bria/image-3.2

Official View on Replicate →

Commercial-ready, trained entirely on licensed data, text-to-image model. With only 4B parameters provides exceptional aesthetics and text rendering. Evaluated to be on par to other leading models in the market

Capabilities

Negative Prompt Seed

Cost

Community model (estimated from hardware time)

Input Parameters

Name	Type	Description	Default	Constraints
`prompt` *	string	Text prompt for image generation	`—`	—
`aspect_ratio`	string	Aspect ratio for expansion. Either aspect_ratio or canvas_size with original_image_size/location must be provided. Can be a predefined string like '1:1', '16:9' etc. or a custom float between 0.5 and 3.0	`"1:1"`	1:1 2:3 3:2 3:4 4:3 4:5 5:4 9:16 16:9
`enhance_image`	boolean	Enhance image details and clarity	`false`	—
`guidance_scale`	number	Guidance scale (1-10)	`—`	min: 3, max: 5
`negative_prompt`	string	Negative prompt for image generation	`—`	—
`prompt_enhancement`	boolean	Enhance prompt for more creative output	`false`	—
`seed`	integer	Random seed. Set for reproducible generation	`—`	—

prompt required string

Text prompt for image generation

aspect_ratio string

Aspect ratio for expansion. Either aspect_ratio or canvas_size with original_image_size/location must be provided. Can be a predefined string like '1:1', '16:9' etc. or a custom float between 0.5 and 3.0

Default: "1:1"

1:1 2:3 3:2 3:4 4:3 4:5 5:4 9:16 16:9

enhance_image boolean

Enhance image details and clarity

Default: false

guidance_scale number

Guidance scale (1-10)

min: 3, max: 5

negative_prompt string

Negative prompt for image generation

prompt_enhancement boolean

Enhance prompt for more creative output

Default: false

seed integer

Random seed. Set for reproducible generation

Version: cd4f78ccda1e Updated: 2/26/2026 163.9K runs