search

hotshotco / Hotshot-XL

✨ Hotshot-XL: State-of-the-art AI text-to-GIF model trained to work alongside Stable Diffusion XL
https://hotshot.co
Apache License 2.0
982 stars 77 forks source link

Question for finetune #45

Closed xiefan233 closed 5 months ago

xiefan233 commented 5 months ago

I am using your code for finetune, but I will always have "cuda out of memory" error. My experimental conditions are two 40GB A100, may I ask what experimental conditions are needed to run your code?

johnmullan commented 5 months ago

What batch size and frame length are you using? the model was trained on 80gbs. 40GB can be achievable but you really gotta pull a lot of tricks memory wise. Use gradient checkpointing, xformers, torch.cuda.empty_cache() every step.