Bria Launches Open-Source Text-To-Image AI Model That Matches Industry-Leading Performance At One-Third The Size

Bria Next-Gen Text to Image Model Beats Other Models With Only 4B Parameters, Built Entirely on Licensed Data for Enterprise Development

NEW YORK, June 26, 2025 /PRNewswire/ -- Bria, the visual generative responsible AI platform, today announced the release of its third-generation model, now available as the first fully open-source text-to-image model from Bria. This release continues Bria's commitment to training exclusively on fully licensed data. 

Research shows that Bria's new open-source model performance is comparable to leading open-source models, with 66% fewer parameters, while training only on licensed data. This study also shows that Bria models are twice as easy to fine-tune, which means that one needs 50% less compute and data to achieve the same result.

To effectively evaluate the performance of models, Bria selected all market-available models that met at least one of the following criteria: (1) built as open source, or (2) built only using licensed data. Two leading open-source models and one licensed model met the study's criteria. The test included blind preference evaluations among thousands of design professionals, who selected which model output they preferred when using the same prompts across all four models. The test included blind preference evaluations among thousands of design professionals, who selected which model output they preferred when using the same prompts across all four models. 

As part of the evaluation, participants were asked to assess the model's Aesthetic Quality, prompt adherence, text rendering accuracy, and, finally, to evaluate the Fine-Tuning Effectiveness and Computational Performance of the models. After the evaluation, a statistical analysis was performed to cluster the different models across these criteria. 

"While the industry races to build ever-larger models using scraped web data, we've proven that smaller, ethically-trained models can deliver equivalent performance," said Yair Adato, CEO of Bria. "Our new source code available model demonstrates that respecting creators' rights and building efficient AI aren't mutually exclusive—they're complementary strategies that benefit everyone in the ecosystem."

The third-generation model is available immediately through Hugging Face, including a complete development framework with ControlNets, IP adaptors, and other auxiliary models, as well as Bria's platform-as-a-service offering. Bria's platform optimizes for developer velocity with built-in content moderation, enterprise security standards, and support for multiple access methods, including MCP (Model Context Protocol) servers, a Plugin for Figma, and Adobe Creative Suite.

Addressing the Creator Economy Challenge

Bria's approach represents a fundamental shift in how AI companies engage with the creative community. By partnering directly with artists, photographers, and content creators, Bria ensures that those whose work powers AI innovation share in its economic benefits.

Unlike competitors relying on internet-scraped data with unclear origins, Bria's approach, which uses only licensed content, eliminates the copyright and trademark risks that have prevented many corporations from adopting AI technology. The company ensures fair compensation for all content creators contributing to its training data.

"Every image generated by Bria represents a vote for a sustainable creative ecosystem," added Vered Horesh, CSO at Bria. "We're proving that AI can amplify artistic work rather than exploit it, creating value for all intellectual property holders, including the entire premium content ecosystem that surrounds Hollywood."

About Bria

Bria is the Visual Generative AI Platform-as-a-Service (PaaS) purpose-built for developers and builders to develop, deploy, and manage AI-powered visual solutions at scale. Its enterprise-grade platform delivers unprecedented speed and flexibility along with the safety, compliance, and quality needed for commercial production. Bria's foundation models, trained on 100% licensed data from 30+ partners, ensure legal compliance with proper attribution to data owners and artists.

Bria provides technical teams with full access to source code and weights, as well as production-grade APIs and SDKs, allowing them to incorporate these AI building blocks into their preferred development environments with flexibility. Bria's pre-built pipelines offer the fastest path to market-ready visual AI implementation. At the same time, advanced teams utilize our ControlNets, LoRAs, and LCMs to achieve pixel-perfect precision and maximum control over visual outputs. Bria offers comprehensive IP/privacy indemnity and EU AI Act-compliant architecture, along with flexible commercial terms that leverage existing cloud commitments.

Leading advertising, gaming, media, and retail enterprises rely on Bria to deliver precise, on-brand visual content at scale. Bria is pioneering the future of premium content generation, where visual AI, data ownership, and artistic contribution coexist to create sustainable value. For technical documentation, visit Bria.ai.

Media Contact

Sarah Small
Headline Media
sarah.small@headline.media 
IL:+972 52 214 8601 
US:+1 929 255 1449 
UK:+44 203 807 1858 

View original content:https://www.prnewswire.com/news-releases/bria-launches-open-source-text-to-image-ai-model-that-matches-industry-leading-performance-at-one-third-the-size-302492468.html

SOURCE Bria