ComfyUI zero to your first H3 video with audio — MiniMax H3 tutorial
Start with a clean ComfyUI setup, place all five model files correctly, and render a playable T2VA MP4 with picture and synchronized audio.
Audience: First-time NVIDIA users who want a guided local MiniMax H3 run instead of reverse-engineering a node graph.
Hardware: Windows or Linux with an NVIDIA GPU and ample disk space. Start at the template preview size when VRAM is limited instead of jumping to 1344×768.
Prerequisites
- Current NVIDIA drivers and ComfyUI 0.30.0 or newer
- Python 3.13, with Python 3.12 as the fallback for custom-node compatibility
- Access to the Comfy-Org/MiniMax-H3 files on Hugging Face
- One short prompt that clearly states scene, subject action, camera, dialogue, or ambience
Steps
- Install or update ComfyUI. Use the official Desktop or Portable build on Windows, or a separate Python environment for a manual/Linux install. Confirm the UI opens without a CUDA initialization error.
- Open Template Library → Video → MiniMax H3 T2V. Use the model-download popup when available; preserve the exact filenames for manual downloads.
- Place minimax_h3_fl2va_pruned_int8_convrot.safetensors in ComfyUI/models/diffusion_models/. T2V and I2V use FL2VA; only R2V switches to Ref2VA weights.
- Place qwen3vl_32b_minimax_h3_nvfp4_awq.safetensors in ComfyUI/models/text_encoders/. Put both the video and audio VAEs in ComfyUI/models/vae/. A silent render is not a successful audio-video setup.
- Place minimax_h3_fl2v_turbo_8step_v1.0_comfyui_bf16.safetensors in ComfyUI/models/loras/. It powers the optional turbo_mode; keep Turbo off and use the default 20 steps for the first baseline.
- Restart ComfyUI or refresh the model list. Confirm every Loader finds the diffusion model, text encoder, both VAEs, and LoRA. Fix null, undefined, or red nodes before queuing.
- Render a short clip at the template preview size, 16:9, and multiple=32. Describe the scene first, then shots and camera, then dialogue, effects, or music. Add no custom nodes or stacked accelerators yet.
- Queue the graph and wait through VAE decode and MP4 assembly. Open the file and verify picture, duration, audio, and event or lip synchronization. Save this untouched graph as the baseline.
- After the baseline passes, move to the native 1344×768 canvas or 0.98 MP in Resolution Selector. Do not choose 1.0 MP because it produces 1376×768, above the model area cap.
- For first/last frames, connect first_frame or last_frame in the same FL2VA graph. For identity, style, motion, camera, or voice references, open the R2V template and switch to Ref2VA weights instead of mixing model families.
Commands
python --version
python -m pip install -r requirements.txt
python main.py
ComfyUI/models/diffusion_models/minimax_h3_fl2va_pruned_int8_convrot.safetensors
ComfyUI/models/text_encoders/qwen3vl_32b_minimax_h3_nvfp4_awq.safetensors
ComfyUI/models/vae/minimax_h3_video_vae_fp16.safetensors
ComfyUI/models/vae/minimax_h3_audio_vae_fp32.safetensors
ComfyUI/models/loras/minimax_h3_fl2v_turbo_8step_v1.0_comfyui_bf16.safetensors
Caveats
- Model files are large; storage, interrupted downloads, and wrong folders are the most common first-run failures.
- T2V and I2V use FL2VA while R2V uses Ref2VA; mixing weight families causes missing models or bad output.
- H3 resolutions must be multiples of 32, and higher resolution or duration sharply increases VRAM and wait time.
- Templates and filenames evolve; verify the current reference before following an old screenshot.
View original source · ComfyUI · 2026-08-23