invoke-ai / invoke-ai/InvokeAI

[enhancement]: Model and lora selectable settings

Open
#5,359 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

### What should this feature add?

There are some enhancements to the model manager that support or enhance this request:
https://github.com/invoke-ai/InvokeAI/issues/4594
https://github.com/invoke-ai/InvokeAI/issues/4550
https://github.com/invoke-ai/InvokeAI/issues/4043

Allow the selection of default values in the prompt fields.
For 4594 - Allow Trigger word/s to be selected in the prompts
Extend this to all fields and add a load defaults button that pulls the information from the model profile

When loading the model in 4550 ask to load defaults.

I think 4043 is self explanatory, but adding the possibility for Model and lora profiles now would make the transition later much easier.

Add the same treatment to LoRa. i.e. add ability to store and select trigger words and default weight

### Alternatives

Create a profile selector instead of model selector. A database of selectable profiles that load models, LoRa, ..., and prompts.

### 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.