MiniMax H3 Video Section Editor ComfyUI Workflow (Frame Infill, optional mask)
==============================================================================

Article: https://freakyjolly.com/best-minimax-h3-video-section-editor-comfyui/

What's inside:
  - MiniMax_H3_Video_Section_Editor_Optional_Mask.json: ComfyUI workflow (UI format). Drag it onto the ComfyUI canvas or use Workflow > Open.

Required models (download each file and put it in the folder shown):
  - minimax_h3_fl2va_pruned_int8_convrot.safetensors
      folder: ComfyUI/models/diffusion_models/
      download: https://huggingface.co/Comfy-Org/MiniMax-H3/resolve/main/diffusion_models/minimax_h3_fl2va_pruned_int8_convrot.safetensors
  - minimax_h3_video_vae_fp16.safetensors
      folder: ComfyUI/models/vae/
      download: https://huggingface.co/Comfy-Org/MiniMax-H3/resolve/main/vae/minimax_h3_video_vae_fp16.safetensors
  - qwen3vl_32b_minimax_h3_nvfp4_awq.safetensors
      folder: ComfyUI/models/text_encoders/
      download: https://huggingface.co/Comfy-Org/MiniMax-H3/resolve/main/text_encoders/qwen3vl_32b_minimax_h3_nvfp4_awq.safetensors

Custom nodes:
  - ComfyUI-MiniMaxH3FrameInfill: https://github.com/red-polo/ComfyUI-MiniMaxH3FrameInfill  (ComfyUI Manager > Install Missing Custom Nodes, or git clone into ComfyUI/custom_nodes/)

How to use:
  1. Install ComfyUI-MiniMaxH3FrameInfill and restart ComfyUI.
  2. Download the model files into the folders listed.
  3. Drag MiniMax_H3_Video_Section_Editor_Optional_Mask.json onto the canvas.
  4. Load your video, set the first and last frame of the section to re-generate, optionally connect a mask, edit the prompt and queue. The original audio is kept.

Notes:
  - Fixed in this version: the two Math Expression nodes now use the current ComfyUI input names (values.a / values.b), so the frame math connects on current ComfyUI builds.

Model weights are not included. Each model keeps its own licence; check the model page before commercial use.
Workflow shared by FreakyJolly.com.
