removebg-api
Use remove.bg for high-quality background removal.
API key setup
- Create/sign in at
https://www.remove.bg/dashboard#api-key - Create an API key
- Configure
REMOVE_BG_API_KEYin OpenClaw config (openclaw.json) so it is present in runtime environment.
Important
- Skill metadata (
requires.env) declares thatREMOVE_BG_API_KEYis required. - Metadata does not auto-load shell env files.
- Preferred: provide key via OpenClaw config-managed environment.
Usage (preferred: uv)
Run from the skill directory:
uv run scripts/removebg_api.py --input /path/in.jpg --output /path/out.png
Options:
-
--size auto|preview|full|4k(default:auto) -
--format png|jpg|zip(default:png) Security defaults: -
--inputmust be a real image file inside the OpenClaw workspace. -
Allowed input types:
.png,.jpg,.jpeg,.webp(extension + magic-byte validation). -
--outputmust be underoutputs/removebg-api/inside the workspace. -
Large/abusive files are rejected (size + dimension limits).
-
This prevents arbitrary file read/write outside normal skill boundaries.
Example:
uv run scripts/removebg_api.py --input ./input.jpg --output ./output.png --size auto --format png
Fallback (without uv)
python3 scripts/removebg_api.py --input ./input.jpg --output ./output.png
Output
- Writes result file to
--output - Prints
MEDIA:line for chat workflows
Notes
- API usage may consume free credits / paid quota.
- No absolute-path requirement for skill docs; use local paths in examples.