Model · Nankai University · Image-Enhance
BiRefNet
A high-quality open background-removal and cut-out model from Peng Zheng and co-authors (lead affiliation Nankai University). Separates the subject from the background with clean edges on hair and fine detail; a high-resolution variant works at 2048×2048.
- Modality
- Image-Enhance
- License
- MIT (Open)
- Parameter size
- 220M
- Released
- January 7, 2024
- Last verified
- October 28, 2026
- Runs locally
- Yes
What you need to run it
- Mac
- Yes, but slow. Any Apple Silicon Mac (M1 or newer) with at least 8 GB (16 GB recommended) of memory. It runs, but much slower than on an NVIDIA card.
- Windows / Linux PC
- NVIDIA works best. A graphics card with at least 4 GB (8 GB recommended) of video memory.
- No graphics card
- Works. Runs on a normal computer's processor, just slower.
Runs on a Mac or plain CPU in a few seconds per image, but the official code is built for NVIDIA cards; ONNX builds (via rembg) are the easy Mac route.
Numbers are for: official model at 1024x1024, 16-bit. Our estimate from the model’s size — the maker publishes no figure.
Strengths
- MIT licence — free for commercial use
- Clean edges on hair, fur and fine structures
- Variants for general use, portraits, matting and high resolution (BiRefNet_HR, trained at 2048×2048)
- Small model: runs on an ordinary CPU through rembg, faster with a GPU
- Still actively maintained — repo updated October 2026
Weaknesses
- Only removes backgrounds and segments objects — no generation or upscaling
- Hosted on a personal Hugging Face account rather than an institution's
Try it
| Where | Type | Notes |
|---|---|---|
| Hugging Face | weights | MIT |
| rembg | local | Easy CLI and Python wrapper (MIT); birefnet-general, -portrait and -lite models; CPU or GPU |
| Hugging Face Spaces | hosted | Free demo |
Official sources
- Model card model
- GitHub github
- Paper paper
Change log
- — Added hardware requirements (Mac support, memory, NVIDIA). Source: estimate from size and community builds (HF ZhengPeng7/BiRefNet).
- — Initial entry. Release date is the arXiv paper date (2024-01-07; published in CAAI AIR 2024). MIT licence. Added 2026-10-28 from the popularity sweep: 825k Hugging Face downloads in the last month, 4.3k GitHub stars, and wrapped by rembg (25.2k GitHub stars).
Esc