ImageGenerationRequestSchema

modelstringrequired

ID of the text-to-image model to use, such as FLUX.1-schnell. Use the model_name from List base models; the model must support the text-to-image modality.

promptstringrequired

Text description of the image to generate.

negative_promptstring

Text describing what to exclude from the generated image.

Default: null

image_sizestring

Output image size, as an aspect-ratio preset or an explicit WIDTHxHEIGHT value.

Enum Value	Description
square_hd	Square output, high resolution.
square	Square output (1:1).
portrait_4_3	Portrait output, 3:4 aspect ratio.
portrait_16_9	Portrait output, 9:16 aspect ratio.
landscape_4_3	Landscape output, 4:3 aspect ratio.
landscape_16_9	Landscape output, 16:9 aspect ratio.

Default: square_hd

num_imagesinteger

Number of images to generate.

Default: 1

num_inference_stepsinteger

Number of denoising steps. Higher values can improve quality at the cost of speed.

Default: null

guidance_scalenumber

How closely the result follows the prompt. Higher values follow the prompt more strictly.

Default: null

seedinteger

Random seed for reproducible results.

Default: null

schedulerstring

Sampler or scheduler to use, when supported by the model.

Default: null

output_formatstring

Format of the returned image.

Enum Value	Description
png	Returns a lossless PNG image.
jpeg	Returns a smaller, lossy JPEG image.
webp	Returns a compact WebP image.

Possible values: [png, jpeg, webp]

Default: null

presetstring

Named quality or style preset, when supported by the model.

Default: null

ImageGenerationRequestSchema

{
  "model": "string",
  "prompt": "string",
  "negative_prompt": null,
  "image_size": "square_hd",
  "num_images": 1,
  "num_inference_steps": null,
  "guidance_scale": null,
  "seed": null,
  "scheduler": null,
  "output_format": "png",
  "preset": null
}