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
Issue with Wan2_1-T2V-14B_fp8 model. Images look unfinished even after 50 steps.
#55
by healthyfat - opened
Probably the really low shift value?
No. I tried 5 and 10. Still same problem.
Pretty sure the default is Euler simple and not Euler beta
Otherwise you should try other samplers, I saw a few people using flowmatch something.
Or custom ones from Res4lyf custom nodes (but it seems rather slow)

