{
 "schema_version": 1,
 "generated": "2026-10-20",
 "id": "yzmblog-dmad--run-dmad-video-on-8-gb-gpu",
 "repo": "Yzmblog/DMAD",
 "repo_url": "https://github.com/Yzmblog/DMAD",
 "repo_slug": "yzmblog-dmad",
 "title": "Make 5 s audio-video clips on an 8 GB consumer GPU",
 "page_title": "How to make 5 s audio-video clips on an 8 GB consumer GPU with DMAD",
 "summary": "Use the --low-vram path to run the DMAD students on an 8 GB GPU by streaming weights from the checkpoint files.",
 "who": "A hobbyist or small studio with a consumer GPU of about 8 GB who cannot use the 80 GB default path.",
 "problem": "The default inference path needs an 80 GB GPU, which puts MiniMax-H3 out of reach on consumer hardware.",
 "outcome": "5 s videos with native stereo audio, made in under 7 GiB of GPU memory with the --low-vram path.",
 "steps": [
  "Complete the environment and checkpoint setup from the README, including the MiniMax-H3 download and the lora_critic checkpoint.",
  "Pick a prompt and write it to a text file, one prompt per line, for example `prompts/dmad_sweater.txt`.",
  "Run `python inference.py --model-dir models/MiniMax-H3 --lora ckpt/minimax_h3/dmad_minimax_h3_4step_lora_critic.safetensors --prompt-file prompts/dmad_sweater.txt --seed 42 --low-vram 8 --num-frames 124 --output-dir outputs/low_vram`. (inferred, check the README)",
  "Check the output folder for the MP4 files and the settings.json record."
 ],
 "agent_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.",
 "agents": [
  "any"
 ],
 "difficulty": "Advanced",
 "time": "3 hours",
 "basis": "readme",
 "caveat": "The README states the 8 GB path is bit-identical to larger-GPU runs for 5 s videos, but the run still depends on a large host disk for the model files and the first run is slow.",
 "category": "Content",
 "tags": [
  "Content"
 ],
 "lang": "python",
 "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"
 ],
 "risk": "none",
 "seen_in_the_wild": false,
 "mentioned_publicly": false,
 "risks": [],
 "best": false,
 "score": 0.9,
 "evidence": [],
 "url": "https://dedupedai.com/use-cases/yzmblog-dmad/run-dmad-video-on-8-gb-gpu/",
 "md": "https://dedupedai.com/use-cases/yzmblog-dmad/run-dmad-video-on-8-gb-gpu/index.md",
 "disclaimer": "Deduped lists open-source repositories that belong to other people. We do not own, maintain, audit, or vouch for any of them, and a repo appearing here is not an endorsement or a safety check. The use cases, steps, and prompts are written by AI and may be incomplete, outdated, or just wrong. Where a use case is marked \"Seen in the wild\", we link to public posts where someone described something similar, but we have not verified those posts and the use case itself is still our AI's own write-up. Use all of this at your own risk. Only run code, commands, or agents on systems and accounts you are authorized to use, and read the code and every command before you run it, especially anything that touches credentials, files, or the network. Nothing here is professional, security, legal, or financial advice. All trademarks and project names belong to their respective owners, and their use here does not imply affiliation. Content is provided as is, without warranties of any kind. Found a mistake, a safety problem, or something you want removed? Email hello@dedupedai.com and we will look at it promptly.",
 "api": "https://dedupedai.com/api/v1/usecases/yzmblog-dmad--run-dmad-video-on-8-gb-gpu.json",
 "api_version": "v1"
}