Skip to content

Conversation

@patrickvonplaten
Copy link
Contributor

No description provided.

@patrickvonplaten patrickvonplaten changed the title Start [Docs] DiffusionPipeline Sep 8, 2022
@HuggingFaceDocBuilderDev
Copy link

HuggingFaceDocBuilderDev commented Sep 8, 2022

The documentation is not available anymore as the PR was closed or merged.

@patrickvonplaten patrickvonplaten merged commit e7457b3 into main Sep 8, 2022
@patrickvonplaten patrickvonplaten deleted the add_diffusion_pipeline_docs branch September 8, 2022 11:50
Copy link
Member

@pcuenca pcuenca left a 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:
Copy link
Member

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:

Copy link
Contributor Author

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
Copy link
Member

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.
Copy link
Member

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.

yoonseokjin pushed a commit to yoonseokjin/diffusers that referenced this pull request Dec 25, 2023
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

Successfully merging this pull request may close these issues.

4 participants