-
Notifications
You must be signed in to change notification settings - Fork 6.6k
[Stable Diffusion Inpainting] Deprecate inpainting pipeline in favor of official one #903
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
Conversation
|
The documentation is not available anymore as the PR was closed or merged. |
src/diffusers/pipeline_utils.py
Outdated
|
|
||
| deprecation_message = ( | ||
| "You are using a legacy checkpoint for inpainting with Stable Diffusion, therefore we are loading the" | ||
| f" {StableDiffusionInpaintPipelineLegacy} class instead of {StableDiffusionInpaintPipeline}.For better" |
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.
| f" {StableDiffusionInpaintPipelineLegacy} class instead of {StableDiffusionInpaintPipeline}.For better" | |
| f" {StableDiffusionInpaintPipelineLegacy} class instead of {StableDiffusionInpaintPipeline}. For better" |
Co-authored-by: Anton Lozhkov <[email protected]>
|
Slow tests are passing for me locally - merging! |
| pipeline_class = getattr(diffusers_module, config_dict["_class_name"]) | ||
|
|
||
| # To be removed in 1.0.0 | ||
| if pipeline_class.__name__ == "StableDiffusionInpaintPipeline" and version.parse( |
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.
fallback mechanism
…of official one (huggingface#903) * finish * up * Apply suggestions from code review Co-authored-by: Anton Lozhkov <[email protected]> * Update src/diffusers/pipeline_utils.py * Finish Co-authored-by: Anton Lozhkov <[email protected]>
|
Hi @patrickvonplaten, thanks for the great work! just curious how's the performance improvement look like, in terms of image quality, training time, inference latency ... etc, from the legacy one to the latest inpainting pipeline? |
|
It should be pretty significant, here two spaces where you can try it out: |
|
Awesome, will try them out! |
…of official one (huggingface#903) * finish * up * Apply suggestions from code review Co-authored-by: Anton Lozhkov <[email protected]> * Update src/diffusers/pipeline_utils.py * Finish Co-authored-by: Anton Lozhkov <[email protected]>
…of official one (huggingface#903) * finish * up * Apply suggestions from code review Co-authored-by: Anton Lozhkov <[email protected]> * Update src/diffusers/pipeline_utils.py * Finish Co-authored-by: Anton Lozhkov <[email protected]>
https://huggingface.co/runwayml/stable-diffusion-inpainting