BiRefNet General (birefnet-general) background removal#

How to run BiRefNet

BiRefNet ships with rembg as the session birefnet-general. The weights download on first use.

pip install "rembg[cpu,cli]"
rembg i -m birefnet-general input.jpg output.png

from rembg import new_session, remove
from PIL import Image

session = new_session("birefnet-general")  # load once, reuse for every image
output = remove(Image.open("input.jpg"), session=session)
output.save("output.png")

Other sessions: all rembg models.

BiRefNet General as a free, open-source remove.bg alternative

remove.bg is a paid cloud service. BiRefNet General is open weights under MIT, so commercial use is allowed. It runs on your own machine (rembg i -m birefnet-general input.jpg output.png), offline, with no upload and no per-image cost. On Bench v0 it ranks #4 of 14 by accuracy (MAE); withoutBG Open Weights ranks #3.

remove.bg is not in Bench v0, so there is no score against it. See withoutBG Open Weights and remove.bg side by side, or compare all remove.bg alternatives.

Quick take

• Best for: High-quality open cutouts when you can afford heavier models
• Avoid when: Strict latency or tiny ONNX footprints
• Notes: Available as rembg session `birefnet-general`.

When a hosted model is worth it

BiRefNet is free and runs on your machine; keep it if the results above are good enough. If you need finer hair and edges, or don't want to run large models locally, rembg also ships the withoutBG Pro Model as the withoutbg session, ranked #1 of 14 by accuracy on Bench v0. Images are sent to withoutBG's servers.

export WITHOUTBG_API_KEY=sk_...
rembg i -m withoutbg input.jpg output.png

Sign up for 50 free credits (no credit card) or See its results.