Download OpenAPI specification:Download
REST API for Adobe Firefly for enterprise usage
Generate images based on your text prompt. When you make your request, you can also include an optional reference image and Firefly will try to mimic the layout and style, such as color scheme, lighting, layout of objects in the image and so on.
image generation request body.
numVariations | integer (The number of variations) [ 1 .. 4 ] The number of variations to generate. numVariations will default to the number of seeds, or to 1 if seeds is not specified. | ||||||||||||||||||
seeds | Array of integers (The seed of each variation) [ 1 .. 4 ] items unique Default: [0] Array of seed(s) that ensure consistent image generation across multiple API calls. For example, you can use the same seed to generate a similar image with different styles. If specified alongside with numVariations, the number of seeds must be the equal to numVariations. | ||||||||||||||||||
object (The size) Default: {"width":2048,"height":2048} The size of the requested generations. The supported dimensions for image generations are:
| |||||||||||||||||||
prompt required | string (The prompt) [ 1 .. 1024 ] characters The prompt used to generate the image. The longer the prompt - the better. | ||||||||||||||||||
negativePrompt | string (Avoid prompt) <= 1024 characters Inference will try to generate against this prompt. | ||||||||||||||||||
contentClass | string (The content class) Will guide the generation to being more photographic or more like art. | ||||||||||||||||||
visualIntensity | integer (Visual Intensity) [ 2 .. 10 ] Adjusts the overall intensity of your photo's existing visual characteristics. | ||||||||||||||||||
object (Style Reference) You can specify a preset, a reference image or both. | |||||||||||||||||||
promptBiasingLocaleCode | string (The locale used for image generations) Default: "en-US" A hyphen-separated string combining the ISO 639-1 language code and the ISO 3166-1 region, such as "en-US". When a locale is set, the prompt will be biased to generate more relevant content for that region. The locale will be auto-detected if not specified based on the user's profile and Accept-Language header. | ||||||||||||||||||
tileable | boolean (Output image tileability) Default: false An image is tileable if it can be repeated infinitely in any direction without showing visible seams or edges. | ||||||||||||||||||
object (Structure Reference) Use structure to ensure the generated image maintains a similar layout and organization as the reference image, providing a cohesive and visually balanced result. |
Successful Response
Bad Request
Forbidden
Request Timeout
Unsupported Media Type
Unprocessable Entity
Too Many Requests
Internal Server Error
Not Implemented
Service Unavailable
{- "numVariations": 1,
- "seeds": [
- 0
], - "size": {
- "width": 2048,
- "height": 2048
}, - "prompt": "Horses in a field.",
- "negativePrompt": "string",
- "contentClass": "photo",
- "visualIntensity": 2,
- "style": {
- "presets": [
- "string"
], - "strength": 100,
}, - "promptBiasingLocaleCode": "en-US",
- "tileable": false,
- "structure": {
- "strength": 100,
}
}
{- "size": {
- "width": 1,
- "height": 1
}, - "promptHasDeniedWords": true,
- "promptHasBlockedArtists": true,
- "contentClass": "photo"
}