- Prompt, up to 4 images
Input
- 21, from 5:1 to 1:5
Aspect ratios
- About 1 megapixel
Output size
- Licensed only (Bria)
Training data
About Bria Fibo 2.0
Bria Fibo 2.0 is Bria's image model, which Masonry runs through fal. It does two jobs. With a prompt alone it generates a new image, and Bria describes it as strongest on prompts that need real understanding, such as several subjects, spatial relationships, or knowledge-heavy scenes. With input images it makes targeted edits: swap a background, restage a product in a new scene, change the lighting, or adapt a campaign image, while keeping the product true to the original.
Bria states that Fibo 2.0 is trained only on licensed data. That matters to brands that need to know where their imagery comes from. In Masonry you can add up to four images, with the source first and up to three references after it, and refer to them in the prompt as <image_1>, <image_2>, and so on. Output is about one megapixel, in 21 aspect ratios from a 5:1 panorama to a 1:5 vertical.
Why teams choose Bria Fibo 2.0
Choose Bria Fibo 2.0 when provenance matters, since Bria trains it only on licensed data, and when the job is editing a real product image into a new scene rather than inventing one from scratch. It handles both generation and multi-image edits in one model. For the most photorealistic new imagery from a prompt alone, compare it with GPT Image 2.5 Sunburst or Nano Banana 2 on the same brief.
What Bria Fibo 2.0 can do
The capabilities that set Bria Fibo 2.0 apart and earn its place in a brief
Trained on Licensed Data
Bria states that Fibo 2.0 is trained only on licensed data, for teams that need clear provenance behind their brand imagery.
Product Restaging and Background Swaps
Give it a product photo and describe the new scene. fal lists background changes, product restaging, and campaign adaptations as the edit model's core jobs.
Up to Four Input Images
Add the source image first and up to three references after it, then name them in the prompt as <image_1>, <image_2>, and so on to say which element comes from where.
Strong on Complex Prompts
Bria describes Fibo 2.0 as strongest on reasoning- and knowledge-heavy prompts, such as scenes with several subjects or exact spatial relationships.
21 Aspect Ratios
Choose from 21 ratios at about one megapixel, from 5:1 and 4:1 banners through 1:1 and 4:5 feed posts to 9:16 stories and a 1:5 vertical.
Reproducible With a Seed
Set a seed to repeat a result or to compare one prompt change at a time while everything else stays fixed.
Where teams reach for Bria Fibo 2.0
- Restage a product photo in a new lifestyle scene
- Swap or clean up a product background for a store listing
- Adapt one campaign image to new seasons or markets
- Combine a product with a reference scene or style image
- Generate product and lifestyle concepts from a written brief
- Wide banners and tall stories from the same idea
Frequently asked questions
What teams need to know about creating with Bria Fibo 2.0 in Masonry
What is Bria Fibo 2.0?
Bria Fibo 2.0 is Bria's image model for text-to-image generation and instruction-based edits of up to four images. Bria states it is trained only on licensed data. Masonry runs it through fal.
Can Bria Fibo 2.0 edit my product photos?
Yes. Add the product photo as the first image and describe the change, such as a new background, a new scene, or new lighting. You can add up to three reference images after it.
How do I refer to multiple images in a prompt?
Name them by their order, <image_1> for the first image, <image_2> for the second, and so on. The first image is treated as the source.
What sizes does Bria Fibo 2.0 support?
21 aspect ratios at about one megapixel, from 5:1 and 4:1 panoramas through 1:1, 4:5, and 16:9 to 9:16 and 1:5 verticals.
Is Bria Fibo 2.0 trained on licensed data?
Bria states that Fibo 2.0 is trained only on licensed data. Review Bria's and fal's current terms for the rights your project needs.
How much does Bria Fibo 2.0 cost in Masonry?
Masonry bills each image in credits, and the editor shows the exact cost before you generate.
How should I prompt Bria Fibo 2.0 for edits?
State what to change and what must stay exactly the same, and name each input image by its slot. Short, specific instructions keep the product true to the source.
How does my team use Bria Fibo 2.0 in Masonry?
Open a Masonry canvas, pick Bria Fibo 2.0 from the model selector, and describe the image you need: a product shot, an ad creative, a social post. Masonry generates it, then you refine, edit, and combine Bria Fibo 2.0 with other models in one workspace.
Is Bria Fibo 2.0 free to try?
New Masonry accounts get 50 free credits to try GPT Image 2.5 Flare. Bria Fibo 2.0 is included in every paid plan, and the editor shows the exact credit cost before you generate.
How do I write good prompts for Bria Fibo 2.0?
For an edit, say what to change and what must stay the same, and name each image by its slot, for example "place the bottle from <image_1> on the marble counter from <image_2>, keep the label unchanged". For a new image, describe the subjects, where each one sits in the frame, the setting, and the light. Choose the aspect ratio for the placement first.
Who makes Bria Fibo 2.0?
Bria Fibo 2.0 is built by Bria. Inside Masonry it runs alongside 50+ image and video models, so your team can pick the right one for each brief without switching tools.
Start creating with Bria Fibo 2.0
Generate, edit, and compare across 50+ models in one workspace.
Guides for Bria Fibo 2.0
Prompt walkthroughs and examples from the Masonry blog
Explore more AI models
Compare Bria Fibo 2.0 with other models teams run in Masonry