DiffSynth-Studio/ImagePulseV2-TextImage-MultiResolution

ImagePulseV2数据集是为训练Diffusion Templates系列模型而构建的集合，包含多个子集。这些子集是通过Z-Image-Turbo、Qwen-Image和Qwen-Image-Edit等模型基于从DiffusionDB随机采样的提示生成的。数据集旨在支持多分辨率图像生成任务，并提供了丰富的示例和资源链接。The ImagePulseV2 dataset is a collection constructed for training the Diffusion Templates series of models. It consists of multiple subsets generated using models such as Z-Image-Turbo, Qwen-Image, and Qwen-Image-Edit, based on prompts randomly sampled from DiffusionDB. The dataset is designed to support multi-resolution image generation tasks and provides extensive examples and resource links.