jaddai/openbrush-monet

OpenBrush Monet数据集是OpenBrush-75K的一个精选子集，专门包含克劳德·莫奈的所有作品，共1,334张图像。这些作品来自公共领域艺术收藏，涵盖了莫奈的经典印象派主题，如干草堆、睡莲、鲁昂大教堂和吉维尼花园场景。数据集使用结构化视觉语言模型（VLM）描述，基于Qwen3-VL-30B-A3B生成，每个图像提供详细的描述字段，包括标签、主题、动作、设置、情绪、风格、照明、颜色和构图，以及完整的描述文本。数据集的许可证为MIT，适用于图像到文本、文本到图像和图像分类等任务，旨在支持艺术分析和生成模型的研究与应用。

OpenBrush Monet is a curated subset of OpenBrush-75K containing all Claude Monet works, with structured VLM captions. It includes 1,334 images of Monets canonical Impressionist paintings, such as haystacks, water lilies, Rouen cathedrals, and Giverny garden scenes. The dataset features detailed captions generated by the Qwen3-VL-30B-A3B model, organized into nine aspects: TAGS, SUBJECT, ACTION, SETTING, MOOD, STYLE, LIGHTING, COLOR, and COMPOSITION, along with a full caption. Licensed under MIT, it is derived from public domain art collections and is designed for tasks like image-to-text, text-to-image, and image-classification, supporting research in art analysis and generative models.