Bria Fibo

bria-fibo

Bria Fibo

bria-fibo

Bria Fibo is a JSON-native, open-source text-to-image model with structured prompting, negative prompts, and deterministic seed control for consistent compositions.

Added Jan 25, 2026

Approx. Price

$0.040 per image

Model Type

both

Settings

Generation controls available for this model.

Images Per Run

Up to 1

Output images

Input Images

Up to 1

Reference/edit images accepted • Route max 30 MB

Output Sizes

Square
Portrait
Landscape

Aspect Ratio

Default

1:1

Negative Prompt

Text

Default

N/A

Describe what to avoid in the output.

Number of Images

Default

1

Resolution

Default

1:1

Options (5)

1:1 (Square), 16:9 (Widescreen), 9:16 (Portrait), 4:5 (4:5) +1 more

Seed

Number

Default

-1

Control reproducibility (-1 for random).

Structured Prompt

Text

Default

N/A

Optional JSON or compact schema to guide composition.

Benchmarks

Human preference benchmarks sourced from Artificial Analysis.

Text to Image

#94 / 146

ELO

1076.0

Appearances

4,668

95% CI

-8/8

Release Date 2025-10 · Matched as FIBO

Artificial Analysis API

Compare Bria Fibo with similar models from the same provider or model family.