briaai / BRIA-2.1

BRIA 2.1: The Ultimate Text-to-Image Model with Full Legal Liability for Enterprises

BRIA 2.1 excels in producing images across various aspect ratios and boasts enhanced aesthetics compared to its predecessor, BRIA 2.0.

Our models, are exclusively trained on licensed data, for which we reward the data owners based on the impact of their contribution to the generation. By harnessing proprietary and patented algorithms, BRIA has developed a unique attribution engine for this purpose. Consequently, we have licensed the foundation models for commercial use. For more information, please visit our website .

BRIA 2.1, in particular, offers full legal liability coverage for copyright and privacy infringements, as it was trained exclusively on licensed data from our esteemed data partners. Therefore, the images it generates are safe for commercial use and include harmful content mitigation. Our dataset does not contain copyrighted materials, such as fictional characters, logos, trademarks, public figures, harmful content, or privacy-infringing content.

Get Access to the source code and pre-trained model

Interested in BRIA 2.1? Our Text-to-Image Model is available for purchase.

Purchasing access to BRIA 2.1 ensures royalty management and full liability for commercial use.

Are you a startup or a student? We encourage you to apply for our specialized Academia and Startup Programs to gain access. These programs are designed to support emerging businesses and academic pursuits with our cutting-edge technology.

Contact us today to unlock the potential of BRIA 2.1!

By submitting the form above, you agree to BRIA’s Privacy policy and Terms & conditions .

How to test BRIA for free?

You can test BRIA’s models and platform for free in three ways before making a purchase: - Get 1,000 free API calls per month by registering to the Bria open platform. - Try it out for free in our playground - Experience it for free with our demos

Model Description

• Developed by: BRIA AI
• Model type: Latent diffusion text-to-image model
• License: bria-2.1 Licensing terms & conditions .
• Purchase is required to license and access the model.
• Model Description: BRIA 2.1 is a text-to-image model trained exclusively on a professional-grade, licensed dataset. It is designed for commercial use and includes full legal liability coverage.
• Resources for more information: BRIA AI

Code example using Diffusers

pip install diffusers

from diffusers import DiffusionPipeline
import torch

pipe = DiffusionPipeline.from_pretrained("briaai/BRIA-2.1", torch_dtype=torch.float16, use_safetensors=True)
pipe.to("cuda")


prompt = "A portrait of a Beautiful and playful ethereal singer, golden designs, highly detailed, blurry background"
negative_prompt = "Logo,Watermark,Text,Ugly,Morbid,Extra fingers,Poorly drawn hands,Mutation,Blurry,Extra limbs,Gross proportions,Missing arms,Mutated hands,Long neck,Duplicate,Mutilated,Mutilated hands,Poorly drawn face,Deformed,Bad anatomy,Cloned face,Malformed limbs,Missing legs,Too many fingers"

images = pipe(prompt=prompt, negative_prompt=negative_prompt, height=1024, width=1024).images[0]