SeedEdit 3.0：快速且高质量的生成式图像编辑
SeedEdit 3.0: Fast and High-Quality Generative Image Editing
AI总结：
SeedEdit 3.0 通过元信息数据筛选和扩散损失与奖励损失联合学习，在真实图像编辑中显著提升指令遵循与内容保持，可用率达 56.1%，优于 SeedEdit 1.6、GPT4o 和 Gemini 2.0。
摘要：
我们推出 SeedEdit 3.0，与我们的文生图模型 Seedream 3.0 配套，在真实图像输入上，它在编辑指令遵循和图像内容（如身份/知识产权）保持两个方面都显著优于我们此前的 SeedEdit 版本。除了借助文生图进行模型升级外，本报告还介绍了几项关键改进。首先，我们开发了一种增强的数据筛选流程，采用元信息范式和元信息嵌入策略，有助于混合来自多个数据源的图像。这使我们能够有效扩展编辑数据，并且元信息有助于更紧密地连接视觉语言模型与扩散模型。其次，我们引入了一种联合学习流程，用于同时计算扩散损失和奖励损失。最后，我们在真实/合成图像编辑的测试基准上评估 SeedEdit 3.0，它在多个方面取得了最佳权衡，实现了 56.1% 的高可用率，相比之下 SeedEdit 1.6 为 38.4%，GPT4o 为 37.1%，Gemini 2.0 为 30.3%。
英文摘要：
We introduce SeedEdit 3.0, in companion with our T2I model Seedream 3.0, which significantly improves over our previous SeedEdit versions in both aspects of edit instruction following and image content (e.g., ID/IP) preservation on real image inputs. Additional to model upgrading with T2I, in this report, we present several key improvements. First, we develop an enhanced data curation pipeline with a meta-info paradigm and meta-info embedding strategy that help mix images from multiple data sources. This allows us to scale editing data effectively, and meta information is helpfult to connect VLM with diffusion model more closely. Second, we introduce a joint learning pipeline for computing a diffusion loss and reward losses. Finally, we evaluate SeedEdit 3.0 on our testing benchmarks, for real/synthetic image editing, where it achieves a best trade-off between multiple aspects, yielding a high usability rate of 56.1%, compared to SeedEdit 1.6 (38.4%), GPT4o (37.1%) and Gemini 2.0 (30.3%).
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。
