v2

latestOpenAPI 3.1.02026-08-01302833.9 KB

Unified Agent APIs

Unified Image Generate

Generate images from text prompts. Returns base64-encoded image bytes.

Response data contains b64_json (base64 string) and content_type (MIME type). Uses Gemini Flash models only (retried); fails gracefully so callers continue without an image.

post/v1/images/generate

Request body

promptstring required

Describe a CONCRETE, grounded scene: real people, real objects, physical screens and devices, natural light, editorial photography quality (or a clean minimal illustration of the actual concept). Words like 'futuristic', 'holographic', 'glowing', or neon-tech scenery produce the same generic AI-cliche image every time; describe the present-day, physical version of the scene instead.

aspect_ratiostring

image_sizestring

reference_image_urlstring nullable

skip_default_styleboolean

Leave false (recommended). False applies the house visual style guidance (grounded realistic imagery, avoids overused AI-tech cliches). Set true ONLY when you are deliberately providing complete art direction of your own and want zero house styling.

Response

Successful Response

{"stackTrail":"paths:/v1/images/generate:post:responses:200:content:application/json:schema","oasType":"schema","type":"unknown"}