Loading playground
Input
Additional Settings
Customize your input with more control.
Result
Idle
Customize your input with more control.
Customize your input with more control.
Structured Prompt will be populated from your instructions or uploaded assets, giving you predictable, repeatable control without any guesswork.
Customize your input with more control.
Your request will cost $0.04 per image
A campaign image can depend on more than a subject and a style: three objects in a particular order, a material that catches the light, or a scene whose parts need to fit together. Fibo 2.0 Generate turns a written brief into an image. Bria describes reasoning- and knowledge-heavy prompts as the model's strengths and states that it is trained on licensed data.
The endpoint expands free-form text into a structured prompt and returns that prompt with the image. The same structured prompt can be supplied directly in a later request, making the interpreted brief available for inspection and reuse.
prompt is expanded automatically; vgl is used directly.5:1 to 1:5, at approximately one megapixel.An editorial still life on pale peach paper: a cobalt glass cylinder on the left, a cut blood orange in the center, and a folded cream linen napkin on the right. Afternoon light enters from the left, casting all three shadows toward the lower right. The glass refracts blue light onto the paper. Overhead composition with space above the objects for a campaign headline.
The prompt describes both the objects and how they relate: position, shared lighting, and a material effect. It can be rendered as a square feed image, a wide banner, or a vertical composition by changing aspect_ratio.
| Control | Behavior |
|---|---|
prompt | Free-form description, expanded into a structured prompt. |
vgl | Uses an existing structured prompt directly. |
aspect_ratio | One of 21 formats; defaults to 1:1. |
seed | Defaults to 5555. |
sync_mode | Returns the image directly in the response; adds latency. |
The response contains image, the same image in the single-item images list, and vgl. The optional image_url provides a visual reference for the prompt, or produces a close variation when used alone. It cannot be combined with vgl or style.
What is Fibo 2.0 Generate? The text-to-image endpoint of Bria's Fibo 2.0. It accepts a prompt, optionally with a reference image, and returns an image.
What is it best at? Reasoning- and knowledge-heavy prompts, where the model has to understand the scene or the subject, not just match a style.
Can I guide it with a reference image?
Yes, with one reference image in image_url alongside the text prompt, or on its own for a close variation. Multi-reference input is available on Fibo 2.0 Edit. Reference-image input cannot be combined with vgl or style.
What aspect ratios does it support? It supports 21 aspect ratios, from panoramic 5:1 through square 1:1 to tall vertical 1:5, at approximately one megapixel. The full list is available in the API schema.
How fast is it? Bria reports under 2 seconds for the model and under 5 seconds end to end through the Bria API. These are Bria API measurements; latency on fal has not been independently verified.
Is it safe for commercial use? Yes. Fibo 2.0 is trained only on licensed data, with clear commercial rights.
Can I edit the result? Yes. Fibo 2.0 also edits images on the separate Fibo 2.0 Edit endpoint.
How is it priced? Your request will cost $0.04 per image.
For changes to an existing image, including reference-guided or masked edits, use Fibo 2.0 Edit.