FireRed-Image-Edit-1.0 技术报告
FireRed-Image-Edit-1.0 Technical Report
AI总结：
提出FireRed-Image-Edit扩散变换器，通过数据整理、多阶段训练和评估优化，在指令图像编辑上达到最先进性能，并开源代码、模型和基准。
摘要：
我们提出FireRed-Image-Edit，一种基于指令的图像编辑扩散变换器，通过系统优化数据整理、训练方法和评估设计，实现了最先进的性能。我们构建了一个16亿样本的训练语料库，包含来自不同来源的9亿文本到图像和7亿图像编辑对。经过严格清洗、分层、自动标注和两阶段过滤，我们保留了超过1亿高质量样本，在生成和编辑之间取得平衡，确保强大的语义覆盖和指令对齐。我们的多阶段训练流程通过预训练、监督微调和强化学习逐步构建编辑能力。为了提高数据效率，我们引入了多条件感知桶采样器用于可变分辨率批处理，以及带有动态提示重索引的随机指令对齐。为了稳定优化并增强可控性，我们提出了用于DPO的非对称梯度优化、用于文本编辑的具有布局感知OCR奖励的DiffusionNFT，以及用于身份保持的可微一致性损失。我们进一步建立了REDEdit-Bench，一个涵盖15个编辑类别的综合基准，包括新引入的美化和低级增强任务。在REDEdit-Bench和公共基准（ImgEdit和GEdit）上的大量实验表明，与开源和专有系统相比，我们的性能具有竞争力或更优。为了支持未来研究，我们的代码、模型和基准套件在此https URL公开提供。
英文摘要：
We present FireRed-Image-Edit, a diffusion transformer for instruction-based image editing that achieves state-of-the-art performance through systematic optimization of data curation, training methodology, and evaluation design. We construct a 1.6B-sample training corpus, comprising 900M text-to-image and 700M image editing pairs from diverse sources. After rigorous cleaning, stratification, auto-labeling, and two-stage filtering, we retain over 100M high-quality samples balanced between generation and editing, ensuring strong semantic coverage and instruction alignment. Our multi-stage training pipeline progressively builds editing capability via pre-training, supervised fine-tuning, and reinforcement learning. To improve data efficiency, we introduce a Multi-Condition Aware Bucket Sampler for variable-resolution batching and Stochastic Instruction Alignment with dynamic prompt re-indexing. To stabilize optimization and enhance controllability, we propose Asymmetric Gradient Optimization for DPO, DiffusionNFT with layout-aware OCR rewards for text editing, and a differentiable Consistency Loss for identity preservation. We further establish REDEdit-Bench, a comprehensive benchmark spanning 15 editing categories, including newly introduced beautification and low-level enhancement tasks. Extensive experiments on REDEdit-Bench and public benchmarks (ImgEdit and GEdit) demonstrate competitive or superior performance against both open-source and proprietary systems. To support future research, our code, models, and benchmark suite are publicly available at https://github.com/FireRedTeam/FireRed-Image-Edit/ .
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
