withoutbg/withoutbg-openweights-v3-service-gpu repository overview

⁠withoutBG Open Weights v3 — Inference API (GPU)

Self-hosted withoutBG⁠ open weights background removal API with GPU acceleration. Runs the v3 ONNX model via CUDA for faster inference.

⁠Quick start

Requires an NVIDIA GPU and the NVIDIA Container Toolkit⁠.

docker run --rm --gpus all -p 8000:8000 withoutbg/withoutbg-openweights-v3-service-gpu:latest

Health check: http://localhost:8000/health

⁠Platforms

Published for linux/amd64 only (NVIDIA CUDA on x86_64).

⁠API

Same input/output schema as the withoutBG Mac Local API: send a raw JPEG/PNG body (or multipart field image); response is image/png with headers X-Latency-Ms, X-Route-Category and X-Route-Pipeline (matting or birefnet). Use ?output=matte for a grayscale alpha matte instead of the default cutout.

curl -X POST \
  --data-binary @photo.jpg \
  -H "Content-Type: image/jpeg" \
  http://127.0.0.1:8000/v1/remove-background \
  -o result.png

curl -X POST "http://127.0.0.1:8000/v1/remove-background?output=matte" \
  -H "Content-Type: image/png" \
  --data-binary @photo.png \
  -o matte.png

⁠Model

The withoutBG Open Weights 10.8.0 bundle (~1.5 GB, baked into the image): a trained router sends fine strands, soft detail and transparency to the withoutBG matting model, and hard opaque objects, flat scenes and vehicles to BiRefNet. Only the selected branch runs.

⁠Related images

⁠Links

• withoutBG open model⁠
• Source on GitHub⁠
• License: Apache-2.0 for the code; the model is under the withoutBG Open Weights license⁠ and includes DINOv3, Depth Anything V2 (Apache-2.0) and BiRefNet (MIT). See /v1/licenses in the running container