DEDUPED Hot AI repos, turned into use cases Get 5 a day

How to pick the right face in a multi-person video with Comfy UI H3 Face Refine

Choose the subject per shot by eye so the tracker stays on the right person across hard cuts.

  • Content
  • Intermediate
  • 2 hours
  • From the README
  • Any agent

Authorization notice. Comfy UI H3 Face Refine is dual-use. Only use it on software, sites and systems you own or have explicit permission to test.

Who it is forAn editor with a clip showing several people, where the tracker might follow someone other than the intended subject.

The problemA hard cut renumbers every face, and with several people in shot the tracker can settle on the wrong face.

The outcomeA subject chosen once per shot before the graph runs, so the crop follows the intended person through the whole clip.

What you need first

  • ComfyUI with MiniMax H3 support (H3 nodes are core in comfy_extras/nodes_minimax_h3.py)
  • A face detector such as face_yolov8m.pt in models/ultralytics/bbox/, which you must supply yourself
  • MiniMax H3 diffusion model, Qwen3-VL text encoder, and the H3 video and audio VAEs in their ComfyUI model folders
  • Git, to clone the pack into ComfyUI/custom_nodes/
  • ComfyUI-VideoHelperSuite if you want to save the output video with VHS_VideoCombine

Steps

  1. Run git clone https://github.com/Carasibana/ComfyUI-H3-FaceRefine.git inside ComfyUI/custom_nodes/.
  2. Restart ComfyUI and add the H3 Load Video + Face Select node to your graph.
  3. Open Pick faces and choose the subject for each shot.
  4. Connect the face_pick output to H3 Face Track + Crop and keep cut_detection set to auto (pyscenedetect).
  5. Run the graph and read the report to confirm each shot used the face you picked.

Prompt for your agent

Using the repo Carasibana/ComfyUI-H3-FaceRefine, set up the H3 Load Video + Face Select node for <video path> so the subject is chosen per shot. Return the list of shots and the chosen face for each, and verify that every shot has a subject assigned.

Caveat. Cut detection depends on PySceneDetect, and if it fails to import the video is treated as a single shot.

Share: X LinkedIn Hacker News Email Copy link

Disclaimer

Deduped lists open-source repositories that belong to other people. We do not own, maintain, audit, or vouch for any of them, and a repo appearing here is not an endorsement or a safety check. The use cases, steps, and prompts are written by AI and may be incomplete, outdated, or just wrong. Where a use case is marked "Seen in the wild", we link to public posts where someone described something similar, but we have not verified those posts and the use case itself is still our AI's own write-up. Use all of this at your own risk. Only run code, commands, or agents on systems and accounts you are authorized to use, and read the code and every command before you run it, especially anything that touches credentials, files, or the network. Nothing here is professional, security, legal, or financial advice. All trademarks and project names belong to their respective owners, and their use here does not imply affiliation. Content is provided as is, without warranties of any kind. Found a mistake, a safety problem, or something you want removed? Email [email protected] and we will look at it promptly. Full disclaimer page