Generate Images Using Flux

Follow this recipes to generate images using the Flux model.


The guide will recreate the following functionality in the Web UI via API.

Sample Request

curl --request POST \
     --url https://cloud.leonardo.ai/api/rest/v1/generations \
     --header 'accept: application/json' \
     --header 'authorization: Bearer <YOUR_API_KEY>' \
     --header 'content-type: application/json' \
     --data '
{
  "modelId": "b2614463-296c-462a-9586-aafdb8f00e36",
  "contrast": 3.5,
  "prompt": "an orange cat playing with a tennis ball with the text FLUX",
  "num_images": 4,
  "width": 1472,
  "height": 832,
  "alchemy": true,
  "styleUUID": "111dc692-d470-4eec-b791-3475abac4c46",
  "enhancePrompt": false
}
'

Sample Output

Leonardo Phoenix with the prompt "an orange cat standing on a blue basketball with the text PAWS"

Flux Precision (Flux Dev) with the prompt "an orange cat playing with a tennis ball with the text FLUX"

Required Parameters

  • modelId

    PresetModelmodelId
    Flux SpeedFlux Schnell1dd50843-d653-4516-a8e3-f0238ee453ff
    Flux PrecisionFlux Devb2614463-296c-462a-9586-aafdb8f00e36
  • prompt - Text prompt to use for generation.

Supported Parameters

  • alchemy (Generation Mode - Fast / Quality)

    Generation ModeValue
    Fastalchemy:false
    Qualityalchemy:true

    Generation Mode uses the alchemy pipeline.

  • contrast

    ContrastValue
    Low3
    Medium3.5
    High4

    Accepts [1.0, 1.3, 1.8, 2.5, 3, 3.5, 4, 4.5]. If alchemy is true, contrast needs to be 2.5 or higher.

  • enhancePrompt (Prompt Enhance)

    • Set to false for OFF.
    • Set to true for ON and specify enhancePromptInstruction: "INSTRUCTION_AS_STRING".
  • height - Height input resolution.

  • num_images - Number of images.

  • styleUUID (Preset Style)

    Preset StyleUUID
    3D Renderdebdf72a-91a4-467b-bf61-cc02bdeb69c6
    Bokeh9fdc5e8c-4d13-49b4-9ce6-5a74cbb19177
    Cinematica5632c7c-ddbb-4e2f-ba34-8456ab3ac436
    Cinematic Concept33abbb99-03b9-4dd7-9761-ee98650b2c88
    Creative6fedbf1f-4a17-45ec-84fb-92fe524a29ef
    Dynamic111dc692-d470-4eec-b791-3475abac4c46
    Fashion594c4a08-a522-4e0e-b7ff-e4dac4b6b622
    Graphic Design Pop Art2e74ec31-f3a4-4825-b08b-2894f6d13941
    Graphic Design Vector1fbb6a68-9319-44d2-8d56-2957ca0ece6a
    HDR97c20e5c-1af6-4d42-b227-54d03d8f0727
    Illustration645e4195-f63d-4715-a3f2-3fb1e6eb8c70
    Macro30c1d34f-e3a9-479a-b56f-c018bbc9c02a
    Minimalistcadc8cd6-7838-4c99-b645-df76be8ba8d8
    Moody621e1c9a-6319-4bee-a12d-ae40659162fa
    None556c1ee5-ec38-42e8-955a-1e82dad0ffa1
    Portrait8e2bc543-6ee2-45f9-bcd9-594b6ce84dcd
    Ray Tracedb504f83c-3326-4947-82e1-7fe9e839ec0f
    Sketch (B&W)be8c6b58-739c-4d44-b9c1-b032ed308b61
    Sketch (Color)093accc3-7633-4ffd-82da-d34000dfc0d6
    Stock Photo5bdc3f2a-1be6-4d1c-8e77-992a30824a2c
    Vibrantdee282d3-891f-4f73-ba02-7f8131e5541b
  • ultra (Generation Mode - Ultra) - Set to true to turn on ultra.

  • width - Width input resolution.

Cost

Please refer to the apiCreditCost in the API response.