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。

The OpenBrush Monet dataset is a curated subset of OpenBrush-75K, specifically containing all works of Claude Monet, totaling 1,334 images. These works are sourced from public domain art collections, covering Monet's classic Impressionist themes such as haystacks, water lilies, Rouen Cathedral, and Giverny garden scenes. The dataset adopts structured visual language model (VLM) descriptions generated by Qwen3-VL-30B-A3B, with each image providing detailed description fields including tags, themes, actions, settings, moods, styles, lighting, colors, composition, and complete descriptive text. The dataset is licensed under MIT, applicable to tasks such as image-to-text, text-to-image, and image classification, aiming to support research and applications of art analysis and generative models.