Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

is support generate single image?How much VRAM is needed to run inference #7

Open
libai-lab opened this issue Dec 1, 2024 · 1 comment

Comments

@libai-lab
Copy link

No description provided.

@SHYuanBest
Copy link
Member

Thanks for your interest. Generate single image is not supported yet; If you add the following lines, only 18G VRAM is needed for inference, but the generated quality will be reduced. Otherwise, 40G VRAM is needed. And we are continuously optimizing the code to reduce VRAM requirements.

pipe.enable_model_cpu_offload()
pipe.enable_sequential_cpu_offload()
pipe.vae.enable_slicing()
pipe.vae.enable_tiling()

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

2 participants