GET

/v1/schemas/fal/image/fal-ai/hunyuan-image/v3/instruct/text-to-image

Accept:

kind inputactivity imagehash 178623c8…extracted Jul 6, 2026version currentsource upstream spec ↗

field	recorded source
schema	Source linked above. Source trace `26aaa1cdf78a17676066a04456fb70cfc4005369d6184ac6c780b080220c5d76` { "fetchedAt": 1783329487, "extractorVersion": "1", "verifiedAt": null }

Request body

9 properties · 1 required · 1 $defs

property	type	description	constraints
prompt*	string	The text prompt to generate an image from.
seed	integer	Random seed for reproducible results. If None, a random seed is used.	nullable
output_format	enum	The format of the generated image.	jpeg \| png · default: "png"
enable_prompt_expansion	boolean	If set to true, the prompt will be expanded through the model's internal recaptioning step.	default: true
image_size	ImageSize \| enum	The desired size of the generated image. If auto, image size will be determined by the model.	default: "auto"
guidance_scale	number	Controls how much the model adheres to the prompt. Higher values mean stricter adherence.	1 < n ≤ 20 · default: 3.5
num_images	integer	The number of images to generate.	1 ≤ n ≤ 4 · default: 1
enable_safety_checker	boolean	If set to true, the safety checker will be enabled.	default: true
sync_mode	boolean	If `True`, the media will be returned as a data URI and the output data won't be available in the 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":"fal-ai/hunyuan-image/v3/instruct/text-to-image","payload":{…}}'
→ {"valid": false, "errors": [{"path": "#", "keyword": "required", …}]}