Instructions to use Kijai/WanVideo_comfy_fp8_scaled with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusion Single File
How to use Kijai/WanVideo_comfy_fp8_scaled with Diffusion Single File:
# No code snippets available yet for this library. # To use this model, check the repository files and the library's documentation. # Want to help? PRs adding snippets are welcome at: # https://github.com/huggingface/huggingface.js
- Notebooks
- Google Colab
- Kaggle
How to use with ComfyUI native WanVideo nodes?
#2
by zhilengjun - opened
When loading,it log that "unet missing: ['text_embedding.0.scale_weight', 'text_embedding.2.scale_weight', 'time_embedding.0.scale_weight', 'time_embedding.2.scale_weight', 'time_projection.1.scale_weight', 'head.head.scale_weight']"
Thank you very much, your response is really fast!
Yes, I use this, and there is indeed no problem with the video quality.
zhilengjun changed discussion status to closed
zhilengjun changed discussion status to open
However, the VACE model should not be used in Comfyui native nodes, right?
However, the VACE model should not be used in Comfyui native nodes, right?
That's right, there's currently no mechanic to load the module only.
