gguf quantized version of wan video drag gguf to ./ComfyUI/models/diffusion models drag t5xxl um to ./ComfyUI/models/text encoders drag vae to ./ComfyUI/models/vae workflow for i2v model, drag clip vision h to ./ComfyUI/models/clip vision run the .bat file in the main directory (assume you are using gguf pack below) if you opt to use fp8 scaled umt5xxl encoder (if applies to any fp8 scale t5 actually), please use cpu offload (switch from default to cpu under device in gguf clip loader ; won't affect speed); btw, it works fine for both gguf umt5xxl and gguf vae drag any demo video (below) to your browser for workflow review 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 might need to manually add pig in it's IMG ARCH LIST (under loader.py); easier than you edit the gguf file itself; btw, model architecture which compatible with comfyui gguf, including wan , should work in gguf node 1.3b model: t2v, vace gguf is working fine; good for old or low end machine run it with diffusers🧨 (alternative 1) run it with gguf connector (alternative 2) update wan2.1 v5 vace 1.3b: except block weights,…
We use cookies for essential functionality and analytics. You can accept or reject analytics cookies.Cookie policy