Generate Structured Prompt - Lite

Creates a new detailed, machine-readable structured prompt in JSON format for the speed-optimized Fibo Lite Pipeline.

This endpoint uses Bria's standard FIBO-VLM bridge (open-source, available on Hugging Face) to generate the prompt. It only returns the JSON string and does not generate an image.

Why use this endpoint?

This endpoint decouples the "intent translation" step from the "image generation" step, giving you maximum flexibility.

• It's Optional: The same structured prompt generation happens automatically behind the scenes when using /v2/image/generate/lite.
• Control & Auditability: Allows for a "human-in-the-loop" to inspect, programmatically edit, or version the JSON before generating an image (e.g., for a custom UI).
• Consistency & Automation: Generate one structured_prompt and pass it to /v2/image/generate/lite multiple times to create consistent, auditable variations.
• Local Deployment Support: This bridge is designed to pair seamlessly with the Fibo Lite text-to-image model. This combination enables fully local, on-prem deployment and unlocks Fibo Lite's faster inference speeds. Contact <a href="mailto:support@bria.ai">support@bria.ai</a> for more information.

The resulting structured_prompt can be used as input for the /v2/image/generate/lite endpoint.

Input Combination Rules

The request body must use exactly one of the following combinations:

• Text Only: prompt
• Image Only: images
• Image and Text: images and prompt
• Structured Prompt and Text: structured_prompt and prompt

---

** API Access **

You can register and access the API Token through Bria's platform <a href="https://platform.bria.ai/console/account/api-keys" target="_blank">by clicking here</a>.