Skip to content
New issue

Have a question about this project? # for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “#”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? # to your account

[Feature Request]: save "trigger words" for a model alongside the checkpoints #6013

Closed
1 task done
Lesani opened this issue Dec 25, 2022 · 3 comments
Closed
1 task done

Comments

@Lesani
Copy link

Lesani commented Dec 25, 2022

Is there an existing issue for this?

  • I have searched the existing issues and checked the recent builds/commits

What would your feature do ?

Models and embeddings have their own trigger words that need to be used. When you have 10-20-30 different models it gets hard to keep track of which model needed which trigger words. The idea is to have the relevant trigger words saved somewhere alongside the model, and when the model is loaded display them near the prompt input so you can copy/paste them into your prompt as needed.

Proposed workflow

  1. Select model from the dropdown
  2. when model loads, additional text is displayed around the prompt area, that "reminds" you of the necessary trigger words for that model
  3. don't get frustrated anymore searching for the right trigger words

Additional information

No response

@ClashSAN
Copy link
Collaborator

#5922
#5237
numerous requests for similar things (PRs welcome!)

@cluder
Copy link
Contributor

cluder commented Dec 26, 2022

i just saw this extension https://github.com/Vetchems/sd-model-preview in unstable diffusions discord, it might be about what you want

@Lesani
Copy link
Author

Lesani commented Dec 26, 2022

@cluder yes this does what I wanted, THANK YOU! would prefer it to be at the selection box rather than a tab, but nontheless

# for free to join this conversation on GitHub. Already have an account? # to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

3 participants