Remove an object from a video — the Vanishing Act
`void-inpaint` accepts `video_url` (required), `prompt` (required — describe the *clean background*), and `mask_prompt` (describe the *subject to remove* — it auto-masks via SAM-3). It also takes `quad_mask_video_url` if you'd rather supply your own mask video, plus `negative_prompt`, `num_inference_steps`, `strength`, `num_frames`, `enable_pass2_refinement`. It returns `{ video: { url } }` — the inpainted clip with the subject gone. LOCAL clip? Host it first: `scripts/host-local-file.sh <path>` -> pass the returned public URL as `video_url` (auto-deletes ~2 days; see CLAUDE.md "GCS ingest").
Output
Time
a short clip + one sentence → the subject erased, background reconstructed, in ~3–6 min
Budget
~$0.30–$0.90 per clip (priced per video-second of inpainting)
Reliability
4.1
Customize this playbook
Fill in the fields below. Your answers are inserted into the complete recipe when you copy it.
This playbook is ready to use without additional details.
RUNNER
Create and edit images and video with your agent.
npm install -g @livepeer/runner