Skip to main content
Generate and edit images with FLUX 3 Image, the full FLUX 3 image model from Black Forest Labs. One route covers text-to-image, image editing and multi-reference generation with up to 10 reference images, and the prompt can carry bounding boxes that place each element. Try it in the browser: FLUX 3 Image API playground.

Model

Parameters

FLUX 3 Image has no seed, steps, guidance or negative_prompt. Output is a single JPG image.

Bounding boxes

Append a JSON array to the prompt, one row per element, and tag each element in the caption with its id (<cabin_1>). Each bbox is [top, left, bottom, right] on a 0 to 1000 grid at any aspect ratio.

Example Request

Multi-reference generation:

Response

Poll GET /v1/tasks/<task_id> or set a callback_url to receive the finished image URL.
Volume discounts are available for almost all models. Reach out at contact@unifically.com to discuss custom pricing.