GET

/v1/schemas/fal/image/fal-ai/omnigen-v2

Accept:

kind inputactivity imagehash 65fd9276…extracted Aug 10, 2026version currentsource upstream spec ↗

field	recorded source
schema	Source linked above. Source trace `f70009f0e1c48994fbf341d4c0f71a1d11544b4037778ac4716832e8d2bf54fc` { "fetchedAt": 1786338105, "extractorVersion": "1", "verifiedAt": null }

Request body

15 properties · 1 required · 1 $defs

property	type	description	constraints
prompt*	string	The prompt to generate or edit an image. Use specific language like 'Add the bird from image 1 to the desk in image 2' for better results.
enable_safety_checker	boolean	If set to true, the safety checker will be enabled. Disabling it requires account authorization; unauthorized requests are always checked, and images flagged as unsafe are returned as black images.	default: true
cfg_range_end	number	CFG range end value.	0 ≤ n ≤ 1 · default: 1
negative_prompt	string	Negative prompt to guide what should not be in the image.	default: "(((deformed))), blurry, over sa…
text_guidance_scale	number	The Text Guidance scale controls how closely the model follows the text prompt. Higher values make the model stick more closely to the prompt.	1 ≤ n ≤ 8 · default: 5
image_size	ImageSize \| enum	The size of the generated image.	default: "square_hd"
cfg_range_start	number	CFG range start value.	0 ≤ n ≤ 1 · default: 0
input_image_urls	string[]	URLs of input images to use for image editing or multi-image generation. Support up to 3 images.	default: []
num_inference_steps	integer	The number of inference steps to perform.	20 ≤ n ≤ 50 · default: 50
image_guidance_scale	number	The Image Guidance scale controls how closely the model follows the input images. For image editing: 1.3-2.0, for in-context generation: 2.0-3.0	1 ≤ n ≤ 3 · default: 2
output_format	enum	The format of the generated image.	jpeg \| png · default: "jpeg"
seed	integer	The same seed and the same prompt given to the same version of the model will output the same image every time.	nullable
scheduler	enum	The scheduler to use for the diffusion process.	euler \| dpmsolver · default: "euler"
num_images	integer	The number of images to generate.	1 ≤ n ≤ 4 · default: 1
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

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":"fal-ai/omnigen-v2","payload":{…}}'
→ {"valid": false, "errors": [{"path": "#", "keyword": "required", …}]}