MiniMax-H3 TaoMate-HD-preview Audio Driven Avatar
Note: All model files and custom nodes below must be downloaded via the 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.
| Name | Size | Target Dir |
|---|
| ig_tiktok_aesthetic_h3_lora_v2_500.safetensors | 155.11 MB | loras |
| ig_tiktok_aesthetic_h3_lora_v1_500.safetensors | 310.17 MB | loras |
| Name | Size | Target Dir |
|---|
| qwen3vl_32b_minimax_h3_nvfp4_awq.safetensors | 15.69 GB | text_encoders |
| qwen3vl_32b_minimax_h3_int8_convrot.safetensors | 27.14 GB | text_encoders |
| qwen3vl_32b_minimax_h3_bf16.safetensors | 51.51 GB | text_encoders |
| Name | Size | Target Dir |
|---|
| minimax_h3_audio_vae_fp32.safetensors | 605.25 MB | vae |
| minimax_h3_video_vae_int8_convrot.safetensors | 2.81 GB | vae |
| minimax_h3_video_vae_fp16.safetensors | 5.21 GB | vae |
| Name | Size | Target Dir |
|---|
| adapter_model.safetensors | 2.48 GB | loras |
| Name | Size | Target Dir |
|---|
| minimax_h3_fl2v_turbo_4step_v1.0_768p_comfyui_bf16.safetensors | 1.96 GB | loras |
| minimax_h3_fl2v_turbo_4step_v1.1_768p_comfyui_bf16.safetensors | 1.96 GB | loras |
| minimax_h3_fl2v_turbo_4step_v1.2_768p_comfyui_bf16.safetensors | 1.96 GB | loras |
| minimax_h3_fl2v_turbo_8step_v1.0_768p_comfyui_bf16.safetensors | 1.96 GB | loras |
| minimax_h3_fl2v_turbo_8step_v1.0_comfyui_bf16.safetensors | 1.96 GB | loras |
| minimax_h3_ref2v_turbo_8step_v1.0_768p_comfyui_bf16.safetensors | 1.96 GB | loras |
| Name | Size | Target Dir |
|---|
| Minimax-h3_Singularity_ref2va_v1.3_Pruned_w4a8.safetensors | 11.77 GB | diffusion_models |
| Minimax-h3_Singularity_ref2va_Pruned_v1.3_int8.safetensors | 20.97 GB | diffusion_models |
| Minimax-h3_Singularity_ref2va_v2_pruned_int8.safetensors | 20.97 GB | diffusion_models |
| Minimax-h3_Singularity_ref2va_v1.3_int8.safetensors | 34 GB | diffusion_models |
| Minimax-h3_Singularity_ref2va_v2_int8.safetensors | 34 GB | diffusion_models |
| Minimax-h3_Singularity_ref2va_v2_bf16.safetensors | 66.28 GB | diffusion_models |
| Name | Size | Target Dir |
|---|
| minimax_h3_live_wallpaper_v1.0_ref2va_r32.safetensors | 310.17 MB | loras |
| minimax_h3_head_swap_v1.0_r32.safetensors | 310.18 MB | loras |
| minimax_h3_live_wallpaper_v1.0_ref2va_r64.safetensors | 620.29 MB | loras |
| minimax_h3_style_transfer_v1.0_r64.safetensors | 620.31 MB | loras |
| minimax_h3_lms_v1.0_r64.safetensors | 1.24 GB | loras |
| minimax_h3_vfx_edit_v1.0_r128_ffp.safetensors | 1.24 GB | loras |
| minimax_h3_vfx_edit_v1.0_r128.safetensors | 1.24 GB | loras |
| Name | Size | Target Dir |
|---|
| relayvsr_flash_vae_x2_fp32.safetensors | 127.76 MB | vae |
| relayvsr_flash_vae_x4_fp32.safetensors | 127.76 MB | vae |
| Name | Size | Target Dir |
|---|
| relayvsr_x2_lightx2v_int8_convrot.safetensors | 5.16 GB | diffusion_models |
| relayvsr_x4_int8_convrot.safetensors | 5.16 GB | diffusion_models |
