ComposeMe：用于可控人体图像生成的属性特定图像提示
ComposeMe: Attribute-Specific Image Prompts for Controllable Human Image Generation
AI总结：
本文提出ComposeMe，一种属性特定图像提示方法，通过编码不同参考图像为属性标记并注入扩散模型，实现对人体发型、服装和身份的组合解耦控制，达到最先进性能。
摘要：
在个性化文本到图像合成中，生成具有细粒度控制（如发型和服装等属性）的高保真人体图像仍然是一个核心挑战。尽管先前的方法强调从参考图像中保持身份，但它们缺乏模块化，无法对特定视觉属性提供解耦控制。我们提出了一种新的属性特定图像提示范式，其中使用不同的参考图像集来引导人体外观的各个方面的生成，例如头发、服装和身份。我们的方法将这些输入编码为属性特定的标记，并将其注入到预训练的文本到图像扩散模型中。这使得能够对多个视觉因素进行组合和解耦控制，即使在单个图像中的多个人物之间也能实现。为了促进自然的组合和稳健的解耦，我们策划了一个跨参考训练数据集，其中包含不同姿势和表情的主体，并提出了一种多属性跨参考训练策略，该策略鼓励模型从不一致的属性输入中生成忠实的输出，同时遵循身份和文本条件。大量实验表明，我们的方法在准确遵循视觉和文本提示方面达到了最先进的性能。我们的框架通过将视觉提示与文本驱动生成相结合，为更可配置的人体图像合成铺平了道路。网页可在以下网址获取：https://snap-research.github.io/composeme/。
英文摘要：
Generating high-fidelity images of humans with fine-grained control over attributes such as hairstyle and clothing remains a core challenge in personalized text-to-image synthesis. While prior methods emphasize identity preservation from a reference image, they lack modularity and fail to provide disentangled control over specific visual attributes. We introduce a new paradigm for attribute-specific image prompting, in which distinct sets of reference images are used to guide the generation of individual aspects of human appearance, such as hair, clothing, and identity. Our method encodes these inputs into attribute-specific tokens, which are injected into a pre-trained text-to-image diffusion model. This enables compositional and disentangled control over multiple visual factors, even across multiple people within a single image. To promote natural composition and robust disentanglement, we curate a cross-reference training dataset featuring subjects in diverse poses and expressions, and propose a multi-attribute cross-reference training strategy that encourages the model to generate faithful outputs from misaligned attribute inputs while adhering to both identity and textual conditioning. Extensive experiments show that our method achieves state-of-the-art performance in accurately following both visual and textual prompts. Our framework paves the way for more configurable human image synthesis by combining visual prompting with text-driven generation. Webpage is available at: https://snap-research.github.io/composeme/.
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。
