[Feature Request]: Add support for Make-a-Video Stable Diffusion

kabachuha / sd-webui-text2video

Auto1111 extension implementing text2video diffusion models (like ModelScope or VideoCrafter) using only Auto1111 webui dependencies

Other

1.28k stars 106 forks source link

[Feature Request]: Add support for Make-a-Video Stable Diffusion #150

Open kabachuha opened 1 year ago

kabachuha commented 1 year ago

Is there an existing issue for this?

[X] I have searched the existing issues and checked the recent builds/commits

What would your feature do ?

Adding support for the new https://huggingface.co/spaces/TempoFunk/makeavid-sd-jax model

Proposed workflow

Go to another text2video mode
...

Additional information

No response

lopho commented 1 year ago

Model implementation lives here: https://github.com/lopho/makeavid-sd-tpu (torch + jax implementations, both usable on GPU + TPU) It is still messy and missing docs, but it works.