search

showlab / Tune-A-Video

[ICCV 2023] Tune-A-Video: One-Shot Tuning of Image Diffusion Models for Text-to-Video Generation
https://tuneavideo.github.io
Apache License 2.0
4.22k stars 384 forks source link

Support Stable Diffusion 2 #6

Closed alfredplpl closed 1 year ago

alfredplpl commented 1 year ago

Your work is great! I have generated Anime easily by my model, Cool Japan Diffusion 1.x. test_ test

I would like to generate Anime by Stable Diffusion 2.1 because I develop Cool Japan Diffusion 2.x that is based on Stable Diffusion 2.1. Do you plan to support Stable Diffusion 2.1?

zhangjiewu commented 1 year ago

There shouldn't be any problem to load the weights from Stable Diffusion 2.1. Simply modify the pretrained_model_path to where the model is saved.

alfredplpl commented 1 year ago

OK. Thanks. I could not apply it. However, I have checked that another developer applied it.