MUVideo

MUVideo Dataset This is the MUVideo dataset used to facilitate image to music generation, consisting of 13,203 music files with a total playtime of 36.72 hours generated using the MU-LLaMA and VideoMAE captioning models. This dataset is used to train the M2UGen model. The MUVideoInstructions.json file contains a list with each of the element having the following format: { "input_file": "1OhKgYcAujk.mp4", "output_file": "1OhKgYcAujk.mp3", "conversation": [ {… See the full description on the dataset page: https://huggingface.co/datasets/M2UGen/MUVideo.MU视频数据集系为促进图像至音乐生成而设计，包含13,203首音乐文件，总时长达36.72小时，由MU-LLaMA与VideoMAE字幕模型生成。该数据集旨在用于训练M2UGen模型。MUVideoInstructions.文件中列出了各项元素，每个元素均遵循以下格式： { "input_file": "1OhKgYcAujk.mp4", "output_file": "1OhKgYcAujk.mp3", "conversation": [ {…} ] } 请参阅数据集页面以获取完整描述：https://huggingface.co/datasets/M2UGen/MUVideo.