Hugging Face's logo

Erland
/
tiny-wan2.1-vsa-t2v-14b-720p-debug

Text-to-Video
Diffusers
Safetensors
WanPipeline
wan
tiny-random
debug
Model card Files
xet
 Community
Erland commited on
Commit
5cc72d3
·
verified ·
1 Parent(s): 93c4c26

Add tiny Wan debug pipeline

Browse files
Files changed (2) hide show
  1. README.md +1 -1
  2. transformer/diffusion_pytorch_model.safetensors +2 -2
README.md CHANGED
@@ -12,7 +12,7 @@ tags:
12
  # Tiny Wan2.1 VSA T2V 14B 720P Debug Pipeline
13
 
14
  This is a randomly initialized, tiny `WanPipeline` fixture for `FastVideo/Wan2.1-VSA-T2V-14B-720P-Diffusers`.
15
- FastVideo Wan2.1 VSA 14B 720P text-to-video layout represented as a tiny Diffusers `WanPipeline` artifact for FastVideo `VideoGenerator` and `VIDEO_SPARSE_ATTN` load-path debugging.
16
 
17
  It is intended for fast load-path and inference-control debugging only. It is not trained and should
18
  not be used for generation quality evaluation.
 
12
  # Tiny Wan2.1 VSA T2V 14B 720P Debug Pipeline
13
 
14
  This is a randomly initialized, tiny `WanPipeline` fixture for `FastVideo/Wan2.1-VSA-T2V-14B-720P-Diffusers`.
15
+ FastVideo Wan2.1 VSA 14B 720P text-to-video layout represented as a tiny Diffusers `WanPipeline` artifact for FastVideo `VideoGenerator` and `VIDEO_SPARSE_ATTN` load-path debugging. The saved transformer weights include FastVideo VSA `to_gate_compress` tensors, which are not emitted by Diffusers.
16
 
17
  It is intended for fast load-path and inference-control debugging only. It is not trained and should
18
  not be used for generation quality evaluation.
transformer/diffusion_pytorch_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:973d01c805fef2e05193a331bd2ac9c25ebbf51e593cbbe966cd311fb7da0744
3
- size 365480
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f51d660c2ec748360380426c9b081d2970bb771756dd0079bac057ae25952502
3
+ size 382312