GET

/v1/schemas/fal/image/ideogram/v4/image-to-image

kind inputactivity imagehash e516b291…extracted Aug 10, 2026version currentsource upstream spec ↗
fieldrecorded source
schemaSource linked above.
Source trace
ad7c705d57de7324983f768d36368d31e5a991462e0b5a97914606bf393be8e5
{
  "fetchedAt": 1786338105,
  "extractorVersion": "1",
  "verifiedAt": null
}

Request body

12 properties · 2 required · 1 $defs
propertytypedescriptionconstraints
image_url*stringURL of the input image for image-to-image generation.
prompt*stringThe prompt to generate an image from.
sync_modebooleanIf `True`, the image is returned as a data URI and is not stored.default: false
output_formatenumThe format of the generated image.jpeg | png · default: "jpeg"
accelerationenumThe acceleration level to use for the image generation.none | low | regular | high · default: "none"
seedintegerThe seed to use for generation. If not provided, a random seed will be used.nullable
image_sizeImageSize | enumThe output image size. Use 'auto' to match the input image size (capped at ~25MP, up to 8192px per side).default: "auto"
expansion_modelenumWhich model expands the prompt. 'None' disables prompt expansion and skips its fee; 'Medium' is fast; 'Large' uses Ideogram's Magic Prompt for the highest quality.None | Medium | Large · default: "Medium"
num_imagesintegerNumber of images to generate.1 ≤ n ≤ 4 · default: 1
enable_safety_checkerbooleanIf set to true, the safety checker will be enabled. Disabling it requires account authorization; unauthorized requests are always checked.default: true
strengthnumberHow much to transform the input image. 1.0 ignores the input image entirely; lower values stay closer to it.0 ≤ n ≤ 1 · default: 0.8
rendering_speedenumThe rendering speed to use. Faster speeds use fewer denoising steps.TURBO | BALANCED | QUALITY · default: "BALANCED"

Types

1 $defs

ImageSizeobject

heightintegerThe height of the generated image.0 < n ≤ 14142 · default: 512
widthintegerThe width of the generated image.0 < n ≤ 14142 · default: 512

Validate a payload

before you spend tokens
shell
$ curl -X POST https://modelschemas.com/v1/validate \
    -d '{"provider":"fal","endpointId":"ideogram/v4/image-to-image","payload":{…}}'
→ {"valid": false, "errors": [{"path": "#", "keyword": "required", …}]}