Klein

Klein provides synchronous image generation and editing from text prompts and reference images. A single endpoint handles all workflows — the API automatically selects the right one based on the number of images you provide.

Quick Start

Get an API key.
Submit a generation request: POST /v1/generate with Authorization: Bearer YOUR_API_KEY.
Receive the generated image as raw PNG bytes in the response body.

Endpoint

Method	Path	Description
`POST`	`/v1/generate`	Generate or edit an image (workflow auto-selected by image count)

See API: Image Generation for full endpoint documentation.

Workflow Selection

The workflow is determined by the number of reference images provided:

Reference Images	Workflow	Description
0	Text-to-image	Generates from text prompt only
1	Image-to-image	Edits a single reference image
2–4	Multi-reference	Generates using multiple reference images

Parameters

Parameter	Required	Default	Description
`prompt`	Yes	-	Text description of the image to generate
`model`	No	flux2-klein-4b	Model identifier. Use `flux2-klein-4b`
`images`	No	[]	Uploaded image files (priority over image_uris)
`image_uris`	No	-	JSON array of URLs or base64 data URIs
`aspect_ratio`	No	landscape	Output aspect ratio

Error Responses

Errors are returned in a unified JSON format:

json Copy

{
  "detail": "Error message description"
}

Status Code	Description
401	Authentication failed due to a missing or invalid API key
422	Request parameters failed validation
504	Generation exceeded the allowed time limit
500	Unexpected server error

Limits

Limit	Value
Maximum Reference Images	4

Available aspect ratios and their corresponding resolutions:

Aspect Ratio	Resolution
square	1024 x 1024
landscape	1344 x 768
portrait	768 x 1344
photo	1248 x 832
photo_v	832 x 1248
standard	1184 x 896
standard_v	896 x 1184
wide	1568 x 672

FLUX[klein]

Input

Output