-
Notifications
You must be signed in to change notification settings - Fork 6.5k
[Docs] DiffusionPipeline #418
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. |
pcuenca
left a comment
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.
Very nice!
| Base class for all models. | ||
| [`DiffusionPipeline`] takes care of storing all components (models, schedulers, processors) for diffusion pipelines | ||
| and handles methods for loading, downloading and saving models as well as a few methods common to all pipelines to: |
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.
Maybe a bit too long. Suggestion:
[`DiffusionPipeline`] takes care of storing all components (models, schedulers, processors) for diffusion pipelines
and handles methods for loading, downloading and saving models. It also implements some utility methods common to all pipelines to:
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.
Sorry was a bit too fast here in the rush yesterday 😅 - would you maybe like to open a new PR?
| and handles methods for loading, downloading and saving models as well as a few methods common to all pipelines to: | ||
| - move all PyTorch modules to the device of your choice | ||
| - enabling/disabling the progress bar for the denoising iteration |
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.
Perhaps "enable/disable" (instead of "enabling/disabling") for consistency with the previous use.
| task. | ||
| The warning *Weights from XXX not used in YYY* means that the layer XXX is not used by YYY, therefore those | ||
| weights are discarded. |
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.
Maybe add some comment here that this is common but totally harmless in some situations. Something like:
This is common when using multimodal encoders, such as CLIP, to encode text prompts – the vision part of the model is never used so it's discarded. This is totally ok in this situation.
* Start * up * up * finish
No description provided.