发表机构
Zhejiang University; Nanjing University（浙江大学; 南京大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
Paint-Anything通过共享十六进制提示接口和对象级颜色监督，实现了图像生成与编辑的任意颜色控制，并在ACBench基准上显著提升颜色保真度。
AI 中文摘要
专业设计需要任意颜色控制：即能够以任意24位十六进制值指定图像生成和编辑中对象的目标颜色。先前的工作已经探索了颜色生成、编辑和着色，但往往依赖于专用的颜色表示或专门的推理流程。大语言模型的进展提供了一个更简单的起点：即使是紧凑的模型也能将十六进制值与颜色语义关联起来。我们提出了Paint-Anything，它通过对象级颜色监督学习一个用于生成和编辑的共享十六进制提示接口。我们开发了一个数据流水线，通过对象定位、感知颜色标注和编辑对合成，从真实图像构建Paint-500K数据集。由于阴影使得真实图像标签仅能近似颜色，我们通过纯色锚点来补充这种监督，这些锚点的像素与其配对的十六进制值完全匹配。这些锚点仅在高噪声时间步使用，将低噪声训练留给自然图像。我们进一步引入了任意颜色基准（ACBench），包括ACBench-T2I和ACBench-Edit，以衡量两个任务中的对象级十六进制颜色保真度。在FLUX.2-4B上，相对于基础模型，Paint-Anything将ACBench-T2I和ACBench-Edit分数分别提高了85.3%和28.3%，消融实验支持了训练方案。它还在所比较的方法中取得了最高的平均CompColor分数。
英文摘要
Professional design requires any-color control: the ability to specify an object's target color with any 24-bit hex value for image generation and editing. Prior work has explored color generation, editing, and colorization, but often relies on dedicated color representations or specialized inference procedures. Advances in large language models offer a simpler starting point: even compact models can associate hex values with color semantics. We present Paint-Anything, which learns a shared hex-prompt interface for generation and editing through object-level color supervision. We develop a data pipeline that constructs Paint-500K from real images through object grounding, perceptual color labeling, and editing-pair synthesis. Since shadows make real-image labels only approximate colors, we complement this supervision with pure-color anchors whose pixels exactly match their paired hex values. These anchors are used only at high-noise timesteps, leaving low-noise training to natural images. We further introduce Any Color Benchmark (ACBench), comprising ACBench-T2I and ACBench-Edit, to measure object-level hex color fidelity across both tasks. On FLUX.2-4B, Paint-Anything improves ACBench-T2I and ACBench-Edit scores by 85.3% and 28.3%, respectively, relative to the base model, with ablations supporting the training recipe. It also achieves the highest average CompColor score among the compared methods.
Comments29 pages, Seed Technical Report. HTML compatibility fixes; scientific content unchanged
