calcuis/wan2-gguf

---

license: apache-2.0 pipeline_tag: text-to-video tags:

• gguf-node

base_model:

• Comfy-Org/Wan2.2ComfyUI_Repackaged

widget:

• text: >-

a cute anime girl picking up a little pinky pig and moving quickly parameters: negative_prompt: blurry ugly bad output: url: workflow-14b-i2v.webp

• text: >-

drone shot of a volcano erupting with a pig walking on it parameters: negative_prompt: blurry ugly bad output: url: workflow-embedded.webm

• text: >-

drone shot of a volcano erupting with a pig walking on it parameters: negative_prompt: blurry ugly bad output: url: workflow-embedded.webp

---

gguf quantized version of wan2.2 models

• drag wan to > ./ComfyUI/models/diffusionmodels
• drag umt5xxl to > ./ComfyUI/models/textencoders
• drag pig to > ./ComfyUI/models/vae

!screenshot

!screenshot
tip: for 5b model, use pig-wan2-vae [1.41GB]; for 14b model, please use pig-wan-vae [254MB]

!screenshot
for s2v model setup, please refer to here

update

• upgrade your node (see last item from reference) for new/full quant support
• get more umt5xxl gguf encoder either here or here

reference

• base model from wan-ai
• 4/8-step lightning lora from lightx2v
• comfyui from comfyanonymous
• gguf-node (pypi|repo|pack)