fal.ai·Image generation

FLUX.1 [schnell]

/fal-ai/flux/schnellasync$0.0075 / megapixel

FLUX.1 [schnell] is a 12 billion parameter flow transformer that generates high-quality images from text in 1 to 4 steps, suitable for personal and commercial use. Returns hosted file URLs (download promptly; fal keeps them for a limited time). Billed per megapixel.

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

Input

accelerationstring
The speed of the generation. The higher the speed, the faster the generation. (default "none")
none, regular, high
promptstringrequired
The prompt to generate an image from.
enable_safety_checkerboolean
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)
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)
image_sizeany
The size of the generated image. (default "landscape_4_3")
num_inference_stepsinteger
The number of inference steps to perform. (default 4)
guidance_scalenumber
The CFG (Classifier Free Guidance) scale is a measure of how close you want the model to stick to your prompt when looking for a related image to show you. (default 3.5)
seedany
The same seed and the same prompt given to the same version of the model will output the same image every time.
output_formatstring
The format of the generated image. (default "jpeg")
jpeg, png

Field	Type	Required	Description
acceleration	string (none, regular, high)	—	The speed of the generation. The higher the speed, the faster the generation. (default "none")
prompt	string	yes	The prompt to generate an image from.
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)
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)
image_size	any	—	The size of the generated image. (default "landscape_4_3")
num_inference_steps	integer	—	The number of inference steps to perform. (default 4)
guidance_scale	number	—	The CFG (Classifier Free Guidance) scale is a measure of how close you want the model to stick to your prompt when looking for a related image to show you. (default 3.5)
seed	any	—	The same seed and the same prompt given to the same version of the model will output the same image every time.
output_format	string (jpeg, png)	—	The format of the generated image. (default "jpeg")

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/schnell","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.