Premier：文本到图像生成中基于可学习用户嵌入的个性化偏好调制
Premier: Personalized Preference Modulation with Learnable User Embedding in Text-to-Image Generation
把用户偏好编码为可学习嵌入，并通过适配器与文本提示融合后调制扩散生成过程，为个性化文生图提供了一种无需 MLLM 推断提示的轻量条件控制路径；分散损失强制不同用户嵌入分离的思路也可迁移到多概念定制化生成。
原文依据 Premier represents each user's preference as a learnable embedding and introduces a preference adapter that fuses the user embedding with the text prompt.
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论文本到图像生成已取得快速进展，但仍难以捕捉细微的用户偏好。现有方法通常依赖多模态大语言模型推断用户偏好，但由此得到的提示或潜变量代码很少能忠实反映偏好，导致个性化效果欠佳。我们提出 Premier，一种用于个性化图像生成的新型偏好调制框架。Premier 将每个用户的偏好表示为一个可学习嵌入，并引入偏好适配器，将用户嵌入与文本提示融合。为实现准确且细粒度的偏好控制，融合后的偏好嵌入进一步用于调制生成过程。为增强个体偏好的区分度并改善输出与用户特定风格之间的对齐，我们引入分散损失，强制不同用户嵌入之间相互分离。当用户数据稀缺时，新用户被表示为训练期间学到的现有偏好嵌入的线性组合，从而实现有效泛化。实验表明，在相同历史长度下，Premier 优于先前方法，在偏好对齐上更强，并在文本一致性、ViPer 代理指标和专家评估上取得更优表现。
英文原文摘要 1294 字符
Text-to-image generation has advanced rapidly, yet it still struggles to capture the nuanced user preferences. Existing approaches typically rely on multimodal large language models to infer user preferences, but the derived prompts or latent codes rarely reflect them faithfully, leading to suboptimal personalization. We present Premier, a novel preference modulation framework for personalized image generation. Premier represents each user's preference as a learnable embedding and introduces a preference adapter that fuses the user embedding with the text prompt. To enable accurate and fine-grained preference control, the fused preference embedding is further used to modulate the generative process. To enhance the distinctness of individual preference and improve alignment between outputs and user-specific styles, we incorporate a dispersion loss that enforces separation among user embeddings. When user data are scarce, new users are represented as linear combinations of existing preference embeddings learned during training, enabling effective generalization. Experiments show that Premier outperforms prior methods under the same history length, achieving stronger preference alignment and superior performance on text consistency, ViPer proxy metrics, and expert evaluations.