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

How to check the face crop before a full H3 render with Comfy UI H3 Face Refine

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

  • Content
  • Intermediate
  • 1 hour
  • 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 forA VFX artist or creator who wants to avoid wasting a long H3 render on a crop that wobbles or jumps to another person.

The problemA crop that moves or boils on a moving subject ruins the refined face, and a full render is expensive to repeat.

The outcomeA short check that shows whether the box holds still on the subject and which frames the subject was lost, before the full run.

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 open H3 Face Track + Crop with the preview output enabled.
  3. Check the preview for the crop staying steady on the subject, and note any frames drawn red.
  4. Read the lost line and the dropout runs in the report to see which frame ranges lost the subject.
  5. Use Preview coordinates to confirm where an X and Y value lands, then start the full render.

Prompt for your agent

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.

Caveat. Frames where the subject is lost are left unrefined and keep their original pixels, so a clean preview does not mean every frame was refined.

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