README.md

metadata

license: apache-2.0
base_model:
  - Wan-AI/Wan2.2-S2V-14B
tags:
  - gguf-node
widget:
  - text: >-
      a cute anime girl with massive fennec ears and a big fluffy tail wearing a
      maid outfit
    parameters:
      negative_prompt: blurry ugly bad
    output:
      url: workflow-demo1.webp
  - text: >-
      a cute anime girl with massive fennec ears and a big fluffy tail wearing a
      maid outfit turning around
    parameters:
      negative_prompt: blurry ugly bad
    output:
      url: workflow-demo2.webp
  - text: a conversation between cgg and connector
    parameters:
      negative_prompt: blurry ugly bad
    output:
      url: workflow-conversation.mp4

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]
  • option 2: both cat-umt5xxl [3.66GB] and tokenizer [4.55MB]
• drag wav2vec2 [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 (don't even need to switch to native loaders as GGUF AudioEncoder Loader and GGUF VAE Loader support both gguf and fp8 scaled safetensors files)
• gguf-node (pypi|repo|pack)