FIBO Models by BRIA
BRIA releases · 2 in the last 12 monthsChangelog →
3 models2025–2026
Last refreshed 2026-10-20. Next refresh: weekly.
Capabilities
Vision2 of 3 models
MultimodalAll models
About
Bria AI's FIBO (Foundation Image Base with Order) model family — the first open-source JSON-native text-to-image model. Trained exclusively on licensed data, FIBO uses structured JSON prompts (~1,000 words each) encoding 100+ visual attributes for deterministic, brand-safe image generation.
Decision facts
Current Variants
Use-when guidance is based on each model's tracked capabilities, context window, release date, and replacement status.
3 in view
FIBO 2.0Current
Use when the workload needs image generation and multimodal inputs.
2026-10image generationmultimodal inputs
FIBO 2.0 EditCurrent
Use when the workload needs image editing and multimodal inputs.
2026-10image editingmultimodal inputs
FIBOCurrent
Use when the workload needs image generation, 8B parameters, and multimodal inputs.
2025-11image generation8B parametersmultimodal inputs
| Model | Use when | Released | Signals | Status |
|---|---|---|---|---|
| FIBO 2.0 | Use when the workload needs image generation and multimodal inputs. | 2026-10 | image generationmultimodal inputs | Current |
| FIBO 2.0 Edit | Use when the workload needs image editing and multimodal inputs. | 2026-10 | image editingmultimodal inputs | Current |
| FIBO | Use when the workload needs image generation, 8B parameters, and multimodal inputs. | 2025-11 | image generation8B parametersmultimodal inputs | Current |
Release Timeline
2 release groups2026-10
2 current
FIBO 2.0
Currentimage generationmultimodal inputs
FIBO 2.0 Edit
Currentimage editingmultimodal inputs
2025-11
1 current
FIBO
Currentimage generation8B parametersmultimodal inputs
Specifications(3 models)
| Model | Released | Parameters | Vision | Multimodal |
|---|---|---|---|---|
| FIBO 2.0 | 2026-10 | — | Yes | Yes |
| FIBO 2.0 Edit | 2026-10 | — | Yes | Yes |
| FIBO | 2025-11 | 8B | No | Yes |
