GET

/v1/schemas/fal/image/blackforestlabs%2Fflux-3%2Fklein%2Ftext-to-image

kind inputactivity imagehash 5f58665a…extracted Oct 16, 2026version currentsource upstream spec ↗

Request body

9 properties · 1 required · 3 $defs
propertytypedescriptionconstraints
prompt*stringThe prompt to generate an image from. The model is trained on detailed captions: describe framing, subject, background and lighting.
image_sizeImageSize | enumThe size of the generated image. Each side can be 256 to 4096 pixels (native 4K).default: "square_hd"
seedintegerThe same seed and the same prompt given to the same version of the model will output the same image every time.nullable
sync_modebooleanIf `True`, the media will be returned as a data URI and the output data won't be available in the request history.default: false
bounding_boxesBoundingBox[]Optional layout: draw each described object inside its box. Box edges are fractions of the image size, with (0, 0) at the top-left. Name boxes in the prompt by label, e.g. `A red fox <fox> sits under a red umbrella <umbrella>`.items ≤ 32 · nullable
num_imagesintegerThe number of images to generate.1 ≤ n ≤ 4 · default: 1
output_formatenumThe format of the generated image.jpeg | png | webp · default: "png"
enable_prompt_expansionbooleanIf set to true, the prompt is expanded into a detailed caption (grounded in the reference images when editing) before generation.default: true
enable_safety_checkerbooleanIf set to true, the safety checker will be enabled.default: true

Validate a payload

before you spend tokens
shell
$ curl -X POST https://modelschemas.com/v1/validate \
    -d '{"provider":"fal","endpointId":"blackforestlabs/flux-3/klein/text-to-image","payload":{…}}'
→ {"valid": false, "errors": [{"path": "#", "keyword": "required", …}]}