+          "type": "IMAGE",
+          "links": [
+            181
+          ],
+          "slot_index": 0
+        },
+        {
+          "name": "frame_count",
+          "type": "INT",
+          "links": null
+        },
+        {
+          "name": "audio",
+          "type": "AUDIO",
+          "links": null
+        },
+        {
+          "name": "video_info",
+          "type": "VHS_VIDEOINFO",
+          "links": null
+        }
+      ],
+      "properties": {
+        "Node name for S&R": "VHS_LoadVideo"
+      },
+      "widgets_values": {
+        "video": "AnimateDiff_00023 (16).mp4",
+        "force_rate": 0,
+        "force_size": "Disabled",
+        "custom_width": 512,
+        "custom_height": 512,
+        "frame_load_cap": 0,
+        "skip_first_frames": 0,
+        "select_every_nth": 1,
+        "choose video to upload": "image",
+        "videopreview": {
+          "hidden": false,
+          "paused": false,
+          "params": {
+            "force_rate": 0,
+            "frame_load_cap": 0,
+            "skip_first_frames": 0,
+            "select_every_nth": 1,
+            "filename": "AnimateDiff_00023 (16).mp4",
+            "type": "input",
+            "format": "video/mp4"
+          },
+          "muted": false
+        }
+      }
+    },
+    {
+      "id": 44,
+      "type": "VHS_VideoCombine",
+      "pos": [
+        2071.7626953125,
+        -69.11408233642578
+      ],
+      "size": [
+        1141.2095947265625,
+        721.7365112304688
+      ],
+      "flags": {},
+      "order": 20,
+      "mode": 0,
+      "inputs": [
+        {
+          "name": "images",
+          "type": "IMAGE",
+          "link": 170
+        },
+        {
+          "name": "audio",
+          "type": "AUDIO",
+          "link": null,
+          "shape": 7
+        },
+        {
+          "name": "meta_batch",
+          "type": "VHS_BatchManager",
+          "link": null,
+          "shape": 7
+        },
+        {
+          "name": "vae",
+          "type": "VAE",
+          "link": null,
+          "shape": 7
+        }
+      ],
+      "outputs": [
+        {
+          "name": "Filenames",
+          "type": "VHS_FILENAMES",
+          "links": null,
+          "shape": 3
+        }
+      ],
+      "properties": {
+        "Node name for S&R": "VHS_VideoCombine"
+      },
+      "widgets_values": {
+        "frame_rate": 8,
+        "loop_count": 0,
+        "filename_prefix": "CogVideoX_I2V_NoiseWarp",
+        "format": "video/h264-mp4",
+        "pix_fmt": "yuv420p",
+        "crf": 19,
+        "save_metadata": true,
+        "trim_to_audio": false,
+        "pingpong": false,
+        "save_output": false,
+        "videopreview": {
+          "hidden": false,
+          "paused": false,
+          "params": {
+            "filename": "CogVideoX-I2V_00002.mp4",
+            "subfolder": "",
+            "type": "temp",
+            "format": "video/h264-mp4",
+            "frame_rate": 8,
+            "workflow": "CogVideoX-I2V_00002.png",
+            "fullpath": "N:\\AI\\ComfyUI\\temp\\CogVideoX-I2V_00002.mp4"
+          },
+          "muted": false
+        }
+      }
+    },
+    {
+      "id": 71,
+      "type": "ImageResizeKJ",
+      "pos": [
+        204.58009338378906,
+        1289.261474609375
+      ],
+      "size": [
+        315,
+        266
+      ],
+      "flags": {},
+      "order": 11,
+      "mode": 0,
+      "inputs": [
+        {
+          "name": "image",
+          "type": "IMAGE",
+          "link": 178
+        },
+        {
+          "name": "get_image_size",
+          "type": "IMAGE",
+          "link": null,
+          "shape": 7
+        },
+        {
+          "name": "width_input",
+          "type": "INT",
+          "link": null,
+          "widget": {
+            "name": "width_input"
+          },
+          "shape": 7
+        },
+        {
+          "name": "height_input",
+          "type": "INT",
+          "link": null,
+          "widget": {
+            "name": "height_input"
+          },
+          "shape": 7
+        }
+      ],
+      "outputs": [
+        {
+          "name": "IMAGE",
+          "type": "IMAGE",
+          "links": [
+            161,
+            171,
+            189
+          ],
+          "slot_index": 0,
+          "shape": 3
+        },
+        {
+          "name": "width",
+          "type": "INT",
+          "links": null,
+          "shape": 3
+        },
+        {
+          "name": "height",
+          "type": "INT",
+          "links": null,
+          "shape": 3
+        }
+      ],
+      "properties": {
+        "Node name for S&R": "ImageResizeKJ"
+      },
+      "widgets_values": [
+        720,
+        480,
+        "lanczos",
+        false,
+        16,
+        0,
+        0,
+        "disabled"
+      ]
+    },
+    {
+      "id": 84,
+      "type": "GetImageRangeFromBatch",
+      "pos": [
+        197.0398712158203,
+        1077.9952392578125
+      ],
+      "size": [
+        340.2047424316406,
+        102
+      ],
+      "flags": {},
+      "order": 13,
+      "mode": 0,
+      "inputs": [
+        {
+          "name": "images",
+          "type": "IMAGE",
+          "link": 189,
+          "shape": 7
+        },
+        {
+          "name": "masks",
+          "type": "MASK",
+          "link": null,
+          "shape": 7
+        }
+      ],
+      "outputs": [
+        {
+          "name": "IMAGE",
+          "type": "IMAGE",
+          "links": [
+            190
+          ],
+          "slot_index": 0
+        },
+        {
+          "name": "MASK",
+          "type": "MASK",
+          "links": null
+        }
+      ],
+      "properties": {
+        "Node name for S&R": "GetImageRangeFromBatch"
+      },
+      "widgets_values": [
+        0,
+        1
+      ]
+    }
+  ],
+  "links": [
+    [
+      54,
+      20,
+      0,
+      30,
+      0,
+      "CLIP"
+    ],
+    [
+      132,
+      59,
+      1,
+      60,
+      0,
+      "VAE"
+    ],
+    [
+      141,
+      59,
+      1,
+      62,
+      0,
+      "VAE"
+    ],
+    [
+      144,
+      59,
+      0,
+      63,
+      0,
+      "COGVIDEOMODEL"
+    ],
+    [
+      145,
+      30,
+      0,
+      63,
+      1,
+      "CONDITIONING"
+    ],
+    [
+      146,
+      31,
+      0,
+      63,
+      2,
+      "CONDITIONING"
+    ],
+    [
+      147,
+      62,
+      0,
+      63,
+      4,
+      "LATENT"
+    ],
+    [
+      148,
+      63,
+      0,
+      60,
+      1,
+      "LATENT"
+    ],
+    [
+      149,
+      30,
+      1,
+      31,
+      0,
+      "CLIP"
+    ],
+    [
+      161,
+      71,
+      0,
+      64,
+      0,
+      "IMAGE"
+    ],
+    [
+      164,
+      64,
+      0,
+      63,
+      3,
+      "LATENT"
+    ],
+    [
+      165,
+      59,
+      1,
+      73,
+      0,
+      "VAE"
+    ],
+    [
+      167,
+      64,
+      0,
+      73,
+      1,
+      "LATENT"
+    ],
+    [
+      170,
+      74,
+      0,
+      44,
+      0,
+      "IMAGE"
+    ],
+    [
+      171,
+      71,
+      0,
+      74,
+      0,
+      "IMAGE"
+    ],
+    [
+      174,
+      72,
+      0,
+      59,
+      1,
+      "COGLORA"
+    ],
+    [
+      178,
+      68,
+      0,
+      71,
+      0,
+      "IMAGE"
+    ],
+    [
+      181,
+      69,
+      0,
+      68,
+      0,
+      "IMAGE"
+    ],
+    [
+      184,
+      60,
+      0,
+      74,
+      1,
+      "IMAGE"
+    ],
+    [
+      185,
+      73,
+      0,
+      76,
+      0,
+      "IMAGE"
+    ],
+    [
+      189,
+      71,
+      0,
+      84,
+      0,
+      "IMAGE"
+    ],
+    [
+      190,
+      84,
+      0,
+      62,
+      1,
+      "IMAGE"
+    ]
+  ],
+  "groups": [],
+  "config": {},
+  "extra": {
+    "ds": {
+      "scale": 0.6115909044841579,
+      "offset": [
+        1276.2661497783536,
+        -1.7440717555266154
+      ]
+    },
+    "node_versions": {
+      "ComfyUI-CogVideoXWrapper": "8c5e4f812d869653a6c201af0dcd6249c18b3231",
+      "comfy-core": "0.3.12",
+      "ComfyUI-KJNodes": "c9c8dcd5e7ed2f7669f130a5ced1e3005264a2de",
+      "ComfyUI-VideoHelperSuite": "c47b10ca1798b4925ff5a5f07d80c51ca80a837d",
+      "ComfyUI-NoiseWarp": "8c5e4f812d869653a6c201af0dcd6249c18b3231"
+    },
+    "VHS_latentpreview": true,
+    "VHS_latentpreviewrate": 0
+  },
+  "version": 0.4
+}

custom_nodes/ComfyUI-CogVideoXWrapper/example_workflows/cogvideox_1_0_5b_T2V_02.json

@@ -0,0 +1,529 @@
+{
+  "last_node_id": 37,
+  "last_link_id": 72,
+  "nodes": [
+    {
+      "id": 30,
+      "type": "CogVideoTextEncode",
+      "pos": {
+        "0": 500,
+        "1": 308
+      },
+      "size": [
+        470.99399664051055,
+        237.5088638951354
+      ],
+      "flags": {},
+      "order": 3,
+      "mode": 0,
+      "inputs": [
+        {
+          "name": "clip",
+          "type": "CLIP",
+          "link": 54
+        }
+      ],
+      "outputs": [
+        {
+          "name": "conditioning",
+          "type": "CONDITIONING",
+          "links": [
+            67
+          ],
+          "slot_index": 0,
+          "shape": 3
+        },
+        {
+          "name": "clip",
+          "type": "CLIP",
+          "links": [
+            65
+          ],
+          "slot_index": 1
+        }
+      ],
+      "properties": {
+        "Node name for S&R": "CogVideoTextEncode"
+      },
+      "widgets_values": [
+        "A golden retriever, sporting sleek black sunglasses, with its lengthy fur flowing in the breeze, sprints playfully across a rooftop terrace, recently refreshed by a light rain. The scene unfolds from a distance, the dog's energetic bounds growing larger as it approaches the camera, its tail wagging with unrestrained joy, while droplets of water glisten on the concrete behind it. The overcast sky provides a dramatic backdrop, emphasizing the vibrant golden coat of the canine as it dashes towards the viewer.\n\n",
+        1,
+        false
+      ]
+    },
+    {
+      "id": 31,
+      "type": "CogVideoTextEncode",
+      "pos": {
+        "0": 503,
+        "1": 602
+      },
+      "size": [
+        464.4980515341475,
+        169.87479027400514
+      ],
+      "flags": {},
+      "order": 4,
+      "mode": 0,
+      "inputs": [
+        {
+          "name": "clip",
+          "type": "CLIP",
+          "link": 65
+        }
+      ],
+      "outputs": [
+        {
+          "name": "conditioning",
+          "type": "CONDITIONING",
+          "links": [
+            68
+          ],
+          "slot_index": 0,
+          "shape": 3
+        },
+        {
+          "name": "clip",
+          "type": "CLIP",
+          "links": null
+        }
+      ],
+      "properties": {
+        "Node name for S&R": "CogVideoTextEncode"
+      },
+      "widgets_values": [
+        "",
+        1,
+        true
+      ]
+    },
+    {
+      "id": 11,
+      "type": "CogVideoDecode",
+      "pos": {
+        "0": 1416,
+        "1": 40
+      },
+      "size": {
+        "0": 300.396484375,
+        "1": 198
+      },
+      "flags": {},
+      "order": 6,
+      "mode": 0,
+      "inputs": [
+        {
+          "name": "vae",
+          "type": "VAE",
+          "link": 71
+        },
+        {
+          "name": "samples",
+          "type": "LATENT",
+          "link": 69
+        }
+      ],
+      "outputs": [
+        {
+          "name": "images",
+          "type": "IMAGE",
+          "links": [
+            59
+          ],
+          "slot_index": 0,
+          "shape": 3
+        }
+      ],
+      "properties": {
+        "Node name for S&R": "CogVideoDecode"
+      },
+      "widgets_values": [
+        false,
+        240,
+        360,
+        0.2,
+        0.2,
+        true
+      ]
+    },
+    {
+      "id": 36,
+      "type": "DownloadAndLoadCogVideoModel",
+      "pos": {
+        "0": 645,
+        "1": 17
+      },
+      "size": {
+        "0": 315,
+        "1": 218
+      },
+      "flags": {},
+      "order": 0,
+      "mode": 0,
+      "inputs": [
+        {
+          "name": "block_edit",
+          "type": "TRANSFORMERBLOCKS",
+          "link": null,
+          "shape": 7
+        },
+        {
+          "name": "lora",
+          "type": "COGLORA",
+          "link": null,
+          "shape": 7
+        },
+        {
+          "name": "compile_args",
+          "type": "COMPILEARGS",
+          "link": null,
+          "shape": 7
+        }
+      ],
+      "outputs": [
+        {
+          "name": "model",
+          "type": "COGVIDEOMODEL",
+          "links": [
+            70
+          ]
+        },
+        {
+          "name": "vae",
+          "type": "VAE",
+          "links": [
+            71
+          ],
+          "slot_index": 1
+        }
+      ],
+      "properties": {
+        "Node name for S&R": "DownloadAndLoadCogVideoModel"
+      },
+      "widgets_values": [
+        "THUDM/CogVideoX-5b",
+        "bf16",
+        "disabled",
+        false,
+        "sdpa",
+        "main_device"
+      ]
+    },
+    {
+      "id": 20,
+      "type": "CLIPLoader",
+      "pos": {
+        "0": 5,
+        "1": 308
+      },
+      "size": {
+        "0": 451.30548095703125,
+        "1": 82
+      },
+      "flags": {},
+      "order": 1,
+      "mode": 0,
+      "inputs": [],
+      "outputs": [
+        {
+          "name": "CLIP",
+          "type": "CLIP",
+          "links": [
+            54
+          ],
+          "slot_index": 0,
+          "shape": 3
+        }
+      ],
+      "properties": {
+        "Node name for S&R": "CLIPLoader"
+      },
+      "widgets_values": [
+        "t5\\google_t5-v1_1-xxl_encoderonly-fp8_e4m3fn.safetensors",
+        "sd3"
+      ]
+    },
+    {
+      "id": 37,
+      "type": "EmptyLatentImage",
+      "pos": {
+        "0": 643,
+        "1": 827
+      },
+      "size": {
+        "0": 315,
+        "1": 106
+      },
+      "flags": {},
+      "order": 2,
+      "mode": 0,
+      "inputs": [],
+      "outputs": [
+        {
+          "name": "LATENT",
+          "type": "LATENT",
+          "links": [
+            72
+          ]
+        }
+      ],
+      "properties": {
+        "Node name for S&R": "EmptyLatentImage"
+      },
+      "widgets_values": [
+        720,
+        480,
+        1
+      ]
+    },
+    {
+      "id": 35,
+      "type": "CogVideoSampler",
+      "pos": {
+        "0": 1042,
+        "1": 291
+      },
+      "size": [
+        330,
+        574
+      ],
+      "flags": {},
+      "order": 5,
+      "mode": 0,
+      "inputs": [
+        {
+          "name": "model",
+          "type": "COGVIDEOMODEL",
+          "link": 70
+        },
+        {
+          "name": "positive",
+          "type": "CONDITIONING",
+          "link": 67
+        },
+        {
+          "name": "negative",
+          "type": "CONDITIONING",
+          "link": 68
+        },
+        {
+          "name": "samples",
+          "type": "LATENT",
+          "link": 72,
+          "shape": 7
+        },
+        {
+          "name": "image_cond_latents",
+          "type": "LATENT",
+          "link": null,
+          "shape": 7
+        },
+        {
+          "name": "context_options",
+          "type": "COGCONTEXT",
+          "link": null,
+          "shape": 7
+        },
+        {
+          "name": "controlnet",
+          "type": "COGVIDECONTROLNET",
+          "link": null,
+          "shape": 7
+        },
+        {
+          "name": "tora_trajectory",
+          "type": "TORAFEATURES",
+          "link": null,
+          "shape": 7
+        },
+        {
+          "name": "fastercache",
+          "type": "FASTERCACHEARGS",
+          "link": null,
+          "shape": 7
+        }
+      ],
+      "outputs": [
+        {
+          "name": "samples",
+          "type": "LATENT",
+          "links": [
+            69
+          ]
+        }
+      ],
+      "properties": {
+        "Node name for S&R": "CogVideoSampler"
+      },
+      "widgets_values": [
+        49,
+        50,
+        6,
+        0,
+        "fixed",
+        "CogVideoXDDIM",
+        1
+      ]
+    },
+    {
+      "id": 33,
+      "type": "VHS_VideoCombine",
+      "pos": {
+        "0": 1767,
+        "1": 39
+      },
+      "size": [
+        778.7022705078125,
+        829.801513671875
+      ],
+      "flags": {},
+      "order": 7,
+      "mode": 0,
+      "inputs": [
+        {
+          "name": "images",
+          "type": "IMAGE",
+          "link": 59
+        },
+        {
+          "name": "audio",
+          "type": "AUDIO",
+          "link": null,
+          "shape": 7
+        },
+        {
+          "name": "meta_batch",
+          "type": "VHS_BatchManager",
+          "link": null,
+          "shape": 7
+        },
+        {
+          "name": "vae",
+          "type": "VAE",
+          "link": null,
+          "shape": 7
+        }
+      ],
+      "outputs": [
+        {
+          "name": "Filenames",
+          "type": "VHS_FILENAMES",
+          "links": null,
+          "shape": 3
+        }
+      ],
+      "properties": {
+        "Node name for S&R": "VHS_VideoCombine"
+      },
+      "widgets_values": {
+        "frame_rate": 8,
+        "loop_count": 0,
+        "filename_prefix": "CogVideoX5B-T2V",
+        "format": "video/h264-mp4",
+        "pix_fmt": "yuv420p",
+        "crf": 19,
+        "save_metadata": true,
+        "pingpong": false,
+        "save_output": false,
+        "videopreview": {
+          "hidden": false,
+          "paused": false,
+          "params": {
+            "filename": "CogVideoX5B_00001.mp4",
+            "subfolder": "",
+            "type": "temp",
+            "format": "video/h264-mp4",
+            "frame_rate": 8
+          },
+          "muted": false
+        }
+      }
+    }
+  ],
+  "links": [
+    [
+      54,
+      20,
+      0,
+      30,
+      0,
+      "CLIP"
+    ],
+    [
+      59,
+      11,
+      0,
+      33,
+      0,
+      "IMAGE"
+    ],
+    [
+      65,
+      30,
+      1,
+      31,
+      0,
+      "CLIP"
+    ],
+    [
+      67,
+      30,
+      0,
+      35,
+      1,
+      "CONDITIONING"
+    ],
+    [
+      68,
+      31,
+      0,
+      35,
+      2,
+      "CONDITIONING"
+    ],
+    [
+      69,
+      35,
+      0,
+      11,
+      1,
+      "LATENT"
+    ],
+    [
+      70,
+      36,
+      0,
+      35,
+      0,
+      "COGVIDEOMODEL"
+    ],
+    [
+      71,
+      36,
+      1,
+      11,
+      0,
+      "VAE"
+    ],
+    [
+      72,
+      37,
+      0,
+      35,
+      3,
+      "LATENT"
+    ]
+  ],
+  "groups": [],
+  "config": {},
+  "extra": {
+    "ds": {
+      "scale": 0.7627768444387061,
+      "offset": [
+        734.1791945221892,
+        237.29437844909364
+      ]
+    }
+  },
+  "version": 0.4
+}

custom_nodes/ComfyUI-CogVideoXWrapper/example_workflows/cogvideox_1_0_5b_interpolation_02.json

@@ -0,0 +1,864 @@
+{
+  "last_node_id": 68,
+  "last_link_id": 155,
+  "nodes": [
+    {
+      "id": 31,
+      "type": "CogVideoTextEncode",
+      "pos": {
+        "0": 497,
+        "1": 520
+      },
+      "size": {
+        "0": 463.01251220703125,
+        "1": 144
+      },
+      "flags": {},
+      "order": 6,
+      "mode": 0,
+      "inputs": [
+        {
+          "name": "clip",
+          "type": "CLIP",
+          "link": 149
+        }
+      ],
+      "outputs": [
+        {
+          "name": "conditioning",
+          "type": "CONDITIONING",
+          "links": [
+            146
+          ],
+          "slot_index": 0,
+          "shape": 3
+        },
+        {
+          "name": "clip",
+          "type": "CLIP",
+          "links": null
+        }
+      ],
+      "properties": {
+        "Node name for S&R": "CogVideoTextEncode"
+      },
+      "widgets_values": [
+        "The video is not of a high quality, it has a low resolution. Watermark present in each frame. Strange motion trajectory. ",
+        1,
+        true
+      ]
+    },
+    {
+      "id": 63,
+      "type": "CogVideoSampler",
+      "pos": {
+        "0": 1142,
+        "1": 74
+      },
+      "size": [
+        330,
+        574
+      ],
+      "flags": {},
+      "order": 9,
+      "mode": 0,
+      "inputs": [
+        {
+          "name": "model",
+          "type": "COGVIDEOMODEL",
+          "link": 144
+        },
+        {
+          "name": "positive",
+          "type": "CONDITIONING",
+          "link": 145
+        },
+        {
+          "name": "negative",
+          "type": "CONDITIONING",
+          "link": 146
+        },
+        {
+          "name": "samples",
+          "type": "LATENT",
+          "link": null,
+          "shape": 7
+        },
+        {
+          "name": "image_cond_latents",
+          "type": "LATENT",
+          "link": 147,
+          "shape": 7
+        },
+        {
+          "name": "context_options",
+          "type": "COGCONTEXT",
+          "link": null,
+          "shape": 7
+        },
+        {
+          "name": "controlnet",
+          "type": "COGVIDECONTROLNET",
+          "link": null,
+          "shape": 7
+        },
+        {
+          "name": "tora_trajectory",
+          "type": "TORAFEATURES",
+          "link": null,
+          "shape": 7
+        },
+        {
+          "name": "fastercache",
+          "type": "FASTERCACHEARGS",
+          "link": null,
+          "shape": 7
+        }
+      ],
+      "outputs": [
+        {
+          "name": "samples",
+          "type": "LATENT",
+          "links": [
+            148
+          ]
+        }
+      ],
+      "properties": {
+        "Node name for S&R": "CogVideoSampler"
+      },
+      "widgets_values": [
+        49,
+        25,
+        6,
+        0,
+        "fixed",
+        "CogVideoXDDIM",
+        1
+      ]
+    },
+    {
+      "id": 30,
+      "type": "CogVideoTextEncode",
+      "pos": {
+        "0": 493,
+        "1": 303
+      },
+      "size": {
+        "0": 471.90142822265625,
+        "1": 168.08047485351562
+      },
+      "flags": {},
+      "order": 4,
+      "mode": 0,
+      "inputs": [
+        {
+          "name": "clip",
+          "type": "CLIP",
+          "link": 54
+        }
+      ],
+      "outputs": [
+        {
+          "name": "conditioning",
+          "type": "CONDITIONING",
+          "links": [
+            145
+          ],
+          "slot_index": 0,
+          "shape": 3
+        },
+        {
+          "name": "clip",
+          "type": "CLIP",
+          "links": [
+            149
+          ],
+          "slot_index": 1
+        }
+      ],
+      "properties": {
+        "Node name for S&R": "CogVideoTextEncode"
+      },
+      "widgets_values": [
+        "a majestic stag is grazing in an enhanced forest, basking in the setting sun filtered by the trees",
+        1,
+        false
+      ]
+    },
+    {
+      "id": 20,
+      "type": "CLIPLoader",
+      "pos": {
+        "0": -2,
+        "1": 304
+      },
+      "size": {
+        "0": 451.30548095703125,
+        "1": 82
+      },
+      "flags": {},
+      "order": 0,
+      "mode": 0,
+      "inputs": [],
+      "outputs": [
+        {
+          "name": "CLIP",
+          "type": "CLIP",
+          "links": [
+            54
+          ],
+          "slot_index": 0,
+          "shape": 3
+        }
+      ],
+      "properties": {
+        "Node name for S&R": "CLIPLoader"
+      },
+      "widgets_values": [
+        "t5\\google_t5-v1_1-xxl_encoderonly-fp8_e4m3fn.safetensors",
+        "sd3"
+      ]
+    },
+    {
+      "id": 36,
+      "type": "LoadImage",
+      "pos": {
+        "0": 105,
+        "1": 732
+      },
+      "size": {
+        "0": 402.06353759765625,
+        "1": 396.6225891113281
+      },
+      "flags": {},
+      "order": 1,
+      "mode": 0,
+      "inputs": [],
+      "outputs": [
+        {
+          "name": "IMAGE",
+          "type": "IMAGE",
+          "links": [
+            71
+          ],
+          "slot_index": 0,
+          "shape": 3
+        },
+        {
+          "name": "MASK",
+          "type": "MASK",
+          "links": null,
+          "shape": 3
+        }
+      ],
+      "properties": {
+        "Node name for S&R": "LoadImage"
+      },
+      "widgets_values": [
+        "sd3stag.png",
+        "image"
+      ]
+    },
+    {
+      "id": 64,
+      "type": "LoadImage",
+      "pos": {
+        "0": 105,
+        "1": 1189
+      },
+      "size": {
+        "0": 402.06353759765625,
+        "1": 396.6225891113281
+      },
+      "flags": {},
+      "order": 2,
+      "mode": 0,
+      "inputs": [],
+      "outputs": [
+        {
+          "name": "IMAGE",
+          "type": "IMAGE",
+          "links": [
+            151
+          ],
+          "slot_index": 0,
+          "shape": 3
+        },
+        {
+          "name": "MASK",
+          "type": "MASK",
+          "links": null,
+          "shape": 3
+        }
+      ],
+      "properties": {
+        "Node name for S&R": "LoadImage"
+      },
+      "widgets_values": [
+        "sd3stag.png",
+        "image"
+      ]
+    },
+    {
+      "id": 65,
+      "type": "ImageResizeKJ",
+      "pos": {
+        "0": 607,
+        "1": 1188
+      },
+      "size": [
+        315,
+        266
+      ],
+      "flags": {},
+      "order": 7,
+      "mode": 0,
+      "inputs": [
+        {
+          "name": "image",
+          "type": "IMAGE",
+          "link": 151
+        },
+        {
+          "name": "get_image_size",
+          "type": "IMAGE",
+          "link": null,
+          "shape": 7
+        },
+        {
+          "name": "width_input",
+          "type": "INT",
+          "link": null,
+          "widget": {
+            "name": "width_input"
+          },
+          "shape": 7
+        },
+        {
+          "name": "height_input",
+          "type": "INT",
+          "link": null,
+          "widget": {
+            "name": "height_input"
+          },
+          "shape": 7
+        },
+        {
+          "name": "width",
+          "type": "INT",
+          "link": 152,
+          "widget": {
+            "name": "width"
+          }
+        },
+        {
+          "name": "height",
+          "type": "INT",
+          "link": 153,
+          "widget": {
+            "name": "height"
+          }
+        }
+      ],
+      "outputs": [
+        {
+          "name": "IMAGE",
+          "type": "IMAGE",
+          "links": [
+            155
+          ],
+          "slot_index": 0,
+          "shape": 3
+        },
+        {
+          "name": "width",
+          "type": "INT",
+          "links": null,
+          "shape": 3
+        },
+        {
+          "name": "height",
+          "type": "INT",
+          "links": null,
+          "shape": 3
+        }
+      ],
+      "properties": {
+        "Node name for S&R": "ImageResizeKJ"
+      },
+      "widgets_values": [
+        720,
+        480,
+        "lanczos",
+        false,
+        16,
+        0,
+        0,
+        "disabled"
+      ]
+    },
+    {
+      "id": 37,
+      "type": "ImageResizeKJ",
+      "pos": {
+        "0": 593,
+        "1": 731
+      },
+      "size": {
+        "0": 315,
+        "1": 266
+      },
+      "flags": {},
+      "order": 5,
+      "mode": 0,
+      "inputs": [
+        {
+          "name": "image",
+          "type": "IMAGE",
+          "link": 71
+        },
+        {
+          "name": "get_image_size",
+          "type": "IMAGE",
+          "link": null,
+          "shape": 7
+        },
+        {
+          "name": "width_input",
+          "type": "INT",
+          "link": null,
+          "widget": {
+            "name": "width_input"
+          }
+        },
+        {
+          "name": "height_input",
+          "type": "INT",
+          "link": null,
+          "widget": {
+            "name": "height_input"
+          }
+        }
+      ],
+      "outputs": [
+        {
+          "name": "IMAGE",
+          "type": "IMAGE",
+          "links": [
+            142
+          ],
+          "slot_index": 0,
+          "shape": 3
+        },
+        {
+          "name": "width",
+          "type": "INT",
+          "links": [
+            152
+          ],
+          "shape": 3,
+          "slot_index": 1
+        },
+        {
+          "name": "height",
+          "type": "INT",
+          "links": [
+            153
+          ],
+          "shape": 3,
+          "slot_index": 2
+        }
+      ],
+      "properties": {
+        "Node name for S&R": "ImageResizeKJ"
+      },
+      "widgets_values": [
+        720,
+        480,
+        "lanczos",
+        false,
+        16,
+        0,
+        0,
+        "disabled"
+      ]
+    },
+    {
+      "id": 60,
+      "type": "CogVideoDecode",
+      "pos": {
+        "0": 1526,
+        "1": -4
+      },
+      "size": {
+        "0": 315,
+        "1": 198
+      },
+      "flags": {},
+      "order": 10,
+      "mode": 0,
+      "inputs": [
+        {
+          "name": "vae",
+          "type": "VAE",
+          "link": 132
+        },
+        {
+          "name": "samples",
+          "type": "LATENT",
+          "link": 148
+        }
+      ],
+      "outputs": [
+        {
+          "name": "images",
+          "type": "IMAGE",
+          "links": [
+            134
+          ]
+        }
+      ],
+      "properties": {
+        "Node name for S&R": "CogVideoDecode"
+      },
+      "widgets_values": [
+        true,
+        240,
+        360,
+        0.2,
+        0.2,
+        true
+      ]
+    },
+    {
+      "id": 62,
+      "type": "CogVideoImageEncode",
+      "pos": {
+        "0": 1152,
+        "1": 706
+      },
+      "size": {
+        "0": 315,
+        "1": 122
+      },
+      "flags": {},
+      "order": 8,
+      "mode": 0,
+      "inputs": [
+        {
+          "name": "vae",
+          "type": "VAE",
+          "link": 141
+        },
+        {
+          "name": "start_image",
+          "type": "IMAGE",
+          "link": 142
+        },
+        {
+          "name": "end_image",
+          "type": "IMAGE",
+          "link": 155,
+          "shape": 7
+        }
+      ],
+      "outputs": [
+        {
+          "name": "samples",
+          "type": "LATENT",
+          "links": [
+            147
+          ]
+        }
+      ],
+      "properties": {
+        "Node name for S&R": "CogVideoImageEncode"
+      },
+      "widgets_values": [
+        false,
+        0
+      ]
+    },
+    {
+      "id": 44,
+      "type": "VHS_VideoCombine",
+      "pos": {
+        "0": 1884,
+        "1": -3
+      },
+      "size": [
+        605.3909912109375,
+        714.2606608072917
+      ],
+      "flags": {},
+      "order": 11,
+      "mode": 0,
+      "inputs": [
+        {
+          "name": "images",
+          "type": "IMAGE",
+          "link": 134
+        },
+        {
+          "name": "audio",
+          "type": "AUDIO",
+          "link": null,
+          "shape": 7
+        },
+        {
+          "name": "meta_batch",
+          "type": "VHS_BatchManager",
+          "link": null,
+          "shape": 7
+        },
+        {
+          "name": "vae",
+          "type": "VAE",
+          "link": null,
+          "shape": 7
+        }
+      ],
+      "outputs": [
+        {
+          "name": "Filenames",
+          "type": "VHS_FILENAMES",
+          "links": null,
+          "shape": 3
+        }
+      ],
+      "properties": {
+        "Node name for S&R": "VHS_VideoCombine"
+      },
+      "widgets_values": {
+        "frame_rate": 8,
+        "loop_count": 0,
+        "filename_prefix": "CogVideoX-Interpolation",
+        "format": "video/h264-mp4",
+        "pix_fmt": "yuv420p",
+        "crf": 19,
+        "save_metadata": true,
+        "pingpong": false,
+        "save_output": true,
+        "videopreview": {
+          "hidden": false,
+          "paused": false,
+          "params": {
+            "filename": "CogVideoX-I2V_00003.mp4",
+            "subfolder": "",
+            "type": "temp",
+            "format": "video/h264-mp4",
+            "frame_rate": 8
+          },
+          "muted": false
+        }
+      }
+    },
+    {
+      "id": 59,
+      "type": "DownloadAndLoadCogVideoModel",
+      "pos": {
+        "0": 622,
+        "1": -25
+      },
+      "size": [
+        347.24594407027485,
+        218
+      ],
+      "flags": {},
+      "order": 3,
+      "mode": 0,
+      "inputs": [
+        {
+          "name": "block_edit",
+          "type": "TRANSFORMERBLOCKS",
+          "link": null,
+          "shape": 7
+        },
+        {
+          "name": "lora",
+          "type": "COGLORA",
+          "link": null,
+          "shape": 7
+        },
+        {
+          "name": "compile_args",
+          "type": "COMPILEARGS",
+          "link": null,
+          "shape": 7
+        }
+      ],
+      "outputs": [
+        {
+          "name": "model",
+          "type": "COGVIDEOMODEL",
+          "links": [
+            144
+          ]
+        },
+        {
+          "name": "vae",
+          "type": "VAE",
+          "links": [
+            132,
+            141
+          ],
+          "slot_index": 1
+        }
+      ],
+      "properties": {
+        "Node name for S&R": "DownloadAndLoadCogVideoModel"
+      },
+      "widgets_values": [
+        "feizhengcong/CogvideoX-Interpolation",
+        "bf16",
+        "disabled",
+        false,
+        "sdpa",
+        "main_device"
+      ]
+    }
+  ],
+  "links": [
+    [
+      54,
+      20,
+      0,
+      30,
+      0,
+      "CLIP"
+    ],
+    [
+      71,
+      36,
+      0,
+      37,
+      0,
+      "IMAGE"
+    ],
+    [
+      132,
+      59,
+      1,
+      60,
+      0,
+      "VAE"
+    ],
+    [
+      134,
+      60,
+      0,
+      44,
+      0,
+      "IMAGE"
+    ],
+    [
+      141,
+      59,
+      1,
+      62,
+      0,
+      "VAE"
+    ],
+    [
+      142,
+      37,
+      0,
+      62,
+      1,
+      "IMAGE"
+    ],
+    [
+      144,
+      59,
+      0,
+      63,
+      0,
+      "COGVIDEOMODEL"
+    ],
+    [
+      145,
+      30,
+      0,
+      63,
+      1,
+      "CONDITIONING"
+    ],
+    [
+      146,
+      31,
+      0,
+      63,
+      2,
+      "CONDITIONING"
+    ],
+    [
+      147,
+      62,
+      0,
+      63,
+      4,
+      "LATENT"
+    ],
+    [
+      148,
+      63,
+      0,
+      60,
+      1,
+      "LATENT"
+    ],
+    [
+      149,
+      30,
+      1,
+      31,
+      0,
+      "CLIP"
+    ],
+    [
+      151,
+      64,
+      0,
+      65,
+      0,
+      "IMAGE"
+    ],
+    [
+      152,
+      37,
+      1,
+      65,
+      4,
+      "INT"
+    ],
+    [
+      153,
+      37,
+      2,
+      65,
+      5,
+      "INT"
+    ],
+    [
+      155,
+      65,
+      0,
+      62,
+      2,
+      "IMAGE"
+    ]
+  ],
+  "groups": [],
+  "config": {},
+  "extra": {
+    "ds": {
+      "scale": 0.7627768444387061,
+      "offset": [
+        630.1733472923837,
+        148.14641794691272
+      ]
+    }
+  },
+  "version": 0.4
+}

custom_nodes/ComfyUI-CogVideoXWrapper/example_workflows/cogvideox_1_0_5b_vid2vid_02.json

@@ -0,0 +1,1061 @@
+{
+  "last_node_id": 78,
+  "last_link_id": 218,
+  "nodes": [
+    {
+      "id": 20,
+      "type": "CLIPLoader",
+      "pos": {
+        "0": -29,
+        "1": 407
+      },
+      "size": {
+        "0": 451.30548095703125,
+        "1": 82
+      },
+      "flags": {},
+      "order": 0,
+      "mode": 0,
+      "inputs": [],
+      "outputs": [
+        {
+          "name": "CLIP",
+          "type": "CLIP",
+          "links": [
+            54
+          ],
+          "slot_index": 0,
+          "shape": 3
+        }
+      ],
+      "properties": {
+        "Node name for S&R": "CLIPLoader"
+      },
+      "widgets_values": [
+        "t5\\google_t5-v1_1-xxl_encoderonly-fp8_e4m3fn.safetensors",
+        "sd3"
+      ]
+    },
+    {
+      "id": 41,
+      "type": "ImageResizeKJ",
+      "pos": {
+        "0": 206,
+        "1": -69
+      },
+      "size": {
+        "0": 315,
+        "1": 242
+      },
+      "flags": {},
+      "order": 7,
+      "mode": 0,
+      "inputs": [
+        {
+          "name": "image",
+          "type": "IMAGE",
+          "link": 180
+        },
+        {
+          "name": "get_image_size",
+          "type": "IMAGE",
+          "link": null,
+          "shape": 7
+        },
+        {
+          "name": "width_input",
+          "type": "INT",
+          "link": null,
+          "widget": {
+            "name": "width_input"
+          }
+        },
+        {
+          "name": "height_input",
+          "type": "INT",
+          "link": null,
+          "widget": {
+            "name": "height_input"
+          }
+        }
+      ],
+      "outputs": [
+        {
+          "name": "IMAGE",
+          "type": "IMAGE",
+          "links": [
+            126
+          ],
+          "slot_index": 0,
+          "shape": 3
+        },
+        {
+          "name": "width",
+          "type": "INT",
+          "links": null,
+          "shape": 3
+        },
+        {
+          "name": "height",
+          "type": "INT",
+          "links": null,
+          "shape": 3
+        }
+      ],
+      "properties": {
+        "Node name for S&R": "ImageResizeKJ"
+      },
+      "widgets_values": [
+        720,
+        480,
+        "lanczos",
+        false,
+        2,
+        0,
+        0,
+        "disabled"
+      ]
+    },
+    {
+      "id": 45,
+      "type": "VHS_LoadVideo",
+      "pos": {
+        "0": -93,
+        "1": -153
+      },
+      "size": [
+        247.455078125,
+        365.7275390625
+      ],
+      "flags": {},
+      "order": 4,
+      "mode": 0,
+      "inputs": [
+        {
+          "name": "meta_batch",
+          "type": "VHS_BatchManager",
+          "link": null,
+          "shape": 7
+        },
+        {
+          "name": "vae",
+          "type": "VAE",
+          "link": null,
+          "shape": 7
+        },
+        {
+          "name": "frame_load_cap",
+          "type": "INT",
+          "link": 177,
+          "widget": {
+            "name": "frame_load_cap"
+          }
+        }
+      ],
+      "outputs": [
+        {
+          "name": "IMAGE",
+          "type": "IMAGE",
+          "links": [
+            179
+          ],
+          "slot_index": 0,
+          "shape": 3
+        },
+        {
+          "name": "frame_count",
+          "type": "INT",
+          "links": null,
+          "shape": 3
+        },
+        {
+          "name": "audio",
+          "type": "AUDIO",
+          "links": null,
+          "shape": 3
+        },
+        {
+          "name": "video_info",
+          "type": "VHS_VIDEOINFO",
+          "links": null,
+          "shape": 3
+        }
+      ],
+      "properties": {
+        "Node name for S&R": "VHS_LoadVideo"
+      },
+      "widgets_values": {
+        "video": "jeep.mp4",
+        "force_rate": 0,
+        "force_size": "Disabled",
+        "custom_width": 512,
+        "custom_height": 512,
+        "frame_load_cap": 20,
+        "skip_first_frames": 0,
+        "select_every_nth": 1,
+        "choose video to upload": "image",
+        "videopreview": {
+          "hidden": false,
+          "paused": false,
+          "params": {
+            "frame_load_cap": 20,
+            "skip_first_frames": 0,
+            "force_rate": 0,
+            "filename": "jeep.mp4",
+            "type": "input",
+            "format": "video/mp4",
+            "select_every_nth": 1
+          }
+        }
+      }
+    },
+    {
+      "id": 70,
+      "type": "GetImageSizeAndCount",
+      "pos": {
+        "0": 214,
+        "1": -234
+      },
+      "size": {
+        "0": 202.2143096923828,
+        "1": 99.23601531982422
+      },
+      "flags": {},
+      "order": 6,
+      "mode": 0,
+      "inputs": [
+        {
+          "name": "image",
+          "type": "IMAGE",
+          "link": 179,
+          "slot_index": 0
+        }
+      ],
+      "outputs": [
+        {
+          "name": "image",
+          "type": "IMAGE",
+          "links": [
+            180
+          ],
+          "slot_index": 0,
+          "shape": 3
+        },
+        {
+          "name": "512 width",
+          "type": "INT",
+          "links": [],
+          "slot_index": 1,
+          "shape": 3
+        },
+        {
+          "name": "256 height",
+          "type": "INT",
+          "links": [],
+          "slot_index": 2,
+          "shape": 3
+        },
+        {
+          "name": "33 count",
+          "type": "INT",
+          "links": [],
+          "slot_index": 3,
+          "shape": 3
+        }
+      ],
+      "properties": {
+        "Node name for S&R": "GetImageSizeAndCount"
+      },
+      "widgets_values": []
+    },
+    {
+      "id": 69,
+      "type": "INTConstant",
+      "pos": {
+        "0": -90,
+        "1": -305
+      },
+      "size": {
+        "0": 210,
+        "1": 58
+      },
+      "flags": {},
+      "order": 1,
+      "mode": 0,
+      "inputs": [],
+      "outputs": [
+        {
+          "name": "value",
+          "type": "INT",
+          "links": [
+            177
+          ],
+          "shape": 3
+        }
+      ],
+      "title": "Frames to load",
+      "properties": {
+        "Node name for S&R": "INTConstant"
+      },
+      "widgets_values": [
+        33
+      ],
+      "color": "#1b4669",
+      "bgcolor": "#29699c"
+    },
+    {
+      "id": 58,
+      "type": "ImageConcanate",
+      "pos": {
+        "0": 1594,
+        "1": 230
+      },
+      "size": {
+        "0": 315,
+        "1": 102
+      },
+      "flags": {},
+      "order": 13,
+      "mode": 0,
+      "inputs": [
+        {
+          "name": "image1",
+          "type": "IMAGE",
+          "link": 191
+        },
+        {
+          "name": "image2",
+          "type": "IMAGE",
+          "link": 170
+        }
+      ],
+      "outputs": [
+        {
+          "name": "IMAGE",
+          "type": "IMAGE",
+          "links": [
+            132
+          ],
+          "slot_index": 0,
+          "shape": 3
+        }
+      ],
+      "properties": {
+        "Node name for S&R": "ImageConcanate"
+      },
+      "widgets_values": [
+        "right",
+        false
+      ]
+    },
+    {
+      "id": 55,
+      "type": "GetImageSizeAndCount",
+      "pos": {
+        "0": 1654,
+        "1": 77
+      },
+      "size": {
+        "0": 210,
+        "1": 86
+      },
+      "flags": {},
+      "order": 12,
+      "mode": 0,
+      "inputs": [
+        {
+          "name": "image",
+          "type": "IMAGE",
+          "link": 208,
+          "slot_index": 0
+        }
+      ],
+      "outputs": [
+        {
+          "name": "image",
+          "type": "IMAGE",
+          "links": [
+            170
+          ],
+          "slot_index": 0,
+          "shape": 3
+        },
+        {
+          "name": "720 width",
+          "type": "INT",
+          "links": null,
+          "shape": 3
+        },
+        {
+          "name": "480 height",
+          "type": "INT",
+          "links": null,
+          "shape": 3
+        },
+        {
+          "name": "33 count",
+          "type": "INT",
+          "links": [],
+          "slot_index": 3,
+          "shape": 3
+        }
+      ],
+      "properties": {
+        "Node name for S&R": "GetImageSizeAndCount"
+      },
+      "widgets_values": []
+    },
+    {
+      "id": 77,
+      "type": "CogVideoImageEncode",
+      "pos": {
+        "0": 952,
+        "1": -118
+      },
+      "size": {
+        "0": 315,
+        "1": 122
+      },
+      "flags": {},
+      "order": 9,
+      "mode": 0,
+      "inputs": [
+        {
+          "name": "vae",
+          "type": "VAE",
+          "link": 209
+        },
+        {
+          "name": "start_image",
+          "type": "IMAGE",
+          "link": 210
+        },
+        {
+          "name": "end_image",
+          "type": "IMAGE",
+          "link": null,
+          "shape": 7
+        }
+      ],
+      "outputs": [
+        {
+          "name": "samples",
+          "type": "LATENT",
+          "links": [
+            215
+          ]
+        }
+      ],
+      "properties": {
+        "Node name for S&R": "CogVideoImageEncode"
+      },
+      "widgets_values": [
+        false,
+        0
+      ]
+    },
+    {
+      "id": 76,
+      "type": "CogVideoDecode",
+      "pos": {
+        "0": 1335,
+        "1": -123
+      },
+      "size": {
+        "0": 315,
+        "1": 198
+      },
+      "flags": {},
+      "order": 11,
+      "mode": 0,
+      "inputs": [
+        {
+          "name": "vae",
+          "type": "VAE",
+          "link": 206
+        },
+        {
+          "name": "samples",
+          "type": "LATENT",
+          "link": 216
+        }
+      ],
+      "outputs": [
+        {
+          "name": "images",
+          "type": "IMAGE",
+          "links": [
+            208
+          ]
+        }
+      ],
+      "properties": {
+        "Node name for S&R": "CogVideoDecode"
+      },
+      "widgets_values": [
+        true,
+        240,
+        360,
+        0.2,
+        0.2,
+        true
+      ]
+    },
+    {
+      "id": 30,
+      "type": "CogVideoTextEncode",
+      "pos": {
+        "0": 491,
+        "1": 372
+      },
+      "size": [
+        478.6890949595422,
+        215.66308749666905
+      ],
+      "flags": {},
+      "order": 3,
+      "mode": 0,
+      "inputs": [
+        {
+          "name": "clip",
+          "type": "CLIP",
+          "link": 54
+        }
+      ],
+      "outputs": [
+        {
+          "name": "conditioning",
+          "type": "CONDITIONING",
+          "links": [
+            213
+          ],
+          "slot_index": 0,
+          "shape": 3
+        },
+        {
+          "name": "clip",
+          "type": "CLIP",
+          "links": [
+            217
+          ],
+          "slot_index": 1
+        }
+      ],
+      "properties": {
+        "Node name for S&R": "CogVideoTextEncode"
+      },
+      "widgets_values": [
+        "A high-definition nature video showcasing a brown bear as it gracefully runs down a crystal-clear stream, surrounded by the serene ambiance of a dense, verdant forest. The sunlight filters through the canopy of tall trees, casting dappled light on the forest floor, while the gentle sound of flowing water and rustling leaves creates a peaceful atmosphere. The brown bear's fur glistens in the sunlight, highlighting its striking red and white markings as it navigates the stream with agility and playfulness.",
+        1,
+        false
+      ]
+    },
+    {
+      "id": 31,
+      "type": "CogVideoTextEncode",
+      "pos": {
+        "0": 504,
+        "1": 651
+      },
+      "size": {
+        "0": 463.01251220703125,
+        "1": 144
+      },
+      "flags": {},
+      "order": 5,
+      "mode": 0,
+      "inputs": [
+        {
+          "name": "clip",
+          "type": "CLIP",
+          "link": 217
+        }
+      ],
+      "outputs": [
+        {
+          "name": "conditioning",
+          "type": "CONDITIONING",
+          "links": [
+            214
+          ],
+          "slot_index": 0,
+          "shape": 3
+        },
+        {
+          "name": "clip",
+          "type": "CLIP",
+          "links": null
+        }
+      ],
+      "properties": {
+        "Node name for S&R": "CogVideoTextEncode"
+      },
+      "widgets_values": [
+        "",
+        1,
+        true
+      ]
+    },
+    {
+      "id": 78,
+      "type": "CogVideoSampler",
+      "pos": {
+        "0": 1083,
+        "1": 255
+      },
+      "size": [
+        330,
+        574
+      ],
+      "flags": {},
+      "order": 10,
+      "mode": 0,
+      "inputs": [
+        {
+          "name": "model",
+          "type": "COGVIDEOMODEL",
+          "link": 212
+        },
+        {
+          "name": "positive",
+          "type": "CONDITIONING",
+          "link": 213
+        },
+        {
+          "name": "negative",
+          "type": "CONDITIONING",
+          "link": 214
+        },
+        {
+          "name": "samples",
+          "type": "LATENT",
+          "link": 215,
+          "shape": 7
+        },
+        {
+          "name": "image_cond_latents",
+          "type": "LATENT",
+          "link": null,
+          "shape": 7
+        },
+        {
+          "name": "context_options",
+          "type": "COGCONTEXT",
+          "link": null,
+          "shape": 7
+        },
+        {
+          "name": "controlnet",
+          "type": "COGVIDECONTROLNET",
+          "link": null,
+          "shape": 7
+        },
+        {
+          "name": "tora_trajectory",
+          "type": "TORAFEATURES",
+          "link": null,
+          "shape": 7
+        },
+        {
+          "name": "fastercache",
+          "type": "FASTERCACHEARGS",
+          "link": null,
+          "shape": 7
+        },
+        {
+          "name": "num_frames",
+          "type": "INT",
+          "link": 218,
+          "widget": {
+            "name": "num_frames"
+          }
+        }
+      ],
+      "outputs": [
+        {
+          "name": "samples",
+          "type": "LATENT",
+          "links": [
+            216
+          ]
+        }
+      ],
+      "properties": {
+        "Node name for S&R": "CogVideoSampler"
+      },
+      "widgets_values": [
+        49,
+        25,
+        6,
+        0,
+        "fixed",
+        "CogVideoXDDIM",
+        0.8
+      ]
+    },
+    {
+      "id": 57,
+      "type": "GetImageSizeAndCount",
+      "pos": {
+        "0": 595,
+        "1": -79
+      },
+      "size": {
+        "0": 202.2143096923828,
+        "1": 99.23601531982422
+      },
+      "flags": {},
+      "order": 8,
+      "mode": 0,
+      "inputs": [
+        {
+          "name": "image",
+          "type": "IMAGE",
+          "link": 126,
+          "slot_index": 0
+        }
+      ],
+      "outputs": [
+        {
+          "name": "image",
+          "type": "IMAGE",
+          "links": [
+            191,
+            210
+          ],
+          "slot_index": 0,
+          "shape": 3
+        },
+        {
+          "name": "720 width",
+          "type": "INT",
+          "links": [],
+          "slot_index": 1,
+          "shape": 3
+        },
+        {
+          "name": "480 height",
+          "type": "INT",
+          "links": [],
+          "slot_index": 2,
+          "shape": 3
+        },
+        {
+          "name": "33 count",
+          "type": "INT",
+          "links": [
+            218
+          ],
+          "slot_index": 3,
+          "shape": 3
+        }
+      ],
+      "properties": {
+        "Node name for S&R": "GetImageSizeAndCount"
+      },
+      "widgets_values": []
+    },
+    {
+      "id": 75,
+      "type": "DownloadAndLoadCogVideoModel",
+      "pos": {
+        "0": 606,
+        "1": 85
+      },
+      "size": {
+        "0": 315,
+        "1": 218
+      },
+      "flags": {},
+      "order": 2,
+      "mode": 0,
+      "inputs": [
+        {
+          "name": "block_edit",
+          "type": "TRANSFORMERBLOCKS",
+          "link": null,
+          "shape": 7
+        },
+        {
+          "name": "lora",
+          "type": "COGLORA",
+          "link": null,
+          "shape": 7
+        },
+        {
+          "name": "compile_args",
+          "type": "COMPILEARGS",
+          "link": null,
+          "shape": 7
+        }
+      ],
+      "outputs": [
+        {
+          "name": "model",
+          "type": "COGVIDEOMODEL",
+          "links": [
+            212
+          ]
+        },
+        {
+          "name": "vae",
+          "type": "VAE",
+          "links": [
+            206,
+            209
+          ]
+        }
+      ],
+      "properties": {
+        "Node name for S&R": "DownloadAndLoadCogVideoModel"
+      },
+      "widgets_values": [
+        "THUDM/CogVideoX-5b",
+        "bf16",
+        "disabled",
+        false,
+        "sdpa",
+        "main_device"
+      ]
+    },
+    {
+      "id": 47,
+      "type": "VHS_VideoCombine",
+      "pos": {
+        "0": 1946,
+        "1": -172
+      },
+      "size": [
+        1110,
+        687.3333333333333
+      ],
+      "flags": {},
+      "order": 14,
+      "mode": 0,
+      "inputs": [
+        {
+          "name": "images",
+          "type": "IMAGE",
+          "link": 132
+        },
+        {
+          "name": "audio",
+          "type": "AUDIO",
+          "link": null,
+          "shape": 7
+        },
+        {
+          "name": "meta_batch",
+          "type": "VHS_BatchManager",
+          "link": null,
+          "shape": 7
+        },
+        {
+          "name": "vae",
+          "type": "VAE",
+          "link": null,
+          "shape": 7
+        }
+      ],
+      "outputs": [
+        {
+          "name": "Filenames",
+          "type": "VHS_FILENAMES",
+          "links": null,
+          "shape": 3
+        }
+      ],
+      "properties": {
+        "Node name for S&R": "VHS_VideoCombine"
+      },
+      "widgets_values": {
+        "frame_rate": 8,
+        "loop_count": 0,
+        "filename_prefix": "CogVideoX_vid2vid",
+        "format": "video/h264-mp4",
+        "pix_fmt": "yuv420p",
+        "crf": 19,
+        "save_metadata": true,
+        "pingpong": false,
+        "save_output": true,
+        "videopreview": {
+          "hidden": false,
+          "paused": false,
+          "params": {
+            "filename": "CogVideoX_vid2vid_00003.mp4",
+            "subfolder": "",
+            "type": "temp",
+            "format": "video/h264-mp4",
+            "frame_rate": 8
+          }
+        }
+      }
+    }
+  ],
+  "links": [
+    [
+      54,
+      20,
+      0,
+      30,
+      0,
+      "CLIP"
+    ],
+    [
+      126,
+      41,
+      0,
+      57,
+      0,
+      "IMAGE"
+    ],
+    [
+      132,
+      58,
+      0,
+      47,
+      0,
+      "IMAGE"
+    ],
+    [
+      170,
+      55,
+      0,
+      58,
+      1,
+      "IMAGE"
+    ],
+    [
+      177,
+      69,
+      0,
+      45,
+      2,
+      "INT"
+    ],
+    [
+      179,
+      45,
+      0,
+      70,
+      0,
+      "IMAGE"
+    ],
+    [
+      180,
+      70,
+      0,
+      41,
+      0,
+      "IMAGE"
+    ],
+    [
+      191,
+      57,
+      0,
+      58,
+      0,
+      "IMAGE"
+    ],
+    [
+      206,
+      75,
+      1,
+      76,
+      0,
+      "VAE"
+    ],
+    [
+      208,
+      76,
+      0,
+      55,
+      0,
+      "IMAGE"
+    ],
+    [
+      209,
+      75,
+      1,
+      77,
+      0,
+      "VAE"
+    ],
+    [
+      210,
+      57,
+      0,
+      77,
+      1,
+      "IMAGE"
+    ],
+    [
+      212,
+      75,
+      0,
+      78,
+      0,
+      "COGVIDEOMODEL"
+    ],
+    [
+      213,
+      30,
+      0,
+      78,
+      1,
+      "CONDITIONING"
+    ],
+    [
+      214,
+      31,
+      0,
+      78,
+      2,
+      "CONDITIONING"
+    ],
+    [
+      215,
+      77,
+      0,
+      78,
+      3,
+      "LATENT"
+    ],
+    [
+      216,
+      78,
+      0,
+      76,
+      1,
+      "LATENT"
+    ],
+    [
+      217,
+      30,
+      1,
+      31,
+      0,
+      "CLIP"
+    ],
+    [
+      218,
+      57,
+      3,
+      78,
+      9,
+      "INT"
+    ]
+  ],
+  "groups": [],
+  "config": {},
+  "extra": {
+    "ds": {
+      "scale": 0.8390545288825798,
+      "offset": [
+        -318.82552550589344,
+        331.70430573737934
+      ]
+    }
+  },
+  "version": 0.4
+}

custom_nodes/ComfyUI-CogVideoXWrapper/example_workflows/cogvideox_1_5_5b_I2V_01.json

@@ -0,0 +1,688 @@
+{
+  "last_node_id": 64,
+  "last_link_id": 149,
+  "nodes": [
+    {
+      "id": 63,
+      "type": "CogVideoSampler",
+      "pos": {
+        "0": 1142,
+        "1": 74
+      },
+      "size": {
+        "0": 330,
+        "1": 574
+      },
+      "flags": {},
+      "order": 7,
+      "mode": 0,
+      "inputs": [
+        {
+          "name": "model",
+          "type": "COGVIDEOMODEL",
+          "link": 144
+        },
+        {
+          "name": "positive",
+          "type": "CONDITIONING",
+          "link": 145
+        },
+        {
+          "name": "negative",
+          "type": "CONDITIONING",
+          "link": 146
+        },
+        {
+          "name": "samples",
+          "type": "LATENT",
+          "link": null,
+          "shape": 7
+        },
+        {
+          "name": "image_cond_latents",
+          "type": "LATENT",
+          "link": 147,
+          "shape": 7
+        },
+        {
+          "name": "context_options",
+          "type": "COGCONTEXT",
+          "link": null,
+          "shape": 7
+        },
+        {
+          "name": "controlnet",
+          "type": "COGVIDECONTROLNET",
+          "link": null,
+          "shape": 7
+        },
+        {
+          "name": "tora_trajectory",
+          "type": "TORAFEATURES",
+          "link": null,
+          "shape": 7
+        },
+        {
+          "name": "fastercache",
+          "type": "FASTERCACHEARGS",
+          "link": null,
+          "shape": 7
+        }
+      ],
+      "outputs": [
+        {
+          "name": "samples",
+          "type": "LATENT",
+          "links": [
+            148
+          ]
+        }
+      ],
+      "properties": {
+        "Node name for S&R": "CogVideoSampler"
+      },
+      "widgets_values": [
+        49,
+        25,
+        6,
+        0,
+        "fixed",
+        "CogVideoXDDIM",
+        1
+      ]
+    },
+    {
+      "id": 62,
+      "type": "CogVideoImageEncode",
+      "pos": {
+        "0": 1149,
+        "1": 711
+      },
+      "size": {
+        "0": 315,
+        "1": 122
+      },
+      "flags": {},
+      "order": 5,
+      "mode": 0,
+      "inputs": [
+        {
+          "name": "vae",
+          "type": "VAE",
+          "link": 141
+        },
+        {
+          "name": "start_image",
+          "type": "IMAGE",
+          "link": 142
+        },
+        {
+          "name": "end_image",
+          "type": "IMAGE",
+          "link": null,
+          "shape": 7
+        }
+      ],
+      "outputs": [
+        {
+          "name": "samples",
+          "type": "LATENT",
+          "links": [
+            147
+          ]
+        }
+      ],
+      "properties": {
+        "Node name for S&R": "CogVideoImageEncode"
+      },
+      "widgets_values": [
+        false,
+        0
+      ]
+    },
+    {
+      "id": 30,
+      "type": "CogVideoTextEncode",
+      "pos": {
+        "0": 493,
+        "1": 303
+      },
+      "size": {
+        "0": 471.90142822265625,
+        "1": 168.08047485351562
+      },
+      "flags": {},
+      "order": 4,
+      "mode": 0,
+      "inputs": [
+        {
+          "name": "clip",
+          "type": "CLIP",
+          "link": 54
+        }
+      ],
+      "outputs": [
+        {
+          "name": "conditioning",
+          "type": "CONDITIONING",
+          "links": [
+            145
+          ],
+          "slot_index": 0,
+          "shape": 3
+        },
+        {
+          "name": "clip",
+          "type": "CLIP",
+          "links": [
+            149
+          ],
+          "slot_index": 1
+        }
+      ],
+      "properties": {
+        "Node name for S&R": "CogVideoTextEncode"
+      },
+      "widgets_values": [
+        "a majestic stag is grazing in an enhanced forest, basking in the setting sun filtered by the trees",
+        1,
+        false
+      ]
+    },
+    {
+      "id": 36,
+      "type": "LoadImage",
+      "pos": {
+        "0": 335,
+        "1": 731
+      },
+      "size": {
+        "0": 402.06353759765625,
+        "1": 396.6225891113281
+      },
+      "flags": {},
+      "order": 0,
+      "mode": 0,
+      "inputs": [],
+      "outputs": [
+        {
+          "name": "IMAGE",
+          "type": "IMAGE",
+          "links": [
+            71
+          ],
+          "slot_index": 0,
+          "shape": 3
+        },
+        {
+          "name": "MASK",
+          "type": "MASK",
+          "links": null,
+          "shape": 3
+        }
+      ],
+      "properties": {
+        "Node name for S&R": "LoadImage"
+      },
+      "widgets_values": [
+        "sd3stag.png",
+        "image"
+      ]
+    },
+    {
+      "id": 20,
+      "type": "CLIPLoader",
+      "pos": {
+        "0": -2,
+        "1": 304
+      },
+      "size": {
+        "0": 451.30548095703125,
+        "1": 82
+      },
+      "flags": {},
+      "order": 1,
+      "mode": 0,
+      "inputs": [],
+      "outputs": [
+        {
+          "name": "CLIP",
+          "type": "CLIP",
+          "links": [
+            54
+          ],
+          "slot_index": 0,
+          "shape": 3
+        }
+      ],
+      "properties": {
+        "Node name for S&R": "CLIPLoader"
+      },
+      "widgets_values": [
+        "t5\\google_t5-v1_1-xxl_encoderonly-fp8_e4m3fn.safetensors",
+        "sd3"
+      ]
+    },
+    {
+      "id": 60,
+      "type": "CogVideoDecode",
+      "pos": {
+        "0": 1523,
+        "1": -6
+      },
+      "size": {
+        "0": 315,
+        "1": 198
+      },
+      "flags": {},
+      "order": 8,
+      "mode": 0,
+      "inputs": [
+        {
+          "name": "vae",
+          "type": "VAE",
+          "link": 132
+        },
+        {
+          "name": "samples",
+          "type": "LATENT",
+          "link": 148
+        }
+      ],
+      "outputs": [
+        {
+          "name": "images",
+          "type": "IMAGE",
+          "links": [
+            134
+          ]
+        }
+      ],
+      "properties": {
+        "Node name for S&R": "CogVideoDecode"
+      },
+      "widgets_values": [
+        true,
+        240,
+        360,
+        0.2,
+        0.2,
+        true
+      ]
+    },
+    {
+      "id": 37,
+      "type": "ImageResizeKJ",
+      "pos": {
+        "0": 784,
+        "1": 731
+      },
+      "size": {
+        "0": 315,
+        "1": 266
+      },
+      "flags": {},
+      "order": 3,
+      "mode": 0,
+      "inputs": [
+        {
+          "name": "image",
+          "type": "IMAGE",
+          "link": 71
+        },
+        {
+          "name": "get_image_size",
+          "type": "IMAGE",
+          "link": null,
+          "shape": 7
+        },
+        {
+          "name": "width_input",
+          "type": "INT",
+          "link": null,
+          "widget": {
+            "name": "width_input"
+          }
+        },
+        {
+          "name": "height_input",
+          "type": "INT",
+          "link": null,
+          "widget": {
+            "name": "height_input"
+          }
+        }
+      ],
+      "outputs": [
+        {
+          "name": "IMAGE",
+          "type": "IMAGE",
+          "links": [
+            142
+          ],
+          "slot_index": 0,
+          "shape": 3
+        },
+        {
+          "name": "width",
+          "type": "INT",
+          "links": null,
+          "shape": 3
+        },
+        {
+          "name": "height",
+          "type": "INT",
+          "links": null,
+          "shape": 3
+        }
+      ],
+      "properties": {
+        "Node name for S&R": "ImageResizeKJ"
+      },
+      "widgets_values": [
+        1360,
+        768,
+        "lanczos",
+        false,
+        16,
+        0,
+        0,
+        "disabled"
+      ]
+    },
+    {
+      "id": 31,
+      "type": "CogVideoTextEncode",
+      "pos": {
+        "0": 497,
+        "1": 520
+      },
+      "size": {
+        "0": 463.01251220703125,
+        "1": 144
+      },
+      "flags": {},
+      "order": 6,
+      "mode": 0,
+      "inputs": [
+        {
+          "name": "clip",
+          "type": "CLIP",
+          "link": 149
+        }
+      ],
+      "outputs": [
+        {
+          "name": "conditioning",
+          "type": "CONDITIONING",
+          "links": [
+            146
+          ],
+          "slot_index": 0,
+          "shape": 3
+        },
+        {
+          "name": "clip",
+          "type": "CLIP",
+          "links": null
+        }
+      ],
+      "properties": {
+        "Node name for S&R": "CogVideoTextEncode"
+      },
+      "widgets_values": [
+        "",
+        1,
+        true
+      ]
+    },
+    {
+      "id": 59,
+      "type": "DownloadAndLoadCogVideoModel",
+      "pos": {
+        "0": 622,
+        "1": -25
+      },
+      "size": {
+        "0": 315,
+        "1": 218
+      },
+      "flags": {},
+      "order": 2,
+      "mode": 0,
+      "inputs": [
+        {
+          "name": "block_edit",
+          "type": "TRANSFORMERBLOCKS",
+          "link": null,
+          "shape": 7
+        },
+        {
+          "name": "lora",
+          "type": "COGLORA",
+          "link": null,
+          "shape": 7
+        },
+        {
+          "name": "compile_args",
+          "type": "COMPILEARGS",
+          "link": null,
+          "shape": 7
+        }
+      ],
+      "outputs": [
+        {
+          "name": "model",
+          "type": "COGVIDEOMODEL",
+          "links": [
+            144
+          ]
+        },
+        {
+          "name": "vae",
+          "type": "VAE",
+          "links": [
+            132,
+            141
+          ],
+          "slot_index": 1
+        }
+      ],
+      "properties": {
+        "Node name for S&R": "DownloadAndLoadCogVideoModel"
+      },
+      "widgets_values": [
+        "kijai/CogVideoX-5b-1.5-I2V",
+        "bf16",
+        "disabled",
+        false,
+        "sdpa",
+        "main_device"
+      ]
+    },
+    {
+      "id": 44,
+      "type": "VHS_VideoCombine",
+      "pos": {
+        "0": 1884,
+        "1": -6
+      },
+      "size": [
+        605.3909912109375,
+        310
+      ],
+      "flags": {},
+      "order": 9,
+      "mode": 0,
+      "inputs": [
+        {
+          "name": "images",
+          "type": "IMAGE",
+          "link": 134
+        },
+        {
+          "name": "audio",
+          "type": "AUDIO",
+          "link": null,
+          "shape": 7
+        },
+        {
+          "name": "meta_batch",
+          "type": "VHS_BatchManager",
+          "link": null,
+          "shape": 7
+        },
+        {
+          "name": "vae",
+          "type": "VAE",
+          "link": null,
+          "shape": 7
+        }
+      ],
+      "outputs": [
+        {
+          "name": "Filenames",
+          "type": "VHS_FILENAMES",
+          "links": null,
+          "shape": 3
+        }
+      ],
+      "properties": {
+        "Node name for S&R": "VHS_VideoCombine"
+      },
+      "widgets_values": {
+        "frame_rate": 16,
+        "loop_count": 0,
+        "filename_prefix": "CogVideoX_1_5_I2V",
+        "format": "video/h264-mp4",
+        "pix_fmt": "yuv420p",
+        "crf": 19,
+        "save_metadata": true,
+        "pingpong": false,
+        "save_output": true,
+        "videopreview": {
+          "hidden": false,
+          "paused": false,
+          "params": {
+            "filename": "CogVideoX-I2V_00004.mp4",
+            "subfolder": "",
+            "type": "temp",
+            "format": "video/h264-mp4",
+            "frame_rate": 8
+          },
+          "muted": false
+        }
+      }
+    }
+  ],
+  "links": [
+    [
+      54,
+      20,
+      0,
+      30,
+      0,
+      "CLIP"
+    ],
+    [
+      71,
+      36,
+      0,
+      37,
+      0,
+      "IMAGE"
+    ],
+    [
+      132,
+      59,
+      1,
+      60,
+      0,
+      "VAE"
+    ],
+    [
+      134,
+      60,
+      0,
+      44,
+      0,
+      "IMAGE"
+    ],
+    [
+      141,
+      59,
+      1,
+      62,
+      0,
+      "VAE"
+    ],
+    [
+      142,
+      37,
+      0,
+      62,
+      1,
+      "IMAGE"
+    ],
+    [
+      144,
+      59,
+      0,
+      63,
+      0,
+      "COGVIDEOMODEL"
+    ],
+    [
+      145,
+      30,
+      0,
+      63,
+      1,
+      "CONDITIONING"
+    ],
+    [
+      146,
+      31,
+      0,
+      63,
+      2,
+      "CONDITIONING"
+    ],
+    [
+      147,
+      62,
+      0,
+      63,
+      4,
+      "LATENT"
+    ],
+    [
+      148,
+      63,
+      0,
+      60,
+      1,
+      "LATENT"
+    ],
+    [
+      149,
+      30,
+      1,
+      31,
+      0,
+      "CLIP"
+    ]
+  ],
+  "groups": [],
+  "config": {},
+  "extra": {
+    "ds": {
+      "scale": 0.7627768444387097,
+      "offset": [
+        716.7143770104391,
+        291.75859557289965
+      ]
+    }
+  },
+  "version": 0.4
+}