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
generated output license usages for CausVid lora or the license in general.
Wan21_CausVid_14B_T2V_lora_rank32_v2, what's the license on the output it generates? is it the same as the main Causvid or different since its pruned? sort of new and no one see to be able to answer this question on outputs.
I honestly don't know how that all ends up, the original CausVid training code is marked as cc 4.0 non-commercial, the 14B version being trained by the Lightx2v -team using code they forked from original CausVid, still marked as same cc4.0 license, but the weights themselves they uploaded are marked as Apache 2.0.
So this would be a question for Lightx2v team to answer in more detail, normally the licensing of the extracted lora in general would obey the licensing of the original model it's extracted from, which as mentioned, is Apache 2.0.