Hugging Face's logo

Phr00t
/
Qwen-Image-Edit-Rapid-AIO

Text-to-Image
comfyUI
qwen
qwen-edit
t2i
i2i
Model card Files
xet
Community
171
Phr00t commited on
Commit
32e5ff3
·
verified ·
1 Parent(s): 3c20bb8

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +1 -1
README.md CHANGED
@@ -36,4 +36,4 @@ Use a "Load Checkpoint" node. 1 CFG, 4 step. Use the "TextEncodeQwenImageEditPlu
36
 
37
  **V7:** valiantcat/Qwen-Image-Edit-MeiTu and chestnutlzj/Edit-R1-Qwen-Image-Edit-2509 included as LORAs. Accelerator and NSFW LORAs tweaks (v7.1 is more NSFW-heavy). This seemed to be working much better. **lcm/sgm_uniform recommended for 4-6 steps, lcm/normal for 7-8 steps**.
38
 
39
- **V8:** Using the FP8 scaled straight from Lightx2v + FP32 versions of accelerators. Tweaked accelerator amounts. Significant NSFW LORA tweaks (and new SNOFS). Still uploading/verifying...
 
36
 
37
  **V7:** valiantcat/Qwen-Image-Edit-MeiTu and chestnutlzj/Edit-R1-Qwen-Image-Edit-2509 included as LORAs. Accelerator and NSFW LORAs tweaks (v7.1 is more NSFW-heavy). This seemed to be working much better. **lcm/sgm_uniform recommended for 4-6 steps, lcm/normal for 7-8 steps**.
38
 
39
+ **V8:** Using BF16 to load in FP32 LORAs, only to scale down to FP8 for saving. This seems to help resolve "grid" issues and improves quality. Tweaked accelerator amounts. Significant NSFW LORA tweaks (and new SNOFS). **euler_a/beta recommended for 4-6 steps, lcm/normal for 7-8 steps**.