GET

/v1/schemas/fal/image/wan/v2.6/text-to-image

Accept:

kind inputactivity imagehash 56ee14a6…extracted Aug 10, 2026version currentsource upstream spec ↗

field	recorded source
schema	Source linked above. Source trace `bab158f983cc0b0c34af8d9ccb650d078440b866f2e89d33ce6c3a5ce62085ce` { "fetchedAt": 1786338105, "extractorVersion": "1", "verifiedAt": null }

Request body

7 properties · 1 required · 1 $defs

property	type	description	constraints
prompt*	string	Text prompt describing the desired image. Supports Chinese and English. Max 2000 characters.	length ≥ 1
max_images	integer	Maximum number of images to generate (1-5). Actual count may be less depending on model inference.	1 ≤ n ≤ 5 · default: 1
image_size	ImageSize \| enum	Output image size. If not set: matches input image size (up to 1280*1280). Use presets like 'square_hd', 'landscape_16_9', or specify exact dimensions.	nullable
negative_prompt	string	Content to avoid in the generated image. Max 500 characters.	nullable
enable_safety_checker	boolean	Enable content moderation for input and output. Disabling it requires account authorization; unauthorized requests are always checked.	default: true
seed	integer	Random seed for reproducibility (0-2147483647).	nullable
image_url	string	Optional reference image (0 or 1). When provided, can be used for style guidance. Resolution: 384-5000px each dimension. Max size: 10MB. Formats: JPEG, JPG, PNG (no alpha), BMP, WEBP.	nullable

Types

1 $defs

ImageSizeobject

width	integer	The width of the generated image.	0 < n ≤ 14142 · default: 512
height	integer	The height 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":"wan/v2.6/text-to-image","payload":{…}}'
→ {"valid": false, "errors": [{"path": "#", "keyword": "required", …}]}