GET

/v1/schemas/fal/image/nvidia/cosmos-3-super/text-to-image

Accept:

kind inputactivity imagehash f529fd59…extracted Aug 8, 2026version currentsource upstream spec ↗

field	recorded source
schema	Source linked above. Source trace `6d66f6dda73d42110c3346f214fee9affa1e279d2e8eaa3522c7fee01531ca1c` { "fetchedAt": 1786165357, "extractorVersion": "1", "verifiedAt": null }

Request body

15 properties · 1 required · 1 $defs

property	type	description	constraints
prompt*	string	Text prompt describing the image to generate.	length ≥ 1 · length ≤ 4096
sync_mode	boolean	If `True`, the image is returned as a data URI and the output data won't be available in the request history.	default: false
enable_prompt_expansion	boolean	Expand the prompt with OpenRouter before image generation. When enabled, the prompt is rewritten into the dense structured-JSON format Cosmos3 was trained on; generation falls back to the raw prompt if expansion fails.	default: false
agentic_early_stop	boolean	Stop early when a candidate image is already a strong match for the prompt.	default: true
seed	integer	The same seed and prompt given to the same model version will produce the same image every time.	nullable
num_inference_steps	integer	Number of denoising steps. More steps yield higher quality but take longer.	1 ≤ n ≤ 50 · default: 28
enable_safety_checker	boolean	Enable content moderation for the input prompt and generated images. Disabling it requires account authorization; unauthorized requests are always checked, and images flagged as unsafe are returned as black images.	default: true
enable_agentic_generation	boolean	Automatically generate and compare multiple candidate images, then refine the prompt between rounds to better match the original request. This can improve prompt adherence but increases latency and billable image generations.	default: false
guidance_scale	number	Classifier-free guidance scale. Higher values increase prompt adherence at the cost of diversity.	0 ≤ n ≤ 20 · default: 4
num_images	integer	The number of images to generate.	1 ≤ n ≤ 4 · default: 1
agentic_samples_per_iteration	integer	Candidate images to generate and judge per agentic iteration. The best candidate advances to the next rewrite stage.	1 ≤ n ≤ 3 · default: 2
output_format	enum	The format of the generated image.	jpeg \| png · default: "jpeg"
agentic_max_iterations	integer	Maximum number of refinement rounds when agentic generation is enabled.	1 ≤ n ≤ 3 · default: 2
negative_prompt	string	Content to steer the generation away from (colors, objects, artifacts).	length ≤ 1024 · default: ""
image_size	ImageSize \| enum	The size of the generated image. Each edge is clamped to 512-1280px (multiples of 16).	default: "square_hd"

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":"nvidia/cosmos-3-super/text-to-image","payload":{…}}'
→ {"valid": false, "errors": [{"path": "#", "keyword": "required", …}]}