Bria Text-to-Image Fast

bria-text-to-image-fast

Image generationby Bria

Bria's Text-to-Image model with perfect harmony of latency and quality. Trained exclusively on licensed data for safe and risk-free commercial use. Available also as source code and weights. For access to weights:

images

Try in Studio →

Details

Accepts: text

Pricing

Price: 3.5 cr / request

Prices in credits (1 credit = $0.01).

Data schema

Input

Field	Type	Description
seed	—	The same seed and the same prompt given to the same version of the model will output the same image every time.
medium	stringenum: photography, art	Which medium should be included in your generated images. This parameter is optional.
promptrequired	string	The prompt you would like to use to generate images.
guidance	array	Guidance images to use for the generation. Up to 4 guidance methods can be combined during a single inference.
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.
num_images	integer	How many images you would like to generate. When using any Guidance Method, Value is set to 1.
aspect_ratio	stringenum: 1:1, 2:3, 3:2, 3:4, 4:3, 4:5…	The aspect ratio of the image. When a guidance method is being used, the aspect ratio is defined by the guidance image and this parameter is ignored.
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.
negative_prompt	string	The negative prompt you would like to use to generate images.
prompt_enhancement	boolean	When set to true, enhances the provided prompt by generating additional, more descriptive variations, resulting in more diverse and creative output images.
num_inference_steps	integer	The number of iterations the model goes through to refine the generated image. This parameter is optional.

Output

Field	Type	Description
seed	integer	Seed value used for generation.
images	array	The generated images