calcuis/wan-s2v-gguf

gguf quantized version of wan2.2-s2v (all gguf: incl. encoders + vae)

• drag wan to > ./ComfyUI/models/diffusion_models
• anyone below, drag it to > ./ComfyUI/models/text_encoders
  • option 1: just cow-umt5xxl [3.67GB]
  • option 2: both cat-umt5xxl [3.66GB] and tokenizer [4.55MB]
  • option 3: just umt5xxl [3.47GB] (need protobuf to rebuild tokenizer)
• drag wav2vec2-v2 [632MB] to > ./ComfyUI/models/audio_encoders
• drag pig [254MB] to > ./ComfyUI/models/vae

Prompt

a cute anime girl with massive fennec ears and a big fluffy tail wearing a maid outfit

Negative Prompt

blurry ugly bad

Prompt

a cute anime girl with massive fennec ears and a big fluffy tail wearing a maid outfit turning around

Negative Prompt

blurry ugly bad

Prompt

a conversation between cgg and connector

Negative Prompt

blurry ugly bad

note: the new GGUF AudioEncoder Loader on test; running gguf audio encoder wav2vec2 w/o ending error msg compare to fp16 safetensors (depends how long of your prompt/video)

reference

• for the lite workflow (save >70% loading time), get the lite lora for 4/8-step operation here
• or opt to use scaled fp8 e4m3 safetensors audio encoder here and/or fp8 e4m3 vae here and/or scaled fp8 e4m3 safetensors text encoder here (don't even need to switch to native loaders as GGUF AudioEncoder Loader, GGUF VAE Loader and GGUF CLIP Loader support both gguf and fp8 scaled safetensors files; can mix up or combine use as well)
• gguf-node (pypi|repo|pack)