DMAD (4-step H3)
Type: RepoCategory: Generation
DMAD (4-step H3) is an open-source repo in our Generation category. Four-step MiniMax H3 text-to-audio-video distillation LoRAs with Diffusers and native ComfyUI weights, example workflows and training code. T2VA only (not Omni references); don't stack with other speed adapters.
Where it fits: ComfyUI, Open-weight video & audio models.
Listing isn’t endorsement. This is our summary of the project’s own docs. Check the licence and requirements at the source before you build on it.
Lab posts that cover DMAD (4-step H3)
Related Lab posts
- #OpenSourceHiggsfield: Comfy's $25K challenge and the first open rebuilds
- The top GitHub video repos right now, ranked by stars (Oct 2026)
- HyperFlow Infinity: an open agent loop that keeps generating video until you stop it
- PopTok: a fully local pipeline from one prompt to a lip-synced music video (ACE-Step, LTX-2.5, InfiniteTalk)
- Tencent Hy-Nomas: an open interactive video world model you steer as it renders
Similar skills & repos
- Comfield · Repo, Generation
- FreeVideo · ComfyUI, Generation
- SolarRenderer · Repo, Generation
- HyperFlow Infinity · Repo, Generation
- Hy-Nomas · Repo, Generation
- Node Banana · Repo, Generation