-
Notifications
You must be signed in to change notification settings - Fork 5.6k
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
[Core] enable lora for sdxl controlnets too and add slow tests. #4666
Conversation
The documentation is not available anymore as the PR was closed or merged. |
pipe = StableDiffusionXLControlNetPipeline.from_pretrained( | ||
"stabilityai/stable-diffusion-xl-base-1.0", controlnet=controlnet | ||
) | ||
pipe.enable_sequential_cpu_offload() |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Just a question. Is there are difference between enable_model_cpu_offload
and enable_sequential_cpu_offload
? Is one preferred over the other?
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Would suggest checking out the doc here:
def enable_sequential_cpu_offload(self, gpu_id: int = 0, device: Union[torch.device, str] = "cuda"): |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
nice!
…ingface#4666) * enable lora for sdxl controlnets too. * add: tests * fix: assertion values.
…ingface#4666) * enable lora for sdxl controlnets too. * add: tests * fix: assertion values.
Fixes #4664.
Additionally, adds SLOW tests for SDXL ControlNets.