calcuis commited on
Commit
d7ec81b
·
verified ·
1 Parent(s): 1a29de5

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +5 -0
README.md CHANGED
@@ -88,6 +88,11 @@ widget:
88
 
89
  <Gallery />
90
 
 
 
 
 
 
91
  ### **reference**
92
  - base model from [wan-ai](https://huggingface.co/Wan-AI/Wan2.1-T2V-14B)
93
  - comfyui from [comfyanonymous](https://github.com/comfyanonymous/ComfyUI)
 
88
 
89
  <Gallery />
90
 
91
+ ## **review**
92
+ - `pig` is a lazy architecture for gguf node; it applies to all model, encoder and vae gguf file(s); if you try to run it in comfyui-gguf node, you should manually add `pig` in it's IMG_ARCH_LIST (under loader.py)
93
+ - q2 works and usable in this repo; since part/all of the weight were replaced with q3; experimental attempt
94
+ - 1.3b t2v works in fp32-f32 standard; for both safetensors and gguf
95
+
96
  ### **reference**
97
  - base model from [wan-ai](https://huggingface.co/Wan-AI/Wan2.1-T2V-14B)
98
  - comfyui from [comfyanonymous](https://github.com/comfyanonymous/ComfyUI)