Carasibana / ComfyUI-H3-FaceRefine
Refine and improve the quality of small faces in MiniMax H3 video. Per-frame face tracking, crop, refine with H3, stitch back.
Why this job: says: comfyui; topics: comfyui, diffusion-models, comfyui-nodes
What it does
MiniMax H3 renders faces poorly when the head occupies a small fraction of the frame. This is a property of head-size-in-frame, not of output resolution, so it persists at 720p and above. These nodes detect the face on every frame, crop to it so it fills a canvas, let H3 re-generate it, and composite the result back into the original video.
Get started
git clone https://github.com/Carasibana/ComfyUI-H3-FaceRefine.git - Maintenance
- Active
- Last commit 57 days ago
- Stars
- 576
- +20 this week
- Licence
- MIT
- Allows business use
- Downloads for
- None listed
- No release files
- Latest version
- v1.1.2
- Released 57 days ago
- Built with
- Python
- 81% of the code
Is it looked after?
- Contributors
- 3
- Last 90 days
- Issues
- 100% closed
- 0 still open
- Pull requests
- 2 merged
- 1 waiting
- Releases
- 3
- 3 in the last year
- No contributing guide
- No security policy
- No code of conduct
Similar repos
| Repo | Stars | Last commit | Licence | Downloads for |
|---|---|---|---|---|
| scraed / LanPaint | 1,483 | 42 days ago | GPL-3.0 | No downloads |
| JGRFW / comfyui-AICG3D-CSR | 22 | 3 days ago | MIT | No downloads |
| light-and-ray / Minimalistic-Comfy-Wrapper-WebUI | 145 | 15 days ago | AGPL-3.0 | No downloads |
More: languages, topics and project record
Languages
- Python 81%
- JavaScript 19%
Topics
- ai-video
- comfyui
- comfyui-custom-node
- comfyui-custom-nodes
- comfyui-nodes
- comfyui-video
- diffusion-models
- face-detection
- face-enhancement
- face-restoration
- generative-ai
- insightface
Project record
- JobImage generation
- StatusFeatured
- Commits14
- Forks50
- Watching2
- Stars in 28 days+110
- CreatedAug 12, 2026
- First seen by usNov 7, 2026
- CheckedNov 9, 2026