Uni-1 supports prompt-based image editing via the modify_image endpoint rather than traditional mask-based inpainting or outpainting. You provide a source image and text instructions describing changes. The model transforms the scene according to instructions while preserving overall composition.
Was this article helpful?
That’s Great!
Thank you for your feedback
Sorry! We couldn't be helpful
Thank you for your feedback
Feedback sent
We appreciate your effort and will try to fix the article