把图片里的字翻译成另一种语言，不用重新训练模型
把图片里的文字翻译成另一种语言，过去得先准备成千上万张「翻译前/后」的配对图去训练专用模型。这篇直接借现成的文生图模型，加一个 OCR 识别原文、让大模型生成翻译指令，再在扩散生成的中途做两次轨迹微调：先让文字区域的噪声早点和背景脱钩，再放大翻译带来的编辑位移。结果在整张照片翻译成中文的任务上，准确率 40.1%，超过所有现有编辑系统。它不是你明天能装进 App 的成品，但它证明了一条路：翻译图片里的字，可以不再为每个语种囤数据，而是靠通用模型的能力直接迁移。
📄 原文摘要(英文)
In-image machine translation (IIMT) replaces text in an image with its translation while preserving the surrounding visual context. Existing task-specific models achieve convincing performance but require massive paired training images before and after translation. As advanced text-to-image (T2I) models have reached a practically usable level of multilingual text generation, we argue that this capability can be transferred to IIMT and present FlowTranslator. It is a training-free IIMT framework that first employs an OCR model and an LLM to generate the translation prompt, which is injected into the T2I-based diffusion model. To optimize the accurate and natural generation of translated text, we introduce two trajectory controls: Region Coupling Release (RCR) partially decorrelates target-branch noise inside the text region early in the trajectory, while Coupling Expansion (CE) amplifies the emerging edit displacement mid-trajectory. Under the EasyOCR read-back protocol, FlowTranslator achieves average PRIM BLEU and COMET scores of 20.6 and 57.2, respectively, substantially outperforming the strong training-based baseline UniTranslator. On the more challenging and realistic whole-image ScenePair photographs translated into Chinese, it reaches 40.1\% exact-match accuracy and surpasses existing editing systems, some of which only address the text-rendering stage rather than the complete IIMT task. These results establish flow-based editing as a strong, fully training-free baseline for IIMT.