Qwen-Image-2.0-RL Technical Report

• URL: http://arxiv.org/abs/2606.27608v1
• Date: Thu, 25 Jun 2026 23:49:50 GMT
• Title: Qwen-Image-2.0-RL Technical Report
• Abstract summary: We present Qwen-Image-2.0-RL, a post-training pipeline that applies reinforcement learning from human feedback and on-policy distillation.<n>Qwen-Image-2.0-RL achieves 57.84 overall score on Qwen-Image-Bench, Elo ratings of 1193 in text-to-image arena and 1349 in image edit arena.
• Score: 66.2346321737379
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: We present Qwen-Image-2.0-RL, a post-training pipeline that applies reinforcement learning from human feedback (RLHF) and on-policy distillation (OPD) to improve both the visual quality and instruction-following capability of the Qwen-Image-2.0 diffusion model. To provide reliable reward signals, we construct task-specific composite reward models by fine-tuning vision-language models with a pointwise scoring paradigm and chain-of-thought reasoning. For text-to-image generation, the reward models cover alignment, aesthetics, and portrait fidelity dimensions. For image editing tasks, the reward system addresses instruction-following accuracy and face identity preservation. Building on this reward system, we develop a scalable GRPO-based RL training framework, incorporating a hybrid classifier-free guidance (CFG) strategy to preserve pre-trained knowledge, prompt curation via intra-group reward range filtering, and per-category reward weight calibration. To merge the task-specialized RL policies for T2I and editing, we propose on-policy distillation as the final training stage, which consolidates multiple teachers into a single student model through trajectory-level velocity matching. Extensive evaluation shows that Qwen-Image-2.0-RL achieves 57.84 overall score on Qwen-Image-Bench (+2.61 over the base model), Elo ratings of 1193 in text-to-image arena (+78) and 1349 in image edit arena (+93), demonstrating consistent gains in aesthetic quality, prompt adherence, and editing accuracy.

Related papers

• Q-DeepSight: Incentivizing Thinking with Images for Image Quality Assessment and Refinement [58.15004031934379]
  We propose Q-DeepSight, a think-with-image framework that emulates this human-like process.<n>Q-DeepSight achieves state-of-the-art performance across diverse benchmarks, including natural, restored, and AI-generated content.<n>We demonstrate its practical value with Perceptual-in-Generation (PiG), a training-free framework where Q-DeepSight's diagnoses guide iterative image enhancement.
  arXiv  Detail & Related papers  (2026-04-18T06:10:57Z)
• PromptEcho: Annotation-Free Reward from Vision-Language Models for Text-to-Image Reinforcement Learning [14.637088591693088]
  Reinforcement learning can improve the prompt following capability of text-to-image (T2I) models.<n>We propose PromptEcho, a reward construction method that requires emphno annotation and emphno reward model training.
  arXiv  Detail & Related papers  (2026-04-14T12:21:15Z)
• The Image as Its Own Reward: Reinforcement Learning with Adversarial Reward for Image Generation [52.648073272395635]
  We introduce Adv-GRPO, an RL framework with an adversarial reward that iteratively updates both the reward model and the generator.<n>Unlike KL regularization that constrains parameter updates, our learned reward directly guides the generator through its visual outputs.<n>In human evaluation, our method outperforms Flow-GRPO and SD3, achieving 70.0% and 72.4% win rates in image quality and aesthetics, respectively.
  arXiv  Detail & Related papers  (2025-11-25T12:35:57Z)
• 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)
• PromptEnhancer: A Simple Approach to Enhance Text-to-Image Models via Chain-of-Thought Prompt Rewriting [31.35160142315478]
  We introduce PromptEnhancer, a novel and universal prompt rewriting framework for text-to-image (T2I) models.<n>Unlike prior methods that rely on model-specific fine-tuning or implicit reward signals like image-reward scores, our framework decouples the rewriter from the generator.<n>Experiments on the HunyuanImage 2.1 model demonstrate that PromptEnhancer significantly improves image-text alignment across a wide range of semantic and compositional challenges.
  arXiv  Detail & Related papers  (2025-09-04T16:46:10Z)
• AR-GRPO: Training Autoregressive Image Generation Models via Reinforcement Learning [56.71089466532673]
  We propose AR-GRPO, an approach to integrate online RL training into autoregressive (AR) image generation models.<n>We conduct comprehensive experiments on both class-conditional (i.e., class-to-image) and text-conditional (i.e., text-to-image) image generation tasks.<n>Our results show consistent improvements across various evaluation metrics.
  arXiv  Detail & Related papers  (2025-08-09T10:37:26Z)
• RL for Consistency Models: Faster Reward Guided Text-to-Image Generation [15.238373471473645]
  We propose a framework for fine-tuning consistency models viaReinforcement Learning (RL) Our framework, called Reinforcement Learning for Consistency Model (RLCM), frames the iterative inference process of a consistency model as an RL procedure. Comparing to RL finetuned diffusion models, RLCM trains significantly faster, improves the quality of the generation measured under the reward objectives, and speeds up the inference procedure by generating high quality images with as few as two inference steps.
  arXiv  Detail & Related papers  (2024-03-25T15:40:22Z)
• DPOK: Reinforcement Learning for Fine-tuning Text-to-Image Diffusion Models [97.31200133440308]
  We propose using online reinforcement learning to fine-tune text-to-image models. We focus on diffusion models, defining the fine-tuning task as an RL problem. Our approach, coined DPOK, integrates policy optimization with KL regularization.
  arXiv  Detail & Related papers  (2023-05-25T17:35:38Z)

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.