GET

/v1/schemas/fal/image/krea/v3/text-to-image

Accept:

kind inputactivity imagehash 2ef46674…extracted Nov 6, 2026version currentsource upstream spec ↗

field	recorded source
schema	Source linked above. upstream-spec Source trace `f131d84c4cd76afcc43977ede8014f4fcc65aeb78cf52676cd49039782b43371` { "fetchedAt": 1793941202, "extractorVersion": "1", "verifiedAt": null }

Request body

8 properties · 1 required · 1 $defs

property	type	description	constraints
prompt*	string	Description of the image to generate.	length ≥ 1 · length ≤ 5000
seed	integer	Latent noise seed. Use a new seed when editing a previous output again.	nullable
output_format	enum	Output image format.	png \| jpeg · default: "png"
reasoning_level	enum	How much effort the prompt expander spends reasoning about the given prompt. Higher reasoning effort means slower generation time.	medium \| high · default: "medium"
enable_safety_checker	boolean	Check output images for unsafe content. Disabling requires account authorization.	default: true
image_size	ImageSize \| enum	Output size, rounded up to multiples of 16, at most 4,220,160 total pixels (1680×2512). auto lets the prompt expander pick the aspect ratio at about 2048×2048.	default: "auto"
negative_prompt	string	What to keep out of the image.	length ≤ 1024 · default: ""
sync_mode	boolean	Return images as data URIs instead of saving them in request history.	default: false

Types

1 $defs

ImageSizeobject

height	integer	The height of the generated image.	0 < n ≤ 14142 · default: 512
width	integer	The 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":"krea/v3/text-to-image","payload":{…}}'
→ {"valid": false, "errors": [{"path": "#", "keyword": "required", …}]}