8B DiT model trained on 100% licensed data with JSON-native structured prompts — the first enterprise-grade image model with full IP indemnification and EU AI Act compliance.
Generation, editing, and utility endpoints — all trained on 100% licensed data.
8B text-to-image with structured JSON prompts
8-step distilled variant (~10x faster)
JSON prompt expansion without image generation
Instruction-based image editing
Multi-image composition
Lighting adjustment and transfer
Style transfer between images
Every model on Runflow is scored per vertical — not generic leaderboard numbers. Scores come from domain-expert evaluation on real production prompts.
| Use Case | Assessment | Notes |
|---|---|---|
| Portrait | Pending | Portrait quality |
| Fashion | Pending | Fashion quality |
| Product | Pending | Product quality |
| Creative | Pending | Creative quality |
Full parameter reference for the bria-fibo-generate model endpoint.
| Parameter | Type | Description |
|---|---|---|
| prompt | string | Text prompt for image generation. Short prompts are automatically expanded into structured JSON with 1,000+ words covering 100+ visual attributes. |
| structured_prompt | object | Structured JSON prompt with explicit control over lighting, camera, composition, DoF, color palette, and artistic style. Use instead of or alongside text prompt. |
| image_url | string | Reference image for Inspire mode. The model extracts a structured prompt from the image, merges with your creative direction, and generates a new image. |
| resolution | string | Output resolution tier. Options: "1MP" (~1024×1024), "4MP" (~2048×2048). Default: "1MP". |
| aspect_ratio | string | Output aspect ratio. Options: 1:1 (default), 2:3, 3:2, 3:4, 4:3, 4:5, 5:4, 9:16, 16:9. |
| steps_num | integer | Inference steps. 50 for max quality, 30–40 for balanced. Range: 20–50. Default: 50. |
| negative_prompt | string | Describe what to exclude from the generated image. |
| seed | integer | Reproducibility seed. Default: 5555. |
| sync_mode | boolean | If true, returns the image directly in the response. |
Flux AI models are available on many platforms. Here's what makes the Runflow image generation API different.
Every image in FIBO's training set is licensed and rights-cleared from 30+ premium content partners including Getty Images and Envato. Full IP indemnification for enterprise use.
The first model natively trained on structured JSON captions (~1,000 words, 100+ visual attributes). Control lighting, camera, composition, DoF, color palette, and artistic style with precision.
Generate (text-to-image with auto JSON expansion), Refine (modify specific attributes while preserving everything else), and Inspire (reference image + creative direction).
First AI provider to fully comply with the EU AI Act. GDPR-compliant training data with attribution traceability and content moderation built in.
Spotify-inspired model that programmatically compensates data owners based on their influence on each generated output — ethical AI by design.
Same API, different strengths. Switch models with one parameter change.
Black Forest Labs
FLUX.1 [dev] is a 12B-parameter text-to-image model by Black Forest Labs. Open-w…
ByteDance
Seedream 4.5 by ByteDance — unified generation and editing in one model. Strong…
ByteDance
Seedream 4 by ByteDance — unified generation and editing model with photorealism…
Nano Banana 2 by Google — fast image generation across 4 resolution tiers (0.5K–…
OpenAI
GPT-Image 1.5 by OpenAI — high-fidelity images with strong prompt adherence. Thr…
Nano Banana Pro by Google — premium image generation with sharp detail and natur…
Get API access in minutes. No GPU setup, no infrastructure to manage. Pair with Sentinel to control the quality of every AI-generated image you ship.