kaupane/vintage-photography-captions

该数据集包含445,271张重新标注的复古照片，来源于vintage-photography-450k-high-quality-captions数据集。提供了高质量的双语（英文和中文）标注、美学评分和其他元数据，这些数据是通过Qwen2-VL模型生成的。每张照片包括原始图片URL、详细的中英文描述、美学质量评分、模式（RGB/灰度）和水印检测状态。描述内容强调主体、场景、光线、纹理和空间关系，适合复古摄影风格。数据集可用于训练文本到图像模型、微调视觉语言模型、分析复古摄影的美学质量分布等。

This dataset contains 445,271 recaptioned vintage photographs, derived from the vintage-photography-450k-high-quality-captions dataset. It provides high-quality bilingual (English and Chinese) captions, aesthetic scores, and other metadata generated using the Qwen2-VL model. Each entry includes the original image URL, detailed bilingual captions (Chinese and English), an aesthetic quality score, mode (RGB/Grayscale), and watermark detection status. The captions were generated to emphasize main subjects, scene, lighting, textures, and spatial relationships appropriate for vintage photography. The dataset can be used for training text-to-image models, fine-tuning vision-language models, analyzing aesthetic quality distributions in vintage photography, etc.