ACEdit:以非對稱條件化穩定多輪圖片編輯
ACEdit: Stable Multi-Turn Image Editing via Asymmetric Conditioning
ACEdit提出結合自我強制訓練、教師蒸餾與非對稱條件化的訓練方案,令多輪圖片編輯在累積分佈偏移下保持穩定。學生模型依序編輯自身先前輸出,教師圖像編輯模型則以原始乾淨圖片為基準,並接收複合編輯指令。實驗顯示,該方法在維持編輯品質和指令遵循度的同時,顯著減少長序列多輪編輯中的品質下降。
Published on Oct 15
Authors:
,
,
,
Abstract
Self-forcing training with teacher distillation and asymmetric conditioning stabilizes multi-turn image editing against accumulating distribution shifts.
Image editing models produce impressive results for individual edits, but their quality often deteriorates over multiple editing turns. Each editing turn introduces small distribution shifts that accumulate over successive edits, creating a gap between the input distributions encountered during the editor's original training and multi-turn inference. We introduce a training scheme that makes multi-turn image editing stable under this accumulating distribution shift. A key is to force the editor to operate on its own outputs from previous editing turns during training, bringing the principle of Self-Forcing to image editing. The main challenge is that self-generated editing trajectories deviate from ground-truth trajectories, making direct supervision unreliable. We address this challenge through a distillation objective that leverages a teacher image editor to provide a reliable training signal when the model operates on its own previous outputs. We introduce an asymmetric conditioning scheme: while the student performs edits sequentially on its own outputs, the teacher remains anchored to the original clean image and receives a compound editing instruction. Experiments show substantially reduced degradation over long multi-turn sequences while maintaining editing quality and instruction adherence.
View arXiv page View PDF Project page Add to collection
Get this paper in your agent:
hf papers read 2610.22328
Don't have the latest CLI?
curl -LsSf https://hf.co/cli/install.sh | bash
Models citing this paper 0
No model linking this paper
Cite arxiv.org/abs/2610.22328 in a model README.md to link it from this page.
Datasets citing this paper 0
No dataset linking this paper
Cite arxiv.org/abs/2610.22328 in a dataset README.md to link it from this page.
Spaces citing this paper 0
No Space linking this paper
Cite arxiv.org/abs/2610.22328 in a Space README.md to link it from this page.
Collections including this paper 0
No Collection including this paper
Add this paper to a collection to link it from this page.
來源:HuggingFace Daily Papers(社區熱門論文) · huggingface.co