bytedance-research/UNO-1M

UNO-1M是一个大型数据集（约100万对图像），通过引入UNO论文中提出的上下文生成管道构建而成。该数据集的优势包括高度多样化的类别（超过365个类别）、高分辨率图像（约为1024x1024）、可变的分辨率（不同的宽高比）、高质量的图像（由最先进的文本到图像模型生成）和高度的主题一致性（通过VLM-filter CoT筛选）。您可以在这个数据集上训练以重现UNO模型或构建您自己的最先进主题驱动模型。

UNO-1M is a large dataset (~1M paired images) constructed by the in-context generation pipeline introduced in the UNO paper. Its advantages include highly diverse categories (>365 categories), high-resolution images (around 1024x1024), variable resolutions (different aspect ratios), high-quality images (produced by state-of-the-art text-to-image models), and high subject consistency (filtered by VLM-filter CoT). You can train on this dataset to reproduce the UNO model or build your own state-of-the-art subject-driven model.