fal.ai·Image generation

FLUX1.1 [pro] ultra

/fal-ai/flux-pro/v1.1-ultraasync$0.12 / image

FLUX1.1 [pro] ultra is the newest version of FLUX1.1 [pro], maintaining professional-grade image quality while delivering up to 2K resolution with improved photo realism. Returns hosted file URLs (download promptly; fal keeps them for a limited time). Billed per image.

Charged per image produced; a call that produces nothing is charged one unit.

Input

promptstringrequired
The prompt to generate an image from.
enhance_promptboolean
Whether to enhance the prompt for better results. (default false)
aspect_ratioany
The aspect ratio of the generated image. (default "16:9")
safety_tolerancestring
The safety tolerance level for the generated image. 1 being the most strict and 5 being the most permissive. (default "2")
1, 2, 3, 4, 5, 6
seedany
The same seed and the same prompt given to the same version of the model will output the same image every time.
image_prompt_strengthnumber
The strength of the image prompt, between 0 and 1. (default 0.1)
sync_modeboolean
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)
num_imagesinteger
The number of images to generate. (default 1)
output_formatstring
The format of the generated image. (default "jpeg")
jpeg, png
image_urlany
The image URL to generate an image from.
rawboolean
Generate less processed, more natural-looking images. (default false)

Field	Type	Required	Description
prompt	string	yes	The prompt to generate an image from.
enhance_prompt	boolean	—	Whether to enhance the prompt for better results. (default false)
aspect_ratio	any	—	The aspect ratio of the generated image. (default "16:9")
safety_tolerance	string (1, 2, 3, 4, 5, 6)	—	The safety tolerance level for the generated image. 1 being the most strict and 5 being the most permissive. (default "2")
seed	any	—	The same seed and the same prompt given to the same version of the model will output the same image every time.
image_prompt_strength	number	—	The strength of the image prompt, between 0 and 1. (default 0.1)
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)
num_images	integer	—	The number of images to generate. (default 1)
output_format	string (jpeg, png)	—	The format of the generated image. (default "jpeg")
image_url	any	—	The image URL to generate an image from.
raw	boolean	—	Generate less processed, more natural-looking images. (default false)

Run it

curl -s https://sooma.dev/v1/run \ -H "Authorization: Bearer $SOOMA_API_KEY" \ -H "Content-Type: application/json" \ -d '{"provider":"fal","endpoint":"/fal-ai/flux-pro/v1.1-ultra","input":{"prompt":"A cinematic photo of a lighthouse at dawn, soft light"}}'

Or ask your agent: it will call inspect for this schema and run it over MCP.