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

What you can do with Comfy UI H3 Face Refine

A ComfyUI custom node set that tracks small faces in MiniMax H3 video, crops to each face, refines it with H3, and composites it back into the clip.

Trended earlier

Carasibana/ComfyUI-H3-FaceRefine on GitHub

Third-party repos we don't own or vouch for. AI-generated use cases can be wrong: review everything and run at your own risk.

Authorization notice. This tool is dual-use. Only use it on software, sites and systems you own or have explicit permission to test, and follow the relevant licenses and terms of service.

What do you want to do?

3 use cases

  • Refine small faces in a MiniMax H3 video

    Track each face per frame, crop to it, re-generate it with H3, and stitch it back into the clip.

    View prompt
    Using the repo Carasibana/ComfyUI-H3-FaceRefine, build a ComfyUI graph that refines the small face of <subject description> in <video path> and writes a composited video to <output path>. Verify that the tracker report shows the subject found on most frames and lists any lost frame ranges.

  • Pick the right face in a multi-person video

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

    View prompt
    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.

  • Check the face crop before a full H3 render

    Use preview output to confirm the crop sits still on the subject before spending a full H3 render.

    View prompt
    Using the repo Carasibana/ComfyUI-H3-FaceRefine, run the H3 Face Track + Crop preview on <video path> without starting a full H3 render. Report the face= value, the lost ranges, and any frames drawn red, and verify that the subject is found on the frames you expect.

How to use Comfy UI H3 Face Refine

  1. Check you have what it needs: 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.
  2. Open Carasibana/ComfyUI-H3-FaceRefine on GitHub and read the README and license.
  3. Run git clone https://github.com/Carasibana/ComfyUI-H3-FaceRefine.git inside ComfyUI/custom_nodes/.
  4. Restart ComfyUI and confirm the nodes appear under MiniMax H3/Face Refine.
  5. Place face_yolov8m.pt in models/ultralytics/bbox/, and the H3 diffusion model, Qwen3-VL text encoder, and VAEs in their folders.
  6. Load your clip, choose the subject with the select setting, and connect it to H3 Face Track + Crop.

These steps come from our top use case, Refine small faces in a MiniMax H3 video, which also has a copy-paste agent prompt.

Comfy UI H3 Face Refine alternatives · Best AI repos for Content

About this repo

Requirements

  • 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
Maintain Comfy UI H3 Face Refine? Add the Featured on Deduped badge

Paste this into your README:

[![Featured on Deduped](https://dedupedai.com/badge/carasibana-comfyui-h3-facerefine.svg)](https://dedupedai.com/use-cases/carasibana-comfyui-h3-facerefine/?ref=badge)

More badge styles and HTML

Questions about Comfy UI H3 Face Refine

What is Comfy UI H3 Face Refine?

A ComfyUI custom node set that tracks small faces in MiniMax H3 video, crops to each face, refines it with H3, and composites it back into the clip. It is an open-source project on GitHub: https://github.com/Carasibana/ComfyUI-H3-FaceRefine.

Who is Comfy UI H3 Face Refine for?

Video creators and editors who run MiniMax H3 inside ComfyUI and need faces that look better when the head is small in frame.

What can I do with Comfy UI H3 Face Refine?

3 use cases so far, for example: Refine small faces in a MiniMax H3 video; Pick the right face in a multi-person video; Check the face crop before a full H3 render. Each has steps and a copy-paste agent prompt.

What do I need to run Comfy UI H3 Face Refine?

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/.

What are alternatives to Comfy UI H3 Face Refine?

Other hot AI repos in Content: Voice Studio, Anatomy, Comfy UI, Hyperframes, Earshot.

Is Comfy UI H3 Face Refine safe to run?

Deduped does not own, audit or vouch for it. Read the README and license, run it on your own systems first and review every command before you run it.