MiniMax H3 Extender Multi-Clip ComfyUI Workflow (1 reference image, 3 connected clips)
======================================================================================

Article: https://freakyjolly.com/minimax-h3-extender-comfyui-multi-clip-workflow/

What's inside:
  - minimax-h3-extender-multi-clip.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):
  - ema_vae_fp16.safetensors
      folder: ComfyUI/models/SEEDVR2/
      download: https://huggingface.co/numz/SeedVR2_comfyUI/resolve/main/ema_vae_fp16.safetensors
  - minimax_h3_audio_vae_fp32.safetensors
      folder: ComfyUI/models/vae/
      download: https://huggingface.co/Comfy-Org/MiniMax-H3/resolve/main/vae/minimax_h3_audio_vae_fp32.safetensors
  - minimax_h3_fl2v_turbo_4step_v1.3_768p_comfyui_bf16.safetensors
      folder: ComfyUI/models/loras/
      download: https://huggingface.co/lightx2v/Minimax-h3-Turbo/resolve/main/minimax_h3_fl2v_turbo_4step_v1.3_768p_comfyui_bf16.safetensors
  - 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_ref2v_turbo_4step_v1.0_768p_comfyui_bf16.safetensors
      folder: ComfyUI/models/loras/
      download: https://huggingface.co/lightx2v/Minimax-h3-Turbo/resolve/main/minimax_h3_ref2v_turbo_4step_v1.0_768p_comfyui_bf16.safetensors
  - minimax_h3_ref2va_pruned_int8_convrot.safetensors
      folder: ComfyUI/models/diffusion_models/
      download: https://huggingface.co/Comfy-Org/MiniMax-H3/resolve/main/diffusion_models/minimax_h3_ref2va_pruned_int8_convrot.safetensors
  - minimax_h3_video_vae_int8_convrot.safetensors
      folder: ComfyUI/models/vae/
      download: https://huggingface.co/Comfy-Org/MiniMax-H3/resolve/main/vae/minimax_h3_video_vae_int8_convrot.safetensors
  - qwen3vl_32b_minimax_h3_int8_convrot.safetensors
      folder: ComfyUI/models/text_encoders/
      download: https://huggingface.co/Comfy-Org/MiniMax-H3/resolve/main/text_encoders/qwen3vl_32b_minimax_h3_int8_convrot.safetensors
  - seedvr2_ema_3b_fp8_e4m3fn.safetensors
      folder: ComfyUI/models/SEEDVR2/
      download: https://huggingface.co/numz/SeedVR2_comfyUI/resolve/main/seedvr2_ema_3b_fp8_e4m3fn.safetensors

Custom nodes:
  - ComfyUI-VideoHelperSuite (Video Combine): https://github.com/Kosinkadink/ComfyUI-VideoHelperSuite  (ComfyUI Manager > Install Missing Custom Nodes, or git clone into ComfyUI/custom_nodes/)
  - ComfyUI-SeedVR2_VideoUpscaler: https://github.com/numz/ComfyUI-SeedVR2_VideoUpscaler  (ComfyUI Manager > Install Missing Custom Nodes, or git clone into ComfyUI/custom_nodes/)
  - ComfyUI_MiniMax_H3_Extender: https://github.com/tritant/ComfyUI_MiniMax_H3_Extender  (ComfyUI Manager > Install Missing Custom Nodes, or git clone into ComfyUI/custom_nodes/)

How to use:
  1. Install the custom nodes above and restart ComfyUI.
  2. Download the model files into the folders listed.
  3. Drag minimax-h3-extender-multi-clip.json onto the canvas.
  4. Pick your reference image, edit the three clip prompts and queue.

Notes:
  - This is the same JSON that is shown in the article, packaged as a file.
  - Based on the official example workflow by tritant (Apache 2.0): https://github.com/tritant/ComfyUI_MiniMax_H3_Extender
  - SeedVR2 model files go in ComfyUI/models/SEEDVR2/ (the SeedVR2_VideoUpscaler default folder).

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