invoke-ai / invoke-ai/InvokeAI

[enhancement]: Add a way to convert models to diffusers in bulk

Open
#6,237 0 comments 0 reactions 0 assignees View on GitHub
enhancement
Dominant language
Python
Stars
28.2k
Forks
3k
Avg merge
6d 5h
Merged PRs (30d)
19

Description

### Is there an existing issue for this?

- [X] I have searched the existing issues

### Contact Details

_No response_

### What should this feature add?

Converting models to diffusers can get very time consuming and get in the way of workflow.
What I would like to see is an option to convert all uncached models all at once, so that switching between models becomes more responsive.
I know there is a parameter to control the size of the model conversion cache but that only addresses models converted one at a time.
If you do have the disk space available, an option to convert everything in bulk would save a lot of time in the long run.

A logical place for this feature would be in the Model Management panel, with an option to convert all models.
There is already an option to convert one model at a time.
This would be about building a queue to convert all models currently not in the local cache of diffusers.

### Alternatives

It doesn't have to be an update to the UI. A command line option or batch file menu option would be fine.

### Additional Content

_No response_

Contributor guide

No contributing guide indexed for this repository

Assessment

This issue has not been assessed yet.

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.