- withoutBG Open Weights
- Open weights · commercially permissiveLicense: Apache-2.0
- withoutBG Pro Model API
- ProprietaryLicense: Paid cloud API
withoutBG Open Weights vs Pro Model API
Quantitative comparison: 60 images scored against ground-truth mattes. Lower is better. Use the view controls on each row to switch between transparency, chroma key, and alpha matte on all outputs.
| Metric | withoutBG Open-Weight Model | withoutBG Pro Model API |
|---|---|---|
| MGE (Edge Quality) | 0.04523 | 0.02737 ✓ |
| MAE (Overall Accuracy) | 0.02923 | 0.02399 ✓ |
Disclosure: withoutBG includes BiRefNet
withoutBG Open Weights and Pro Model API are routed pipelines. A classifier sends fine strands, soft detail and transparency to withoutBG's own matting model, and hard opaque objects, flat scenes and vehicles to BiRefNet (MIT license), which is part of the pipeline. On this page, 17 of 58 images went to BiRefNet. Pro Model API also runs an edge refiner on the result of either branch, so its BiRefNet-routed images are refined BiRefNet output, not raw BiRefNet. The table splits the scores by route: the first group is what withoutBG's own matting model handled.
| Images | Metric | withoutBG Open-Weight Model | withoutBG Pro Model API |
|---|---|---|---|
| Routed to withoutBG matting (41) | MAE | 0.01846 | 0.01276 ✓ |
| MGE (edges) | 0.03773 | 0.01989 ✓ | |
| Routed to BiRefNet (17) | MAE | 0.01509 | 0.01233 ✓ |
| MGE (edges) | 0.04305 | 0.02601 ✓ |
Per-image averages, lower is better.
- MGE
- 0.03254
- MAE
- 0.00960
- MGE
- 0.00914✓
- MAE
- 0.00555✓
- MGE
- 0.06122
- MAE
- 0.02110
- MGE
- 0.01106✓
- MAE
- 0.00863✓
Photo by Alexander Dummer on Unsplash
- MGE
- 0.02084
- MAE
- 0.00601
- MGE
- 0.00247✓
- MAE
- 0.00143✓
- MGE
- 0.01262
- MAE
- 0.00461
- MGE
- 0.00373✓
- MAE
- 0.00172✓
- MGE
- 0.17462
- MAE
- 0.19712
- MGE
- 0.09770✓
- MAE
- 0.09947✓
Photo by Andreas Rasmussen on Unsplash
- MGE
- 0.07595
- MAE
- 0.02381✓
- MGE
- 0.04883✓
- MAE
- 0.02657
- MGE
- 0.03402
- MAE
- 0.02906
- MGE
- 0.02718✓
- MAE
- 0.02784✓
- MGE
- 0.04621
- MAE
- 0.01031
- MGE
- 0.03109✓
- MAE
- 0.00737✓
- MGE
- 0.01697
- MAE
- 0.00407✓
- MGE
- 0.01019✓
- MAE
- 0.00417
- MGE
- 0.01899
- MAE
- 0.00660
- MGE
- 0.01637✓
- MAE
- 0.00623✓
- MGE
- 0.04118
- MAE
- 0.01690
- MGE
- 0.01948✓
- MAE
- 0.01161✓
- MGE
- 0.04200
- MAE
- 0.01715✓
- MGE
- 0.02237✓
- MAE
- 0.03738
- MGE
- 0.05736
- MAE
- 0.08254
- MGE
- 0.00000✓
- MAE
- 0.00000✓
Photo by Camila Quintero Franco on Unsplash
- MGE
- 0.01469
- MAE
- 0.00695
- MGE
- 0.00847✓
- MAE
- 0.00568✓
- MGE
- 0.06638
- MAE
- 0.01242
- MGE
- 0.05622✓
- MAE
- 0.01045✓
- MGE
- 0.01093
- MAE
- 0.00177
- MGE
- 0.00297✓
- MAE
- 0.00053✓
Photo by Carlo Sierra on Unsplash
- MGE
- 0.02498
- MAE
- 0.00460
- MGE
- 0.01093✓
- MAE
- 0.00269✓
- MGE
- 0.03139
- MAE
- 0.00959
- MGE
- 0.01840✓
- MAE
- 0.00573✓
- MGE
- 0.02976✓
- MAE
- 0.00740✓
- MGE
- 0.03849
- MAE
- 0.01914
Photo by Conor Samuel on Unsplash
- MGE
- 0.07155
- MAE
- 0.01159
- MGE
- 0.02650✓
- MAE
- 0.00435✓
- MGE
- 0.03577
- MAE
- 0.00660✓
- MGE
- 0.03249✓
- MAE
- 0.00736
- MGE
- 0.01789
- MAE
- 0.00452
- MGE
- 0.00875✓
- MAE
- 0.00277✓
- MGE
- 0.03015
- MAE
- 0.01049
- MGE
- 0.01731✓
- MAE
- 0.00686✓
- MGE
- 0.05026
- MAE
- 0.01100
- MGE
- 0.03829✓
- MAE
- 0.00902✓
- MGE
- 0.01489
- MAE
- 0.00434✓
- MGE
- 0.01037✓
- MAE
- 0.00835
- MGE
- 0.01399
- MAE
- 0.00246
- MGE
- 0.00297✓
- MAE
- 0.00067✓
Photo by Lars Bo Nielsen on Unsplash
- MGE
- 0.05191
- MAE
- 0.01377✓
- MGE
- 0.01854✓
- MAE
- 0.01806
Photo by Mayer Tawfik on Unsplash
- MGE
- 0.01835
- MAE
- 0.00586✓
- MGE
- 0.01169✓
- MAE
- 0.00809
- MGE
- 0.01551
- MAE
- 0.00578✓
- MGE
- 0.01494✓
- MAE
- 0.00935
- MGE
- 0.02743
- MAE
- 0.00856
- MGE
- 0.00270✓
- MAE
- 0.00139✓
Photo by Niko Tsviliov on Unsplash
- MGE
- 0.14105
- MAE
- 0.05132
- MGE
- 0.04838✓
- MAE
- 0.04052✓
Photo by Norbert Braun on Unsplash
- MGE
- 0.01083
- MAE
- 0.00164
- MGE
- 0.00074✓
- MAE
- 0.00012✓
- MGE
- 0.05432
- MAE
- 0.02385
- MGE
- 0.04750✓
- MAE
- 0.02279✓
- MGE
- 0.03119
- MAE
- 0.02758
- MGE
- 0.01466✓
- MAE
- 0.01893✓
- MGE
- 0.02442
- MAE
- 0.01933
- MGE
- 0.01367✓
- MAE
- 0.01838✓
- MGE
- 0.02832
- MAE
- 0.01777
- MGE
- 0.01295✓
- MAE
- 0.00349✓
- MGE
- 0.37410
- MAE
- 0.49629
- MGE
- 0.33346✓
- MAE
- 0.34460✓
- MGE
- 0.02225
- MAE
- 0.00549
- MGE
- 0.01832✓
- MAE
- 0.00467✓
- MGE
- 0.01052
- MAE
- 0.00205
- MGE
- 0.00538✓
- MAE
- 0.00156✓
- MGE
- 0.02272
- MAE
- 0.00521
- MGE
- 0.01100✓
- MAE
- 0.00401✓
- MGE
- 0.03536
- MAE
- 0.00578
- MGE
- 0.03351✓
- MAE
- 0.00533✓
- MGE
- 0.02418
- MAE
- 0.02733
- MGE
- 0.01620✓
- MAE
- 0.01785✓
- MGE
- 0.02203
- MAE
- 0.00368
- MGE
- 0.01196✓
- MAE
- 0.00207✓
- MGE
- 0.01403
- MAE
- 0.00312
- MGE
- 0.00331✓
- MAE
- 0.00072✓
- MGE
- 0.02054
- MAE
- 0.00590
- MGE
- 0.01312✓
- MAE
- 0.00520✓
- MGE
- 0.00960
- MAE
- 0.00134
- MGE
- 0.00373✓
- MAE
- 0.00047✓
- MGE
- 0.02730
- MAE
- 0.00734
- MGE
- 0.01019✓
- MAE
- 0.00435✓
- MGE
- 0.02940
- MAE
- 0.01110✓
- MGE
- 0.02308✓
- MAE
- 0.01728
- MGE
- 0.18102
- MAE
- 0.03429
- MGE
- 0.07930✓
- MAE
- 0.02013✓
- MGE
- 0.07739✓
- MAE
- 0.09324✓
- MGE
- 0.07849
- MAE
- 0.09378
- MGE
- 0.13603
- MAE
- 0.02861
- MGE
- 0.11914✓
- MAE
- 0.02727✓
- MGE
- 0.02226
- MAE
- 0.00320
- MGE
- 0.00653✓
- MAE
- 0.00093✓
- MGE
- 0.03189
- MAE
- 0.00686
- MGE
- 0.00103✓
- MAE
- 0.00081✓
- MGE
- 0.01003
- MAE
- 0.01228
- MGE
- 0.00109✓
- MAE
- 0.00115✓
Photo by Vinicius Wiesehofer on Unsplash
- MGE
- 0.02822✓
- MAE
- 0.01994✓
- MGE
- 0.02893
- MAE
- 0.04267
- MGE
- 0.06085
- MAE
- 0.24387✓
- MGE
- 0.05100✓
- MAE
- 0.36202
- MGE
- 0.02557
- MAE
- 0.01326
- MGE
- 0.00127✓
- MAE
- 0.00108✓
- MGE
- 0.02353
- MAE
- 0.00573
- MGE
- 0.00481✓
- MAE
- 0.00187✓
- MGE
- 0.03757
- MAE
- 0.01221
- MGE
- 0.01195✓
- MAE
- 0.00431✓
- MGE
- 0.01677✓
- MAE
- 0.00759✓
- MGE
- 0.01769
- MAE
- 0.01273
Methodology
- Alpha mattes are grayscale masks encoding per-pixel foreground probability. They capture fine edge detail (hair, fur, semi-transparent regions) that binary masks discard.
- Metrics are computed by comparing predicted mattes against a ground-truth reference: MGE measures edge sharpness and MAE measures pixel-level accuracy. Both are lower-is-better.
- Scored images come from Bench v0, where every image has a ground-truth matte. The benchmark page has the full methodology and per-image scores for every model (CSV / JSON).
Photo Credits
Source images are courtesy of the photographers below via Unsplash.
Technical Specifications#
| Feature | Open Model | Pro Model API |
|---|---|---|
| Status | Active (Open Source) | Active (Cloud API) |
| Availability | Apache 2.0 | API, or self-hosted (commercial license) |
| Pixel Accuracy | Excellent | Best Overall |
| Edge Quality | Excellent | Superior |
| Hardware | CPU / GPU | Managed (AWS Frankfurt), or your own GPU servers |
| Privacy | Images never leave your computer | Server-side processing (deleted after use) |
| Free Credits | Unlimited (run locally) | 50 credits on signup |
| Recommended Use | Privacy-sensitive, local processing | Highest quality requirements, production API |
Installation#
The Open Model runs locally; the cloud API is accessed via REST.
Open Model
Run instantly with Docker
docker run -p 80:80 withoutbg/app:latestPress the copy button to copy this command to your clipboard
Python
Install via pip
pip install withoutbgPress the copy button to copy this command to your clipboard
Cloud API
API Request
Process images via the cloud API
api
curl -X POST https://api.withoutbg.com/v1/remove-background \
-H 'Authorization: Bearer YOUR_API_KEY' \
-F 'image=@input.jpg' \
-o output.pngPress the copy button to copy this command to your clipboard
See the full API documentation for integration details.