跳到正文
HuggingFace Daily Papers(社區熱門論文)·· 2026-10-16AI 評分43

MTEdit: Packed Trajectories Beat Rollouts for Multi-Turn Image Editing

MTEdit: Packed Trajectories Beat Rollouts for Multi-Turn Image Editing

AI 導讀

MTEdit 提出以打包軌跡畫布生成建立多輪圖像編輯數據集,減少逐輪生成造成的視覺品質漂移,並推出 MTEdit-Bench 評估模型。數據集包含 500K 條軌跡,每條最多 8 輪,平均 5.38 輪;以此微調的 Qwen-Image-MTEdit,在受評估的開源模型中表現最佳。

正文

Published on Oct 16

Authors:

,

,

,

,

,

,

,

,

Abstract

MTEdit is a large-scale multi-turn image editing dataset using packed trajectory canvas generation to reduce visual drift, enabling improved multi-turn editing models evaluated on MTEdit-Bench.

Multi-turn image editing aims to modify an image according to a sequence of instructions, making it better aligned with human-AI collaborative creation than single-turn editing. However, constructing high-quality multi-turn training data remains challenging, as conventional sequential rollout accumulates errors and introduces visual-quality drift across editing turns. To address this challenge, we introduce MTEdit, a multi-turn image editing dataset built through a pipeline centered on packed trajectory canvas (PTC) generation. By jointly generating multiple editing states within a unified visual context, this pipeline reduces visual-quality drift across turns. Covering both step-wise and context-aware editing scenarios, MTEdit comprises 500K multi-turn image editing trajectories, with up to 8 turns and an average of 5.38 turns per trajectory, making it one of the most extensive datasets for multi-turn image editing. We further introduce MTEdit-Bench, a benchmark designed to evaluate both scenarios by assessing models' ability to follow editing instructions, maintain content consistency, resist visual-quality drift, and effectively use historical context across turns. Using MTEdit, we fine-tune Qwen-Image-Edit-Causal to obtain Qwen-Image-MTEdit. On MTEdit-Bench, we evaluate a broad range of closed-source and open-source image editing models, including Qwen-Image-MTEdit. Experimental results show that Qwen-Image-MTEdit achieves the best performance among the evaluated open-source models, demonstrating the effectiveness of MTEdit in improving models' multi-turn image editing capabilities.

View arXiv page View PDF Add to collection

Get this paper in your agent:

hf papers read 2610.23751

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/2610.23751 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/2610.23751 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/2610.23751 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