EachLabs Face Swap

Swap faces between images and videos using the EachLabs Predictions API.

Authentication

Header: X-API-Key: <your-api-key>

Set the EACHLABS_API_KEY environment variable. Get your key at eachlabs.ai.

Available Models

Examples

Image Face Swap with AI Face Swap V1

curl -X POST https://api.eachlabs.ai/v1/prediction \
  -H "Content-Type: application/json" \
  -H "X-API-Key: $EACHLABS_API_KEY" \
  -d '{
    "model": "aifaceswap-face-swap",
    "version": "0.0.1",
    "input": {
      "target_image": "https://example.com/target-photo.jpg",
      "swap_image": "https://example.com/source-face.jpg"
    }
  }'

Image Face Swap with Eachlabs

curl -X POST https://api.eachlabs.ai/v1/prediction \
  -H "Content-Type: application/json" \
  -H "X-API-Key: $EACHLABS_API_KEY" \
  -d '{
    "model": "each-faceswap-v1",
    "version": "0.0.1",
    "input": {
      "target_image": "https://example.com/target-photo.jpg",
      "swap_image": "https://example.com/source-face.jpg"
    }
  }'

Video Face Swap

curl -X POST https://api.eachlabs.ai/v1/prediction \
  -H "Content-Type: application/json" \
  -H "X-API-Key: $EACHLABS_API_KEY" \
  -d '{
    "model": "faceswap-video",
    "version": "0.0.1",
    "input": {
      "target_video": "https://example.com/target-video.mp4",
      "swap_image": "https://example.com/source-face.jpg"
    }
  }'

Alternative: Using GPT Image v1.5 Edit

For prompt-based face replacement:

curl -X POST https://api.eachlabs.ai/v1/prediction \
  -H "Content-Type: application/json" \
  -H "X-API-Key: $EACHLABS_API_KEY" \
  -d '{
    "model": "gpt-image-v1-5-edit",
    "version": "0.0.1",
    "input": {
      "prompt": "Replace the face in image 1 with the face from image 2. Keep the same pose, lighting, and expression. Maintain natural skin tone and seamless blending.",
      "image_urls": [
        "https://example.com/target-photo.jpg",
        "https://example.com/source-face.jpg"
      ],
      "quality": "high"
    }
  }'

Prediction Flow

1. Check model GET https://api.eachlabs.ai/v1/model?slug=<slug> — validates the model exists and returns the request_schema with exact input parameters. Always do this before creating a prediction to ensure correct inputs.
2. POST https://api.eachlabs.ai/v1/prediction with model slug, version "0.0.1", and input matching the schema
3. Poll GET https://api.eachlabs.ai/v1/prediction/{id} until status is "success" or "failed"
4. Extract the output image URL from the response

Tips for Best Results

• Use high-quality source images with clear, well-lit faces
• The source face image should be a clear frontal or near-frontal portrait
• Matching lighting conditions between source and target produces more natural results
• Specify "seamless blending" and "natural skin tone" in prompts
• For the target image, faces should be clearly visible and not heavily occluded