Bria: FIBO 2.0 Text to Image

Generate an image from text with Bria FIBO 2.0, a model trained on structured captions for typography-led posters, editorial covers and precise layouts.

Input

The image to generate, described in sections.

Advanced settings

Leave empty for a new result each run. Enter a number to repeat one.

Output
Output
Example

Bir örnek deneyin

Bu iş akışı hakkında

Bria FIBO 2.0 generates and edits with one model and is trained on structured VGL captions, so a long, sectioned brief is followed closely: layout regions, exact wording and a fixed palette all land where the caption puts them. It also returns the structured prompt it derived, so the same image can be rebuilt or refined from JSON instead of prose. That makes it the rare text-to-image model for editorial covers, posters and typography-led layouts where wording has to be literal.

Graph: BriaImageGenerate (prompt, aspect_ratio 1:1, resolution 1MP, seed, moderation) -> SaveImage. Text in, one image out.