Add Bria 3.2 pipeline - next-generation commercial-ready text-to-image model

[galbria]

Model/Pipeline/Scheduler description

TL;DR

Bria 3.2 is the next-generation commercial-ready text-to-image model. With just 4 billion parameters, it provides exceptional aesthetics and text rendering, evaluated to provide on par results to leading open-source models, and outperforming other licensed models.

In addition to being built entirely on licensed data, 3.2 provides several advantages for enterprise and commercial use:

• Efficient Compute - the model is X3 smaller than the equivalent models in the market (4B parameters vs 12B parameters other open source models)
• Architecture Consistency: Same architecture as 3.1—ideal for users looking to upgrade without disruption.
• Fine-tuning Speedup: 2x faster fine-tuning on L40S and A100.

i will be more then happy to help and implement or refactor everything that can help you add us to the glorious diffusers library 🚀

Open source status

• The model implementation is available.
• The model weights are available (Only relevant if addition is not a scheduler).

Provide useful links for the implementation

Model weights: briaai/BRIA-3.2
Official implementation: https://github.com/Bria-AI/bria-3.2

[DN6]

Hi @galbria happy to include in Diffusers. It looks like the source code and weights are already Diffusers compatible. Would you be able to open a PR to add the model/pipeline?

[galbria]

Hey @DN6 i've opennd a PR