Skip to content
BackComfyUI Model Pack Detail
Model Info
TypeModel Pack
License minimax-h3-community
Files1
RepositoryHuggingFace ↗

TaoMate-HD-preview

Note: All model files below must be downloaded via the LM Downloader client. If you do not have the client, Download >>>

TaoMate-HD-preview is a LoRA adapter for MiniMax H3. It runs locally in ComfyUI. You can use one portrait photo plus audio to generate stable lip-sync digital human videos for speech or singing. It officially supports hour-long long-form video via chunked continuation, ideal for talking-head clips and AI singing avatar videos. This model requires powerful hardware. Our test setup was RTX 5060 Ti with 16GB VRAM and 64GB RAM, taking around 28 minutes for a 30-second video. Larger VRAM is needed if you want to generate videos longer than one minute in a single run. Developed by Alibaba TaoLive AIGC team, built upon MiniMax H3.

NameSizeTarget Dir
adapter_model.safetensors2.48 GBloras