DiffSynth-Studio/ImagePulseV2-Edit-Pose

ImagePulseV2数据集是一个为训练Diffusion Templates系列模型而构建的自定义数据集。它包含多个子集，这些子集是使用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。数据集主要用于姿势调整任务，展示了编辑指令、输入图像和输出图像的对比。The ImagePulseV2 dataset is a custom-built dataset created 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 primarily used for pose adjustment tasks, showcasing comparisons between editing instructions, input images, and output images.