calcuis
/

wan-s2v-gguf

Model card Files Files and versions

calcuis commited on 7 days ago

Commit

51c4a40

·

verified ·

1 Parent(s): fa31f9c

Update README.md

Files changed (1) hide show

README.md +3 -1

README.md CHANGED Viewed

@@ -26,7 +26,9 @@ widget:
 ---
 ## **gguf quantized version of wan2.2-s2v (all gguf: incl. encoders + vae)**
 - drag **wan** to > `./ComfyUI/models/diffusion_models`
-- drag **umt5xxl** [[3.47GB](https://huggingface.co/calcuis/wan-s2v-gguf/blob/main/umt5xxl_fp32-q4_0.gguf)] to > `./ComfyUI/models/text_encoders`
 - drag **wav2vec2** [[632MB](https://huggingface.co/calcuis/wan-s2v-gguf/blob/main/wav2vec2_large_english_fp32-f16.gguf)] to > `./ComfyUI/models/audio_encoders`
 - drag **pig** [[254MB](https://huggingface.co/calcuis/wan-s2v-gguf/blob/main/pig_wan_vae_fp32-f16.gguf)] to > `./ComfyUI/models/vae`

 ---
 ## **gguf quantized version of wan2.2-s2v (all gguf: incl. encoders + vae)**
 - drag **wan** to > `./ComfyUI/models/diffusion_models`
+- either 1 or 2 below, drag it to > `./ComfyUI/models/text_encoders`
+  - option 1: just **umt5xxl** [[3.47GB](https://huggingface.co/calcuis/wan-s2v-gguf/blob/main/umt5xxl_fp32-q4_0.gguf)]
+  - option 2: both **cat-umt5xxl** [[3.66GB](https://huggingface.co/calcuis/cat-encoder/blob/main/cat-umt5xxl-q2_k.gguf)] and **tokenizer** [[4.55MB](https://huggingface.co/calcuis/cat-encoder/blob/main/tokenizer-umt5xxl-u8.safetensors)]
 - drag **wav2vec2** [[632MB](https://huggingface.co/calcuis/wan-s2v-gguf/blob/main/wav2vec2_large_english_fp32-f16.gguf)] to > `./ComfyUI/models/audio_encoders`
 - drag **pig** [[254MB](https://huggingface.co/calcuis/wan-s2v-gguf/blob/main/pig_wan_vae_fp32-f16.gguf)] to > `./ComfyUI/models/vae`