VibeEdit: Image Editing with Canvas Instructions

VibeEdit introduces an image editing interface where users place spatial marks and notes to create a 'canvas instruction' instead of text prompts. This allows the system to perform complex edits like adding, removing, or moving objects directly on an image. Trained on 1.55 million pairs, VibeEdit uses decoupled conditioning and reinforcement learning to achieve high accuracy in editing tasks.

Open the full episode

More from AI Radio