We propose a novel modular framework that learns to dynamically mix low-rank adapters (LoRAs) to improve visual analogy learning, enabling flexible and generalizable image edits based on example transformations.
- Updated
- Python
![]() |
VOOZH | about |
We propose a novel modular framework that learns to dynamically mix low-rank adapters (LoRAs) to improve visual analogy learning, enabling flexible and generalizable image edits based on example transformations.
Intro to Problem Solving -- notes
Add a description, image, and links to the visual-analogies topic page so that developers can more easily learn about it.
To associate your repository with the visual-analogies topic, visit your repo's landing page and select "manage topics."