faceswap

Swap a face from a source image into a target video using GPU-accelerated AI processing. The source image provides the face to swap in, and the target video receives the new face. All requests require the X-Api-Key header. Set the HEYGEN_API_KEY environment variable. POST GET Generate an avatar video first, then swap in a custom face: - Call POST /v1/workflows/executions with workflow_type: "FaceswapNode" , a source face image, and a target video - Receive a execution_id in the response - Poll GET /v1/workflows/executions/{id} every 10 seconds until status is completed - Use the returned video_url from the output - Use a clear, front-facing face photo — the source image should show a single face with good lighting - Face swap is GPU-intensive — expect 1-3 minutes processing time, poll every 10 seconds - Source image quality matters — higher resolution face photos produce better results - One face per source image — the source should contain exactly one face to swap in - Works with any video — the target video can be an avatar video, a recording, or any video with visible faces - Chain with other workflows — generate an avatar video first, then swap in a custom face for personalization