OSS Radar
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 it matters: useful plumbing for shipping LLM-powered features.
GitHub description: Refine and improve the quality of small faces in MiniMax H3 video. Per-frame face tracking, crop, refine with H3, stitch back.
Stars
485
Last 24h
+12
Last 7 days
+84est.
Forks
42
Star history
GitHub stars over time. A steeper line means the repo is gaining attention faster.
Last 3 hours · +7 stars
Daily, since Oct 13, 2026 · 473 → 485
* / est. Estimated: until we have enough daily snapshots for a repo, its gain is total stars ÷ days since creation. Measured numbers replace estimates automatically.
Maintainer? Add the badge to your README
Shows your live OSS Radar rank and links back here. Updates hourly.
[](https://ossradar.net/repo/Carasibana/ComfyUI-H3-FaceRefine)<a href="https://ossradar.net/repo/Carasibana/ComfyUI-H3-FaceRefine"><img src="https://ossradar.net/badge/Carasibana/ComfyUI-H3-FaceRefine" alt="Trending on OSS Radar"></a>About ComfyUI-H3-FaceRefine
Carasibana/ComfyUI-H3-FaceRefine is a Python project in the LLM tooling category, created 2 months ago. It has 485 GitHub stars and 42 forks, and gained +84 stars over the last 7 days (early estimate), ranking #91 of 161 LLM tooling repos tracked by OSS Radar this week.
See more trending LLM tooling repos or the top AI repos this week.
- Language
- Python
- Category
- LLM tooling
- Created
- Aug 12, 2026
- Last code push
- 31 days ago (Sep 13, 2026)
- Latest release
- v1.1.2 31 days ago
- ai-video
- comfyui
- comfyui-custom-node
- comfyui-custom-nodes
- comfyui-nodes
- comfyui-video
- diffusion-models
- face-detection
- face-enhancement
- face-restoration
- generative-ai
- insightface
- lipsync
- minimax-h3
- segment-anything
- video-generation
- video-processing
- yolov8
Similar rising repos
- spicyapi-ai/comfyui-spicyapi+35est.
ComfyUI custom nodes for 180+ hosted AI models: Seedance, Kling, Wan, MiniMax H3, Vidu, LTX, Suno, GPT Image, Nano Banana, Seedream, FLUX… Why it matters: useful plumbing for shipping LLM-powered features.
- FlashML-org/FreeVideo+112est.
Make videos on the computer you already own. FreeVideo runs MiniMax H3 in as little as 8 GB of VRAM and 16 GB of RAM, and adapts its… Why it matters: useful plumbing for shipping LLM-powered features.
Learn AI Engineering! Learn it. Build it. Ship it for others. Why it matters: useful plumbing for shipping LLM-powered features.
- BlenderGPT3D/blender-ai-addon+525est.
Blender add-on: create and edit 3D models by chatting with AI - send text or an image, get working bpy code. Why it matters: useful plumbing for shipping LLM-powered features.
- langchain-ai/langchain+161est.
The agent engineering platform. Why it matters: useful plumbing for shipping LLM-powered features.
- langchain-ai/langgraph+119est.
Build resilient agents. Why it matters: useful plumbing for shipping LLM-powered features.