withoutBG Open Weights Inference (v3)

Self-host background removal. Docker images and FastAPI for the withoutBG open weights ONNX model — CPU or NVIDIA GPU.

Run a browser UI, a headless API, or both. Same open-weights quality as the Python package and Mac app, on your own server.

Docker docs → · GPU docs → · Local API docs →

See the results

Open Weights results → · Cloud API results → · Compare →

Images

Image	Description
withoutbg-openweights-v3-service-cpu	Inference API only (CPU), headless
withoutbg-openweights-v3-service-gpu	Inference API only (GPU), headless
withoutbg-openweights-v3-app-cpu	Web UI + API (CPU)
withoutbg-openweights-v3-app-gpu	Web UI + API (GPU)

Docker Hub: withoutbg/withoutbg-openweights-v3-*

CPU images are published for linux/amd64 and linux/arm64 (Intel/AMD and Apple Silicon / ARM servers). GPU images are linux/amd64 only (NVIDIA CUDA).

App image (web UI + API) — drag-and-drop background removal in the browser, same API under /api:

Service image (API only / headless) — FastAPI with no UI. Interactive OpenAPI / Swagger at /docs:

Quick start

# Web UI + API (CPU) — open http://localhost:8080
docker run --rm -p 8080:8080 withoutbg/withoutbg-openweights-v3-app-cpu:latest

# API only (CPU) — OpenAPI at http://localhost:8000/docs
docker run --rm -p 8000:8000 withoutbg/withoutbg-openweights-v3-service-cpu:latest

GPU images require an NVIDIA GPU and the NVIDIA Container Toolkit:

docker run --rm --gpus all -p 8000:8000 withoutbg/withoutbg-openweights-v3-service-gpu:latest
docker run --rm --gpus all -p 8080:8080 withoutbg/withoutbg-openweights-v3-app-gpu:latest

After baking locally, use Compose:

docker compose up app-cpu

Build

docker buildx bake -f docker-bake.hcl

Build a single image:

docker buildx bake -f docker-bake.hcl app-cpu

Build for one platform locally (faster on Apple Silicon):

docker buildx bake -f docker-bake.hcl app-cpu --set '*.platform=linux/arm64'

CI downloads the ~455 MB model once via huggingface_hub. Add a HF_TOKEN repository secret for reliable Hugging Face downloads from GitHub Actions.

Development

Production Docker images bake the ~455 MB model at build time and do not hot-reload. For day-to-day work, use native dev with a one-time model download:

# 1. Download model once (~455 MB, cached in .cache/model/)
./scripts/dev-download-model.sh

# 2. API with hot reload (port 8000)
./scripts/dev-api.sh

# 3. UI with hot reload (port 3000, proxies /api → :8000)
cd ui && npm install && npm run dev

Edit Python under service/ or model/ and uvicorn reloads automatically. Edit React under ui/src/ and Next.js hot-reloads.

UI-only work (no real inference): NEXT_PUBLIC_USE_MOCK=true npm run dev in ui/.

Docker dev (same hot reload, cached model mount):

./scripts/dev-download-model.sh
docker compose -f docker-compose.dev.yml up --build

The first docker compose -f docker-compose.dev.yml build installs Python deps only (no model download). Rebuild only when pyproject.toml changes.

Production-like testing still uses docker buildx bake + docker compose up service-cpu.

More than Docker

This repo is the self-host path: HTTP API and browser UI on your own machine or server. Same open-weights technology powers the rest of the ecosystem:

Surface	Choose when
Python package	You want to embed withoutBG in scripts, notebooks, or backends
Mac app	You want a native desktop cutout tool, with an optional Local API for plugins and scripts
GIMP plugin	You edit in GIMP 3 and want a private, mask-first workflow via Mac Local API or this Docker service
Hugging Face · Space	You want to try a demo or download the ONNX weights directly
Cloud API	You need maximum quality without running inference yourself

# In-process Python (no Docker)
# https://github.com/withoutbg/withoutbg-python
uv add withoutbg

Model

The withoutBG Open Weights Model is a unified ONNX graph hosted at withoutbg/withoutbg-openweights-onnx. Depth, segmentation, matting, and refinement run in one pass. Built with DINOv3.

Licensed under the withoutBG Open Model License (Apache 2.0 for withoutBG portions; Meta DINOv3 License for DINOv3 backbone weights).

License

Apache-2.0 for this repository's code. Built with DINOv3. See THIRD_PARTY_NOTICES.md for upstream model attribution.

Support

• Bugs / questions: GitHub Issues
• Docker docs: withoutbg.com/docs/open-model/docker
• Commercial: contact@withoutbg.com