fix: image generation using imageSettings #1371
Merged
Conversation
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
while still retaining the ability to call via options with js
proteanx
changed the title
proteanx
changed the title
monilpat
approved these changes
Dec 23, 2024
1to3for5vi7ate9x
pushed a commit
to 1to3for5vi7ate9x/eliza
that referenced
this pull request
Jan 26, 2025
fix: image generation using imageSettings
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
Relates to:
So I started working on adding additional venice features for image generation and noticed that image settings for all models are currently completely broken. None of the imageSettings from character files which is what the docs currently say to use are actually passed to the API call. So before I submit the PR to add more venice features (I have this PR done as well) I figured I'd submit this to fix imageSettings for character files (while still retaining the ability to pass these options with js etc).
#1370
Risks
Low risk, this just provides a fix to an already tested feature.
Background
What does this PR do?
We added relevant imageSettings to our types file, created a call to pull the imageSettings in the image generation plugin and then looked for those settings when making our API call to generate an image.
What kind of change is this?
This is a bug fix, I have a feature PR ready for once this is merged.
Documentation changes needed?
No documentation changes needed as this actually just fixes what is already suggested in the docs (using imageSettings in character file for image settings)
Testing
Where should a reviewer start?
First you can test the current develop branch that the settings are not used in a character file by adding these settings (the width&height change is easiest)
If you're using openai make sure you use 1792x1024 (or a different supported size option other than the 1024x1024 default) as openai won't let you pick just any size (Venice lets you pick whatever size though)
Detailed testing steps
Now do the same test with this PR and you will notice your settings are passed and your image size is now using your settings.