Instructions to use Kijai/WanVideo_comfy with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusion Single File
How to use Kijai/WanVideo_comfy 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
I can only generate at 4 Steps with WAN Animate 2.2
#116
by Ulf3000 - opened
everything above 4 Steps will result in a strange image with colored noise. How can i bump up the quality from here ?
4steps , looks ok
8 or 10 steps
fusionx lora results in blurry video
and even running without loras and at 30 steps doesnt work.
im using the packaged workflow and your model , Wan2_2-Animate-14B_fp8_scaled_e4m3fn_KJ_v2.safetensors
Can anyone explain whats going on ?

