Hugging Face's logo

nunchaku-tech
/
nunchaku-qwen-image-edit-2509

Text-to-Image
Diffusers
English
image-editing
SVDQuant
Qwen-Image-Edit-2509
Diffusion
Quantization
ICLR2025
Model card Files
xet
Community
20
Lmxyy commited on
Commit
e93a5fb
·
verified ·
1 Parent(s): a1be2a1

Upload ./README.md with huggingface_hub

Browse files
Files changed (1) hide show
  1. README.md +14 -18
README.md CHANGED
@@ -37,7 +37,6 @@ This repository contains Nunchaku-quantized versions of [Qwen-Image-Edit-2509](h
37
  - [2025-09-25] 🔥 Release **4-bit [4/8-step lightning Qwen-Image-Edit](https://huggingface.co/lightx2v/Qwen-Image-Lightning)**!
38
  - [2025-09-24] 🚀 Release 4-bit SVDQuant quantized Qwen-Image-Edit-2509 model with rank 32 and 128!
39
 
40
-
41
  ## Model Details
42
 
43
  ### Model Description
@@ -49,7 +48,7 @@ This repository contains Nunchaku-quantized versions of [Qwen-Image-Edit-2509](h
49
 
50
  ### Model Files
51
 
52
- **Data Type**: `INT4` for non-Blackwell GPUs (pre-50-series), `NVFP4` for Blackwell GPUs (50-series).
53
  **Rank**: `r32` for faster inference, `r128` for better quality but slower inference.
54
 
55
 
@@ -61,13 +60,12 @@ This repository contains Nunchaku-quantized versions of [Qwen-Image-Edit-2509](h
61
  Standard inference speed models for general use
62
 
63
 
64
-
65
  | Data Type | Rank | Model Name | Comment |
66
- |-----------|------|------------|---------|
67
  | INT4 | r32 | [`svdq-int4_r32-qwen-image-edit-2509.safetensors`](./svdq-int4_r32-qwen-image-edit-2509.safetensors) | |
68
- | INT4 | r128 | [`svdq-int4_r128-qwen-image-edit-2509.safetensors`](./svdq-int4_r128-qwen-image-edit-2509.safetensors) | Better quality, slower inference |
69
  | NVFP4 | r32 | [`svdq-fp4_r32-qwen-image-edit-2509.safetensors`](./svdq-fp4_r32-qwen-image-edit-2509.safetensors) | |
70
- | NVFP4 | r128 | [`svdq-fp4_r128-qwen-image-edit-2509.safetensors`](./svdq-fp4_r128-qwen-image-edit-2509.safetensors) | Better quality, slower inference |
71
 
72
 
73
 
@@ -78,17 +76,16 @@ Standard inference speed models for general use
78
  4-step distilled models fused with [Qwen-Image-Lightning-4steps-V2.0 LoRA](https://huggingface.co/lightx2v/Qwen-Image-Lightning/blob/main/Qwen-Image-Lightning-4steps-V2.0-bf16.safetensors) or [Qwen-Image-Edit-2509-Lightning-4steps-V1.0 LoRA](https://huggingface.co/lightx2v/Qwen-Image-Lightning/blob/main/Qwen-Image-Edit-2509/Qwen-Image-Edit-2509-Lightning-4steps-V1.0-bf16.safetensors) using LoRA strength = 1.0
79
 
80
 
81
-
82
  | Data Type | Rank | Model Name | Comment |
83
- |-----------|------|------------|---------|
84
  | INT4 | r32 | [`svdq-int4_r32-qwen-image-edit-2509-lightning-4steps-251115.safetensors`](./lightning-251115/svdq-int4_r32-qwen-image-edit-2509-lightning-4steps-251115.safetensors) | 🔥 New: Fused with [Qwen-Image-Edit-2509-Lightning-4steps-V1.0 LoRA](https://huggingface.co/lightx2v/Qwen-Image-Lightning/blob/main/Qwen-Image-Edit-2509/Qwen-Image-Edit-2509-Lightning-4steps-V1.0-bf16.safetensors) |
85
- | INT4 | r128 | [`svdq-int4_r128-qwen-image-edit-2509-lightning-4steps-251115.safetensors`](./lightning-251115/svdq-int4_r128-qwen-image-edit-2509-lightning-4steps-251115.safetensors) | 🔥 New: Fused with [Qwen-Image-Edit-2509-Lightning-4steps-V1.0 LoRA](https://huggingface.co/lightx2v/Qwen-Image-Lightning/blob/main/Qwen-Image-Edit-2509/Qwen-Image-Edit-2509-Lightning-4steps-V1.0-bf16.safetensors) |
86
  | NVFP4 | r32 | [`svdq-fp4_r32-qwen-image-edit-2509-lightning-4steps-251115.safetensors`](./lightning-251115/svdq-fp4_r32-qwen-image-edit-2509-lightning-4steps-251115.safetensors) | 🔥 New: Fused with [Qwen-Image-Edit-2509-Lightning-4steps-V1.0 LoRA](https://huggingface.co/lightx2v/Qwen-Image-Lightning/blob/main/Qwen-Image-Edit-2509/Qwen-Image-Edit-2509-Lightning-4steps-V1.0-bf16.safetensors) |
87
- | NVFP4 | r128 | [`svdq-fp4_r128-qwen-image-edit-2509-lightning-4steps-251115.safetensors`](./lightning-251115/svdq-fp4_r128-qwen-image-edit-2509-lightning-4steps-251115.safetensors) | 🔥 New: Fused with [Qwen-Image-Edit-2509-Lightning-4steps-V1.0 LoRA](https://huggingface.co/lightx2v/Qwen-Image-Lightning/blob/main/Qwen-Image-Edit-2509/Qwen-Image-Edit-2509-Lightning-4steps-V1.0-bf16.safetensors) |
88
  | INT4 | r32 | [`svdq-int4_r32-qwen-image-edit-2509-lightningv2.0-4steps.safetensors`](./svdq-int4_r32-qwen-image-edit-2509-lightningv2.0-4steps.safetensors) | Fused with [Qwen-Image-Lightning-4steps-V2.0 LoRA](https://huggingface.co/lightx2v/Qwen-Image-Lightning/blob/main/Qwen-Image-Lightning-4steps-V2.0-bf16.safetensors) |
89
- | INT4 | r128 | [`svdq-int4_r128-qwen-image-edit-2509-lightning`](./svdq-int4_r128-qwen-image-edit-2509-lightning) | Fused with [Qwen-Image-Lightning-4steps-V2.0 LoRA](https://huggingface.co/lightx2v/Qwen-Image-Lightning/blob/main/Qwen-Image-Lightning-4steps-V2.0-bf16.safetensors) |
90
  | NVFP4 | r32 | [`svdq-fp4_r32-qwen-image-edit-2509-lightningv2.0-4steps.safetensors`](./svdq-fp4_r32-qwen-image-edit-2509-lightningv2.0-4steps.safetensors) | Fused with [Qwen-Image-Lightning-4steps-V2.0 LoRA](https://huggingface.co/lightx2v/Qwen-Image-Lightning/blob/main/Qwen-Image-Lightning-4steps-V2.0-bf16.safetensors) |
91
- | NVFP4 | r128 | [`svdq-fp4_r128-qwen-image-edit-2509-lightningv2.0-4steps.safetensors`](./svdq-fp4_r128-qwen-image-edit-2509-lightningv2.0-4steps.safetensors) | Fused with [Qwen-Image-Lightning-4steps-V2.0 LoRA](https://huggingface.co/lightx2v/Qwen-Image-Lightning/blob/main/Qwen-Image-Lightning-4steps-V2.0-bf16.safetensors) |
92
 
93
 
94
 
@@ -99,17 +96,16 @@ Standard inference speed models for general use
99
  8-step distilled models fused with [Qwen-Image-Lightning-8steps-V2.0 LoRA](https://huggingface.co/lightx2v/Qwen-Image-Lightning/blob/main/Qwen-Image-Lightning-8steps-V2.0-bf16.safetensors) or [Qwen-Image-Edit-2509-Lightning-8steps-V1.0 LoRA](https://huggingface.co/lightx2v/Qwen-Image-Lightning/blob/main/Qwen-Image-Edit-2509/Qwen-Image-Edit-2509-Lightning-8steps-V1.0-bf16.safetensors) using LoRA strength = 1.0
100
 
101
 
102
-
103
  | Data Type | Rank | Model Name | Comment |
104
- |-----------|------|------------|---------|
105
  | INT4 | r32 | [`svdq-int4_r32-qwen-image-edit-2509-lightning-8steps-251115.safetensors`](./lightning-251115/svdq-int4_r32-qwen-image-edit-2509-lightning-8steps-251115.safetensors) | 🔥 New: Fused with [Qwen-Image-Edit-2509-Lightning-8steps-V1.0 LoRA](https://huggingface.co/lightx2v/Qwen-Image-Lightning/blob/main/Qwen-Image-Edit-2509/Qwen-Image-Edit-2509-Lightning-8steps-V1.0-bf16.safetensors) |
106
- | INT4 | r128 | [`svdq-int4_r128-qwen-image-edit-2509-lightning-8steps-251115.safetensors`](./lightning-251115/svdq-int4_r128-qwen-image-edit-2509-lightning-8steps-251115.safetensors) | 🔥 New: Fused with [Qwen-Image-Edit-2509-Lightning-8steps-V1.0 LoRA](https://huggingface.co/lightx2v/Qwen-Image-Lightning/blob/main/Qwen-Image-Edit-2509/Qwen-Image-Edit-2509-Lightning-8steps-V1.0-bf16.safetensors) |
107
  | NVFP4 | r32 | [`svdq-fp4_r32-qwen-image-edit-2509-lightning-8steps-251115.safetensors`](./lightning-251115/svdq-fp4_r32-qwen-image-edit-2509-lightning-8steps-251115.safetensors) | 🔥 New: Fused with [Qwen-Image-Edit-2509-Lightning-8steps-V1.0 LoRA](https://huggingface.co/lightx2v/Qwen-Image-Lightning/blob/main/Qwen-Image-Edit-2509/Qwen-Image-Edit-2509-Lightning-8steps-V1.0-bf16.safetensors) |
108
- | NVFP4 | r128 | [`svdq-fp4_r128-qwen-image-edit-2509-lightning-8steps-251115.safetensors`](./lightning-251115/svdq-fp4_r128-qwen-image-edit-2509-lightning-8steps-251115.safetensors) | 🔥 New: Fused with [Qwen-Image-Edit-2509-Lightning-8steps-V1.0 LoRA](https://huggingface.co/lightx2v/Qwen-Image-Lightning/blob/main/Qwen-Image-Edit-2509/Qwen-Image-Edit-2509-Lightning-8steps-V1.0-bf16.safetensors) |
109
  | INT4 | r32 | [`svdq-int4_r32-qwen-image-edit-2509-lightningv2.0-8steps.safetensors`](./svdq-int4_r32-qwen-image-edit-2509-lightningv2.0-8steps.safetensors) | Fused with [Qwen-Image-Lightning-8steps-V2.0 LoRA](https://huggingface.co/lightx2v/Qwen-Image-Lightning/blob/main/Qwen-Image-Lightning-8steps-V2.0-bf16.safetensors) |
110
- | INT4 | r128 | [`svdq-int4_r128-qwen-image-edit-2509-lightningv2.0-8steps.safetensors`](./svdq-int4_r128-qwen-image-edit-2509-lightningv2.0-8steps.safetensors) | Fused with [Qwen-Image-Lightning-8steps-V2.0 LoRA](https://huggingface.co/lightx2v/Qwen-Image-Lightning/blob/main/Qwen-Image-Lightning-8steps-V2.0-bf16.safetensors) |
111
  | NVFP4 | r32 | [`svdq-fp4_r32-qwen-image-edit-2509-lightningv2.0-8steps.safetensors`](./svdq-fp4_r32-qwen-image-edit-2509-lightningv2.0-8steps.safetensors) | Fused with [Qwen-Image-Lightning-8steps-V2.0 LoRA](https://huggingface.co/lightx2v/Qwen-Image-Lightning/blob/main/Qwen-Image-Lightning-8steps-V2.0-bf16.safetensors) |
112
- | NVFP4 | r128 | [`svdq-fp4_r128-qwen-image-edit-2509-lightningv2.0-8steps.safetensors`](./svdq-fp4_r128-qwen-image-edit-2509-lightningv2.0-8steps.safetensors) | Fused with [Qwen-Image-Lightning-8steps-V2.0 LoRA](https://huggingface.co/lightx2v/Qwen-Image-Lightning/blob/main/Qwen-Image-Lightning-8steps-V2.0-bf16.safetensors) |
113
 
114
 
115
 
 
37
  - [2025-09-25] 🔥 Release **4-bit [4/8-step lightning Qwen-Image-Edit](https://huggingface.co/lightx2v/Qwen-Image-Lightning)**!
38
  - [2025-09-24] 🚀 Release 4-bit SVDQuant quantized Qwen-Image-Edit-2509 model with rank 32 and 128!
39
 
 
40
  ## Model Details
41
 
42
  ### Model Description
 
48
 
49
  ### Model Files
50
 
51
+ **Data Type**: `INT4` for non-Blackwell GPUs (pre-50-series), `NVFP4` for Blackwell GPUs (50-series).
52
  **Rank**: `r32` for faster inference, `r128` for better quality but slower inference.
53
 
54
 
 
60
  Standard inference speed models for general use
61
 
62
 
 
63
  | Data Type | Rank | Model Name | Comment |
64
+ |-----------|------|----------|---------|
65
  | INT4 | r32 | [`svdq-int4_r32-qwen-image-edit-2509.safetensors`](./svdq-int4_r32-qwen-image-edit-2509.safetensors) | |
66
+ | | r128 | [`svdq-int4_r128-qwen-image-edit-2509.safetensors`](./svdq-int4_r128-qwen-image-edit-2509.safetensors) | |
67
  | NVFP4 | r32 | [`svdq-fp4_r32-qwen-image-edit-2509.safetensors`](./svdq-fp4_r32-qwen-image-edit-2509.safetensors) | |
68
+ | | r128 | [`svdq-fp4_r128-qwen-image-edit-2509.safetensors`](./svdq-fp4_r128-qwen-image-edit-2509.safetensors) | |
69
 
70
 
71
 
 
76
  4-step distilled models fused with [Qwen-Image-Lightning-4steps-V2.0 LoRA](https://huggingface.co/lightx2v/Qwen-Image-Lightning/blob/main/Qwen-Image-Lightning-4steps-V2.0-bf16.safetensors) or [Qwen-Image-Edit-2509-Lightning-4steps-V1.0 LoRA](https://huggingface.co/lightx2v/Qwen-Image-Lightning/blob/main/Qwen-Image-Edit-2509/Qwen-Image-Edit-2509-Lightning-4steps-V1.0-bf16.safetensors) using LoRA strength = 1.0
77
 
78
 
 
79
  | Data Type | Rank | Model Name | Comment |
80
+ |-----------|------|----------|---------|
81
  | INT4 | r32 | [`svdq-int4_r32-qwen-image-edit-2509-lightning-4steps-251115.safetensors`](./lightning-251115/svdq-int4_r32-qwen-image-edit-2509-lightning-4steps-251115.safetensors) | 🔥 New: Fused with [Qwen-Image-Edit-2509-Lightning-4steps-V1.0 LoRA](https://huggingface.co/lightx2v/Qwen-Image-Lightning/blob/main/Qwen-Image-Edit-2509/Qwen-Image-Edit-2509-Lightning-4steps-V1.0-bf16.safetensors) |
82
+ | | r128 | [`svdq-int4_r128-qwen-image-edit-2509-lightning-4steps-251115.safetensors`](./lightning-251115/svdq-int4_r128-qwen-image-edit-2509-lightning-4steps-251115.safetensors) | 🔥 New: Fused with [Qwen-Image-Edit-2509-Lightning-4steps-V1.0 LoRA](https://huggingface.co/lightx2v/Qwen-Image-Lightning/blob/main/Qwen-Image-Edit-2509/Qwen-Image-Edit-2509-Lightning-4steps-V1.0-bf16.safetensors) |
83
  | NVFP4 | r32 | [`svdq-fp4_r32-qwen-image-edit-2509-lightning-4steps-251115.safetensors`](./lightning-251115/svdq-fp4_r32-qwen-image-edit-2509-lightning-4steps-251115.safetensors) | 🔥 New: Fused with [Qwen-Image-Edit-2509-Lightning-4steps-V1.0 LoRA](https://huggingface.co/lightx2v/Qwen-Image-Lightning/blob/main/Qwen-Image-Edit-2509/Qwen-Image-Edit-2509-Lightning-4steps-V1.0-bf16.safetensors) |
84
+ | | r128 | [`svdq-fp4_r128-qwen-image-edit-2509-lightning-4steps-251115.safetensors`](./lightning-251115/svdq-fp4_r128-qwen-image-edit-2509-lightning-4steps-251115.safetensors) | 🔥 New: Fused with [Qwen-Image-Edit-2509-Lightning-4steps-V1.0 LoRA](https://huggingface.co/lightx2v/Qwen-Image-Lightning/blob/main/Qwen-Image-Edit-2509/Qwen-Image-Edit-2509-Lightning-4steps-V1.0-bf16.safetensors) |
85
  | INT4 | r32 | [`svdq-int4_r32-qwen-image-edit-2509-lightningv2.0-4steps.safetensors`](./svdq-int4_r32-qwen-image-edit-2509-lightningv2.0-4steps.safetensors) | Fused with [Qwen-Image-Lightning-4steps-V2.0 LoRA](https://huggingface.co/lightx2v/Qwen-Image-Lightning/blob/main/Qwen-Image-Lightning-4steps-V2.0-bf16.safetensors) |
86
+ | | r128 | [`svdq-int4_r128-qwen-image-edit-2509-lightning`](./svdq-int4_r128-qwen-image-edit-2509-lightning) | Fused with [Qwen-Image-Lightning-4steps-V2.0 LoRA](https://huggingface.co/lightx2v/Qwen-Image-Lightning/blob/main/Qwen-Image-Lightning-4steps-V2.0-bf16.safetensors) |
87
  | NVFP4 | r32 | [`svdq-fp4_r32-qwen-image-edit-2509-lightningv2.0-4steps.safetensors`](./svdq-fp4_r32-qwen-image-edit-2509-lightningv2.0-4steps.safetensors) | Fused with [Qwen-Image-Lightning-4steps-V2.0 LoRA](https://huggingface.co/lightx2v/Qwen-Image-Lightning/blob/main/Qwen-Image-Lightning-4steps-V2.0-bf16.safetensors) |
88
+ | | r128 | [`svdq-fp4_r128-qwen-image-edit-2509-lightningv2.0-4steps.safetensors`](./svdq-fp4_r128-qwen-image-edit-2509-lightningv2.0-4steps.safetensors) | Fused with [Qwen-Image-Lightning-4steps-V2.0 LoRA](https://huggingface.co/lightx2v/Qwen-Image-Lightning/blob/main/Qwen-Image-Lightning-4steps-V2.0-bf16.safetensors) |
89
 
90
 
91
 
 
96
  8-step distilled models fused with [Qwen-Image-Lightning-8steps-V2.0 LoRA](https://huggingface.co/lightx2v/Qwen-Image-Lightning/blob/main/Qwen-Image-Lightning-8steps-V2.0-bf16.safetensors) or [Qwen-Image-Edit-2509-Lightning-8steps-V1.0 LoRA](https://huggingface.co/lightx2v/Qwen-Image-Lightning/blob/main/Qwen-Image-Edit-2509/Qwen-Image-Edit-2509-Lightning-8steps-V1.0-bf16.safetensors) using LoRA strength = 1.0
97
 
98
 
 
99
  | Data Type | Rank | Model Name | Comment |
100
+ |-----------|------|----------|---------|
101
  | INT4 | r32 | [`svdq-int4_r32-qwen-image-edit-2509-lightning-8steps-251115.safetensors`](./lightning-251115/svdq-int4_r32-qwen-image-edit-2509-lightning-8steps-251115.safetensors) | 🔥 New: Fused with [Qwen-Image-Edit-2509-Lightning-8steps-V1.0 LoRA](https://huggingface.co/lightx2v/Qwen-Image-Lightning/blob/main/Qwen-Image-Edit-2509/Qwen-Image-Edit-2509-Lightning-8steps-V1.0-bf16.safetensors) |
102
+ | | r128 | [`svdq-int4_r128-qwen-image-edit-2509-lightning-8steps-251115.safetensors`](./lightning-251115/svdq-int4_r128-qwen-image-edit-2509-lightning-8steps-251115.safetensors) | 🔥 New: Fused with [Qwen-Image-Edit-2509-Lightning-8steps-V1.0 LoRA](https://huggingface.co/lightx2v/Qwen-Image-Lightning/blob/main/Qwen-Image-Edit-2509/Qwen-Image-Edit-2509-Lightning-8steps-V1.0-bf16.safetensors) |
103
  | NVFP4 | r32 | [`svdq-fp4_r32-qwen-image-edit-2509-lightning-8steps-251115.safetensors`](./lightning-251115/svdq-fp4_r32-qwen-image-edit-2509-lightning-8steps-251115.safetensors) | 🔥 New: Fused with [Qwen-Image-Edit-2509-Lightning-8steps-V1.0 LoRA](https://huggingface.co/lightx2v/Qwen-Image-Lightning/blob/main/Qwen-Image-Edit-2509/Qwen-Image-Edit-2509-Lightning-8steps-V1.0-bf16.safetensors) |
104
+ | | r128 | [`svdq-fp4_r128-qwen-image-edit-2509-lightning-8steps-251115.safetensors`](./lightning-251115/svdq-fp4_r128-qwen-image-edit-2509-lightning-8steps-251115.safetensors) | 🔥 New: Fused with [Qwen-Image-Edit-2509-Lightning-8steps-V1.0 LoRA](https://huggingface.co/lightx2v/Qwen-Image-Lightning/blob/main/Qwen-Image-Edit-2509/Qwen-Image-Edit-2509-Lightning-8steps-V1.0-bf16.safetensors) |
105
  | INT4 | r32 | [`svdq-int4_r32-qwen-image-edit-2509-lightningv2.0-8steps.safetensors`](./svdq-int4_r32-qwen-image-edit-2509-lightningv2.0-8steps.safetensors) | Fused with [Qwen-Image-Lightning-8steps-V2.0 LoRA](https://huggingface.co/lightx2v/Qwen-Image-Lightning/blob/main/Qwen-Image-Lightning-8steps-V2.0-bf16.safetensors) |
106
+ | | r128 | [`svdq-int4_r128-qwen-image-edit-2509-lightningv2.0-8steps.safetensors`](./svdq-int4_r128-qwen-image-edit-2509-lightningv2.0-8steps.safetensors) | Fused with [Qwen-Image-Lightning-8steps-V2.0 LoRA](https://huggingface.co/lightx2v/Qwen-Image-Lightning/blob/main/Qwen-Image-Lightning-8steps-V2.0-bf16.safetensors) |
107
  | NVFP4 | r32 | [`svdq-fp4_r32-qwen-image-edit-2509-lightningv2.0-8steps.safetensors`](./svdq-fp4_r32-qwen-image-edit-2509-lightningv2.0-8steps.safetensors) | Fused with [Qwen-Image-Lightning-8steps-V2.0 LoRA](https://huggingface.co/lightx2v/Qwen-Image-Lightning/blob/main/Qwen-Image-Lightning-8steps-V2.0-bf16.safetensors) |
108
+ | | r128 | [`svdq-fp4_r128-qwen-image-edit-2509-lightningv2.0-8steps.safetensors`](./svdq-fp4_r128-qwen-image-edit-2509-lightningv2.0-8steps.safetensors) | Fused with [Qwen-Image-Lightning-8steps-V2.0 LoRA](https://huggingface.co/lightx2v/Qwen-Image-Lightning/blob/main/Qwen-Image-Lightning-8steps-V2.0-bf16.safetensors) |
109
 
110
 
111