Polaris: 将指令引导的图像生成扩展到数百万个性化风格需求
Polaris: Scaling Up Instruction-Guided Image Generation Towards Millions of Personalized Style Needs
AI总结：
提出Polaris智能检索框架，通过索引和检索超过6500个检查点和75000个适配器，自动选择和集成最相关的模型组件，实现无需额外训练的可扩展、可控且对齐的指令驱动图像生成。
摘要：
用户越来越期望图像生成模型能够快速适应高度多样化和个性化的需求，例如生成具有独特风格或特征的图像。传统方法依赖于微调，成本高昂且难以扩展。为了应对这些限制，社区积累了一个不断增长的微调模块和适配器库，其中每个组件针对特定的生成需求，并共同作为处理新需求的基础。这自然引出一个问题：与其重复训练新模型，我们能否系统地利用这个不断扩展的生态系统来更好地满足用户指令？为此，我们提出了Polaris，一个智能检索框架，根据用户的指令自动从模型库中选择和集成合适的模型。关键见解是，利用如此庞大和异构的库不仅需要在数千个候选中找到最相关的模块，还需要将它们有效地对齐以进行指令驱动的生成和编辑。Polaris通过索引超过6500个检查点和75000个适配器，并根据用户的输入和指令检索最相关的组件来解决这一挑战。通过这种方式，它提供了可扩展、可控且良好对齐的生成——无需任何额外训练。
英文摘要：
Users increasingly expect image generation models to quickly adapt to highly diverse and personalized requirements, such as producing images with distinctive styles or characteristics. Traditional approaches rely on fine-tuning, which is costly and difficult to scale. To cope with these limitations, the community has accumulated a growing library of fine-tuned modules and adapters, where each component targets specific generation needs and collectively serves as a foundation for handling new demands. This naturally raises a question: instead of repeatedly training new models, can we systematically exploit this expanding ecosystem to better fulfill user instructions? To this end, we present Polaris, an intelligent retrieval framework that automatically selects and integrates suitable models from the model library based on a user's instructions. The key insight is that harnessing such a massive and heterogeneous pool requires not only finding the most relevant modules among thousands of candidates, but also aligning them effectively for instruction-driven generation and editing. Polaris addresses this challenge by indexing over 6,500 checkpoints and 75,000 adapters, and retrieving the most relevant components given a user's input and instruction. In doing so, it delivers scalable, controllable, and well-aligned generation -- without any additional training.
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。
