IS-Net (isnet-general-use) background removal#

How to run IS-Net

IS-Net ships with rembg as the session isnet-general-use. The weights download on first use.

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

from rembg import new_session, remove
from PIL import Image

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

Other sessions: all rembg models.

IS-Net (general use) as a free, open-source remove.bg alternative

remove.bg is a paid cloud service. IS-Net (general use) is open weights under Apache-2.0, so commercial use is allowed. It runs on your own machine (rembg i -m isnet-general-use input.jpg output.png), offline, with no upload and no per-image cost. On Bench v0 it ranks #10 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: Sharper general objects vs classic u2net
• Avoid when: Tight CPU budgets — prefer u2netp / BiRefNet lite
• Notes: Available as rembg session `isnet-general-use`.

When a hosted model is worth it

IS-Net 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.