fal.ai·Image generation

Ideogram Text to Image

/fal-ai/ideogram/v3async$0.06 / image

Generate high-quality images, posters, and logos with Ideogram V3. Features exceptional typography handling and realistic outputs optimized for commercial and creative use. 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

style_presetany
Style preset for generation. The chosen style preset will guide the generation.
num_imagesinteger
Number of images to generate. (default 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)
color_paletteany
A color palette for generation, must EITHER be specified via one of the presets (name) or explicitly via hexadecimal representations of the color with optional weights (members)
negative_promptstring
Description of what to exclude from an image. Descriptions in the prompt take precedence to descriptions in the negative prompt. (default "")
image_urlsany
A set of images to use as style references (maximum total size 10MB across all style references). The images should be in JPEG, PNG or WebP format
styleany
The style type to generate with. Cannot be used with style_codes.
expand_promptboolean
Determine if MagicPrompt should be used in generating the request or not. (default true)
rendering_speedstring
The rendering speed to use. (default "BALANCED")
TURBO, BALANCED, QUALITY
style_codesany
A list of 8 character hexadecimal codes representing the style of the image. Cannot be used in conjunction with style_reference_images or style
promptstringrequired
prompt
seedany
Seed for the random number generator
image_sizeany
The resolution of the generated image (default "square_hd")

Field	Type	Required	Description
style_preset	any	—	Style preset for generation. The chosen style preset will guide the generation.
num_images	integer	—	Number of images to generate. (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)
color_palette	any	—	A color palette for generation, must EITHER be specified via one of the presets (name) or explicitly via hexadecimal representations of the color with optional weights (members)
negative_prompt	string	—	Description of what to exclude from an image. Descriptions in the prompt take precedence to descriptions in the negative prompt. (default "")
image_urls	any	—	A set of images to use as style references (maximum total size 10MB across all style references). The images should be in JPEG, PNG or WebP format
style	any	—	The style type to generate with. Cannot be used with style_codes.
expand_prompt	boolean	—	Determine if MagicPrompt should be used in generating the request or not. (default true)
rendering_speed	string (TURBO, BALANCED, QUALITY)	—	The rendering speed to use. (default "BALANCED")
style_codes	any	—	A list of 8 character hexadecimal codes representing the style of the image. Cannot be used in conjunction with style_reference_images or style
prompt	string	yes	prompt
seed	any	—	Seed for the random number generator
image_size	any	—	The resolution of the generated image (default "square_hd")

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/ideogram/v3","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.