The preprocessed training data of the DMAD 4-step students of MiniMax-H3 (text-to-audio-video), from the paper DMAD: Distribution Matching as Adversarial Distillation for Fast Visual Generation. The training code is in train/h3 of the DMAD repository; the released students are at ZhengmingYu/DMAD. Everything here is what train/h3/scripts/preparedata.sh produces from UltraVideo (short.csv and the clipsshort1920 clips) and the MiniMax-H3 base model, so training can start without the ~1 GPU-week of preprocessing. No video or audio is stored: the clips are kept only as MiniMax-H3 VAE latents, the captions as text-encoder outputs (the captions themselves are included as text). 303 GB, 59,818…
Independent publisher
Zhengming
ZhengmingYu
Models in Library0
Datasets in Library1
Models on Hugging Face2
Followers10
Compare the published evidence
This profile connects the 1 model and dataset record shown below to their upstream cards and sources. The library counts describe SAVRN's coverage, rather than this publisher's entire output.
Published tasks: Text to video.
Reported licenses: other. Open a record to review its specific license and conditions.
Compare model specifications, source dates, and hardware estimates on the individual records. Publisher identity verification is separate from a model's quality, deployment readiness, or suitability for your work.