search

gwang-kim / DiffusionCLIP

[CVPR 2022] Official PyTorch Implementation for DiffusionCLIP: Text-guided Image Manipulation Using Diffusion Models
Other
785 stars 113 forks source link

Is there any way to finetune in colab? #4

Closed loboere closed 2 years ago

loboere commented 2 years ago

Is there any way to finetune in colab?, maybe reducing batch size or something similar

gwang-kim commented 2 years ago

Thanks for your interest in our work, @loboere. Unfortunately, for now, VRAM of 12 GB+ for 256x256 images is required at a minimum and Colab allows 11GB VRAM. I think I can reduce the GPU memory by optimizing the code and if I finish it, I will inform you.