how can i use this model
#4
by
PeterYoung777
- opened
i need a workflow thanks
You can use the native comfyui implementation: https://comfyanonymous.github.io/ComfyUI_examples/wan/ then change the default unet loader with the gguf one. Use the text to video workflow until the img2vid gguf model is available, then you can use the img2vid workflow. Notice that you need exactly the text encoder and vae specified at the link above (and probably the same clip vision too), I tried the ones providied by city96 and Kijai and didn't work, while with the ones by comfy-org it worked