DEDUPED Hot AI repos, turned into use cases Get 5 a day

What you can do with DMAD

DMAD is a Python repo with 4-step LoRA students of the MiniMax-H3 33B model that generate 1344x768 video with stereo audio from text prompts, plus inference, ComfyUI, and training code.

Trended earlier

Yzmblog/DMAD on GitHub

Third-party repos we don't own or vouch for. AI-generated use cases can be wrong: review everything and run at your own risk.

What do you want to do?

4 use cases

  • Generate a 4-step audio-video clip from a text prompt

    Run the DMAD 4-step LoRA on MiniMax-H3 to turn one text prompt into a 5.2 s video with stereo audio.

    View prompt
    In the Yzmblog/DMAD repo, set up the environment from the README, download the MiniMax-H3 components and the lora_critic checkpoint, then run inference.py with the prompt <your prompt> and --output-dir outputs/<name>. Expected output: an MP4 in outputs/<name>/ with H.264 video and AAC audio. Verify that the file plays and that settings.json exists in the same folder.

  • Make 5 s audio-video clips on an 8 GB consumer GPU

    Use the --low-vram path to run the DMAD students on an 8 GB GPU by streaming weights from the checkpoint files.

    View prompt
    In the Yzmblog/DMAD repo, run inference.py with --low-vram 8 and the lora_critic checkpoint on the prompt file <prompt_file>, writing to outputs/<name>. Expected output: 5 s MP4 clips with audio in the output folder. Verify that the run finished without an out-of-memory error and that settings.json lists the low-vram setting.

  • Render DMAD clips in ComfyUI with ready-made workflows

    Load the ComfyUI-layout DMAD LoRA and a ready-to-run workflow to make 4-step or 8-step clips with audio.

    View prompt
    In the Yzmblog/DMAD repo, open the ComfyUI workflow described in comfyui/README.md and load dmad_minimax_h3_4step_lora_critic_comfyui.safetensors with the lcm sampler and simple scheduler. Expected output: a 15 s video with audio for the prompt <your prompt>. Verify that the sampler and scheduler names match the README before running.

  • Retrain a DMAD student from the released training code

    Use the train folder and the published Wan2.1 training data to start a DMAD training run.

    View prompt
    In the Yzmblog/DMAD repo, read train/wan/README.md, download the DMAD-Wan-data dataset to data/wan, and start the training command from that README. Expected output: training logs for the Wan2.1 DMAD student. Verify that the dataset folder contains the 42,158 teacher samples the README lists before starting training.

How to use DMAD

  1. Check you have what it needs: A CUDA GPU: 80 GB for the default path, 8 GB and up with --low-vram; Python 3.12 with conda and PyTorch for CUDA 12.6; About 170 GB of free disk space for the MiniMax-H3 base components.
  2. Open Yzmblog/DMAD on GitHub and read the README and license.
  3. Run conda create -n dmad_h3 python=3.12 -y, then run conda activate dmad_h3.
  4. Install PyTorch with pip install torch==2.11.0 torchvision==0.26.0 torchaudio==2.11.0 --index-url https://download.pytorch.org/whl/cu126, then run pip install -r requirements.txt.
  5. Accept the MiniMax H3 Community License on Hugging Face, then run hf download MiniMaxAI/MiniMax-H3 --local-dir models/MiniMax-H3 --exclude "FL2VA/*" --exclude "Ref2VA/*" --exclude "transformer_ref/*". (inferred, check the README)
  6. Run hf download ZhengmingYu/DMAD --include "minimax_h3/*_critic.safetensors" --local-dir ckpt after running mkdir -p ckpt.

These steps come from our top use case, Generate a 4-step audio-video clip from a text prompt, which also has a copy-paste agent prompt.

DMAD alternatives · Best AI repos for Content

About this repo

  • Who it is forCreators, researchers, and developers with a capable NVIDIA GPU who want fast text-to-audio-video generation or want to reproduce or retrain DMAD students.
  • Why it is hot
  • LanguagePython
  • Sourcegithub.com/Yzmblog/DMAD · Back to Hot repos

Requirements

  • A CUDA GPU: 80 GB for the default path, 8 GB and up with --low-vram
  • Python 3.12 with conda and PyTorch for CUDA 12.6
  • About 170 GB of free disk space for the MiniMax-H3 base components
  • A Hugging Face account that has accepted the MiniMax H3 Community License
Maintain DMAD? Add the Featured on Deduped badge

Paste this into your README:

[![Featured on Deduped](https://dedupedai.com/badge/yzmblog-dmad.svg)](https://dedupedai.com/use-cases/yzmblog-dmad/?ref=badge)

More badge styles and HTML

Questions about DMAD

What is DMAD?

DMAD is a Python repo with 4-step LoRA students of the MiniMax-H3 33B model that generate 1344x768 video with stereo audio from text prompts, plus inference, ComfyUI, and training code. It is an open-source project on GitHub: https://github.com/Yzmblog/DMAD.

Who is DMAD for?

Creators, researchers, and developers with a capable NVIDIA GPU who want fast text-to-audio-video generation or want to reproduce or retrain DMAD students.

What can I do with DMAD?

4 use cases so far, for example: Generate a 4-step audio-video clip from a text prompt; Make 5 s audio-video clips on an 8 GB consumer GPU; Render DMAD clips in ComfyUI with ready-made workflows. Each has steps and a copy-paste agent prompt.

What do I need to run DMAD?

A CUDA GPU: 80 GB for the default path, 8 GB and up with --low-vram; Python 3.12 with conda and PyTorch for CUDA 12.6; About 170 GB of free disk space for the MiniMax-H3 base components; A Hugging Face account that has accepted the MiniMax H3 Community License.

What are alternatives to DMAD?

Other hot AI repos in Content: Voice Studio, Anatomy, Comfy UI, Hyperframes, Earshot.

Is DMAD safe to run?

Deduped does not own, audit or vouch for it. Read the README and license, run it on your own systems first and review every command before you run it.