ZhengmingYu/DMAD
text-to-video model by ZhengmingYu
From the publisher
Model card & documentation
Source previewRead the publisher’s intended use, setup instructions, evaluations and limitations. The original model card is the source of truth.
[](https://yzmblog.github.io/projects/DMAD/) [](https://arxiv.org/abs/2610.02188) [](https://github.com/Yzmblog/DMAD) [](https://modelscope.ai/models/ZhengmingYu-Community/DMAD) [](https://modelscope.cn/models/ZhengmingYu-Community/DMAD) [](https://www.youtube.com/watch?v=cOCUCYZzAtE) Zhengming Yu1,2, Junkun Yuan2, Haotian Yang2, Gordon Guocheng Qian2, Yizhi Wang2, Angtian Wang2, Yiding Yang2, Bo Liu2, Xin Li1, Wenping Wang1, Chongyang Ma2 1Texas A&M University, 2ByteDance This repository holds the DMAD students of the paper: 4-step students of MiniMax-H3 (33B, text-to-audio-video) and of Wan2.1-T2V (1.3B and 14B), 4- and 1-step students of SDXL, and 1-step students of the EDM ImageNet-64 teacher. The inference and training code is in the code repository (train/h3, train/wan, train/image). it brings a clear step up in audio-video quality over our 4-step students. Ships with a ComfyUI-layout LoRA: drop it into the 8-step workflow. Feel free to try it out! 🎛️ Wan2.1-14B teacher samples with their real-video latents), so train/wan can start training right away 🤗 --low-vram in the code repository now makes 5 s videos in under 7 GiB of GPU memory and 15 s videos in 12…
Read the full model card ↗ · Preview checked 2026-11-16T20:03:59.802Z
Inside the original model card — Document outline
- DMAD: Distribution Matching as Adversarial Distillation for Fast Visual Generation
- 4-step & 8-step MiniMax-H3 students for joint audio-video generation
- Updates
- MiniMax-H3 (text-to-audio-video)
- ComfyUI
- Ready-to-run workflows (8 GB GPU and up)
- Wan2.1 (text-to-video)
- SDXL (text-to-image)
- ImageNet-64 (class-conditional)
- Citation
- License
Headings are captured from the source. Links open the publisher’s document, not a locally hosted copy.
Links from the model card
References supplied by the publisher, not independently verified endorsements. Check the destination before downloading files or entering credentials.
Documentation belongs to its respective authors. Reported project/model license: other. A listing is not a grant of reuse or training rights. Confirm the document’s own terms at the source.
Model overview
ZhengmingYu/DMAD is a text-to-video model repository published by ZhengmingYu on Hugging Face. The source reports the minimax-h3 library.
This page summarizes Hub metadata. For intended use, training data, evaluation results and limitations, consult the original model card.
Model facts
- Task
- text-to-video
- Library
- minimax-h3
- Recent downloads (30 days)
- 91,251
- Cumulative likes
- 197
- Hugging Face trending score
- 7
- Reported safetensors parameters
- Not reported
- Architecture
- Not reported
- License
- other
- Access
- Not gated by Hugging Face
- Created
- 2026-10-02T00:48:03.000Z
- Last modified
- 2026-10-30T17:49:05.000Z
Compatibility and lineage
Language coverage was not reported.
Reported base models: MiniMaxAI/MiniMax-H3
Parameter count is not a RAM/VRAM requirement. Check precision, quantization, context length and runtime compatibility in the model card; no hardware or API-cost claim is inferred here.
Use and evaluate
Check license terms and access requirements first. Review the model card’s documented loading instructions, evaluations and safety limitations. Benchmark scores are not imported by this directory, and popularity is not an accuracy ranking.
No model weights are downloaded or executed by AltAPIs. Never enable remote model code without reviewing it.
Source and freshness
Source: Hugging Face Hub. Metadata observed 2026-11-20T07:03:16.512Z. Daily imports are snapshots, not real-time monitoring.
Popularity and source listings do not establish security, suitability, licensing rights or benchmark performance.
Related models
QuantStack/Wan2.2-T2V-A14B-GGUF
QuantStack/Wan2.2-TI2V-5B-GGUF