adding image_weight and image_end_percent - #8
Open
MohammadAboulEla wants to merge 2 commits into
Open
Conversation
This file contains hidden or 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
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
image_weight — how loudly the reference image "speaks" inside the text encoder. It scales the image's vision tokens before the language model reads them: 1.0 = normal, below 1 fades the image's specific content out (0.0 leaves a generic "there's an image here" blur), above 1 exaggerates it. One encoder pass, so it's free.
image_end_percent — how long the image keeps influencing the picture while it's being generated. At 0.4, the image-informed conditioning drives the first 40% of the steps (where composition, layout and identity get decided), then your prompt alone finishes the render. Costs a second encoder pass when below 1.0.
Rough guide: use image_weight to change how strong the reference feels, image_end_percent to keep the reference's structure while letting the prompt win on style and detail.