ACEdit: Stable Multi-Turn Image Editing via Asymmetric Conditioning

ACEdit introduces a training scheme that stabilizes multi-turn image editing by forcing the editor to operate on its own previous outputs, a concept called Self-Forcing. To overcome unreliable supervision from self-generated trajectories, the method employs a distillation objective using a teacher editor that remains anchored to the original image while receiving compound instructions. Experiments demonstrate reduced degradation over long editing sequences while preserving quality and instruction adherence.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv AI.

• efficiency