← All models
Fibo 2.0 Generate is Bria's text-to-image model, strongest on reasoning and knowledge-heavy prompts the ones that need real understanding, not just a style match. Trained only on licensed data, with clear commercial rights.
images
Details
- Accepts
- text
Pricing
- Price
- 5 cr / image
Prices in credits (1 credit = $0.01).
Data schema
Input
| Field | Type | Description |
|---|---|---|
| vgl | — | A VGL (Visual Generation Language) document: the structured JSON description of the scene. Alone, the model renders it as-is. With 'prompt', VGL changes it by the prompt (refine) and the result is rendered. Accepts what a previous request returned. Not with 'image_url' or 'style'. |
| seed | integer | Random seed for reproducibility, 0 to 2147483647. |
| style | — | A style for the generated image. Requires 'prompt'; not with 'image_url', 'vgl' or 'negative_prompt'. |
| prompt | — | What to generate, in free-form text. It is expanded into a VGL, which is returned. With 'vgl', the change to make to it. |
| image_url | — | A reference image (inspire mode). With 'prompt', VGL uses it as a visual reference for the prompt's scene and generates a new image of that scene, not the image. Alone, the VGL describes the image itself, so the result is a close variation of it. Not with 'vgl'. |
| sync_mode | boolean | If true, returns the image directly in the response (increases latency). |
| aspect_ratio | stringenum: 1:1, 1:2, 1:3, 1:4, 1:5, 2:1… | Aspect ratio of the image, at about one megapixel. Options: 1:1, 1:2, 1:3, 1:4, 1:5, 2:1, 2:3, 3:1, 3:2, 3:4, 4:1, 4:3, 4:5, 5:1, 5:4, 9:16, 9:21, 10:16, 16:9, 16:10, 21:9 |
Output
| Field | Type | Description |
|---|---|---|
| vgl | object | The VGL the image was generated from. |
| image | — | The generated image. |
| images | array | Single-element list holding the same image, as the sibling FIBO apps return. |