ANGEHUB.COM
中
Docs/AngeMedia

Generate and edit images

Validate text-to-image first. Add reference images and masks gradually so a failed field is easy to identify.

Text to imageImage to imageMask

Endpoint

POST /v1/images/generations
Authorization: Bearer <GATEWAY_API_KEY>

Text to image

curl -X POST http://localhost:9890/v1/images/generations \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer YOUR_GATEWAY_KEY" \
  -d '{
    "model": "agnes-2.1",
    "prompt": "minimal product photo, soft natural light, clean background",
    "size": "1024x1024",
    "response_format": "url"
  }'

Single reference image

{
  "model": "agnes-2.1",
  "prompt": "keep the subject and composition, change to a cinematic poster style",
  "image": "https://example.com/input.jpg",
  "strength": 0.55,
  "size": "1024x1024",
  "response_format": "url"
}

A higher strength generally allows more deviation from the source. Start with a moderate value.

Multiple references

{
  "model": "agnes-2.0",
  "prompt": "combine the clothing style from the first image with the scene from the second",
  "images": [
    "https://example.com/look.jpg",
    "https://example.com/scene.jpg"
  ],
  "size": "1024x1024"
}

Mask editing

{
  "model": "agnes-2.1",
  "prompt": "replace the selected area with white tulips and preserve the original lighting",
  "image": "https://example.com/original.jpg",
  "mask": "https://example.com/mask.png",
  "size": "1024x1024"
}

Input guidance