MT-EditFlow: Reinforcement Learning for Multi-Turn Image Editing with Flow Matching

• URL: http://arxiv.org/abs/2606.01985v1
• Date: Mon, 01 Jun 2026 09:46:10 GMT
• Title: MT-EditFlow: Reinforcement Learning for Multi-Turn Image Editing with Flow Matching
• Abstract summary: MT-EditFlow is a flow-matching reinforcement learning framework designed to optimize reward signals for sequential image editing.<n>We show that MT-EditFlow significantly improves performance across diverse base models.
• Score: 91.83651402045108
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Recent breakthroughs in instruction-based image editing have captured significant attention, as models are now capable of handling real-world editing demands with the practicality required by everyday users. However, editing models trained primarily for single-turn edits often break down in multi-turn editing--the natural interactive setting where a user iteratively refines an image based on the model's own previous outputs. This failure stems from the all-or-nothing requirement, where a single failed turn compromises the entire sequence, and error propagation, where exposure bias leads to compounding editing errors. To address these challenges, we introduce MT-EditFlow, a flow-matching reinforcement learning framework designed to optimize reward signals for sequential image editing. MT-EditFlow integrates a multi-turn perspective with a multi-reward formulation to provide a unified structure applicable to both GRPO and NFT-based reinforcement learning methods. We systematically analyze and optimize the reward signal by investigating effective scoring strategies for turn-level aggregation, VLM reasoning modes to trade off reward bias and variance, and advantage fusion levels to prevent reward hacking. Our findings reveal that broadcasting the aggregated advantage across the entire editing trajectory effectively bridges the gap between local planning and global multi-turn task success. Extensive experiments demonstrate that MT-EditFlow significantly improves performance across diverse base models. Notably, it boosts FLUX.1-Kontext-dev by 6.85 points in turn-3 overall performance, surpassing state-of-the-art open-source models such as Qwen-Image-Edit. By maintaining high marginal success rates and reducing exposure bias, MT-EditFlow provides a foundation for more reliable and natural human-AI collaboration in visual content creation.

Related papers

• Leveraging Verifier-Based Reinforcement Learning in Image Editing [41.64251379221566]
  We introduce Edit-R1, a framework that builds a chain-of-thought (CoT) verifier-based reasoning reward model (RRM) for downstream image editing.<n>Our experiments demonstrate that our Edit-RRM surpasses powerful VLMs as an editing-specific reward model.
  arXiv  Detail & Related papers  (2026-04-30T06:54:39Z)
• Tuning Real-World Image Restoration at Inference: A Test-Time Scaling Paradigm for Flow Matching Models [26.002982722748726]
  ResFlow-Tuner is an image restoration framework based on the state-of-the-art flow matching model, FLUX.1-dev.<n>We propose a training-free test-time scaling paradigm tailored for image restoration.
  arXiv  Detail & Related papers  (2026-03-23T14:33:43Z)
• Uniworld-V2: Reinforce Image Editing with Diffusion Negative-aware Finetuning and MLLM Implicit Feedback [41.41713036839503]
  We introduce Edit-R1, a novel post-training framework for instruction-based image editing based on policy optimization.<n>We employ a Multimodal Large Language Model (MLLM) as a unified, training-free reward model, leveraging its output logits to provide fine-grained feedback.<n>Our framework is model-agnostic, delivering substantial performance gains when applied to diverse base models.
  arXiv  Detail & Related papers  (2025-10-19T15:38:06Z)
• EditScore: Unlocking Online RL for Image Editing via High-Fidelity Reward Modeling [71.8265422228785]
  Reinforcement Learning (RL) offers a promising solution, but its adoption in image editing has been hindered by the lack of a high-fidelity, efficient reward signal.<n>We present a comprehensive methodology to overcome this barrier, centered on the development of a state-of-the-art, specialized reward model.
  arXiv  Detail & Related papers  (2025-09-28T14:28:24Z)
• Stable Flow: Vital Layers for Training-Free Image Editing [74.52248787189302]
  Diffusion models have revolutionized the field of content synthesis and editing.<n>Recent models have replaced the traditional UNet architecture with the Diffusion Transformer (DiT)<n>We propose an automatic method to identify "vital layers" within DiT, crucial for image formation.<n>Next, to enable real-image editing, we introduce an improved image inversion method for flow models.
  arXiv  Detail & Related papers  (2024-11-21T18:59:51Z)
• Taming Rectified Flow for Inversion and Editing [57.3742655030493]
  Rectified-flow-based diffusion transformers like FLUX and OpenSora have demonstrated outstanding performance in the field of image and video generation.<n>Despite their robust generative capabilities, these models often struggle with inaccuracies.<n>We propose RF-r, a training-free sampler that effectively enhances inversion precision by mitigating the errors in the inversion process of rectified flow.
  arXiv  Detail & Related papers  (2024-11-07T14:29:02Z)
• Task-Oriented Diffusion Inversion for High-Fidelity Text-based Editing [60.730661748555214]
  We introduce textbfTask-textbfOriented textbfDiffusion textbfInversion (textbfTODInv), a novel framework that inverts and edits real images tailored to specific editing tasks. ToDInv seamlessly integrates inversion and editing through reciprocal optimization, ensuring both high fidelity and precise editability.
  arXiv  Detail & Related papers  (2024-08-23T22:16:34Z)
• End-to-End Visual Editing with a Generatively Pre-Trained Artist [78.5922562526874]
  We consider the targeted image editing problem: blending a region in a source image with a driver image that specifies the desired change. We propose a self-supervised approach that simulates edits by augmenting off-the-shelf images in a target domain. We show that different blending effects can be learned by an intuitive control of the augmentation process, with no other changes required to the model architecture.
  arXiv  Detail & Related papers  (2022-05-03T17:59:30Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.