black-forest-labs/flux-kontext-pro/multi API

This document describes the input and output parameters for the black-forest-labs/flux-kontext-pro/multi model API, for you to refer to when using the interface.

Request Parameters

Request Body

Field Name	Type	Required	Default	Description
prompt	string	Conditionally Required	-	Prompt
model	string	Required	-	The model name used for this request, which is `black-forest-labs/flux-kontext-pro/multi`.
images	array(string)	Required	-	Multi-image editing, base64 data or image link http://xxx
n	int	Optional	1	Number of images to generate, range is 1~4
aspect_ratio	string	Optional	”1:1”	Aspect ratio of the image, in the format “width:height”, such as “16:9” or “1:1”
seed	int	Optional	-1	Random seed, used to control the randomness of the content generated by the model. If you want the generated content to remain consistent, you can use the same seed parameter value.
steps	int	Optional	20	Number of inferences, range 1~50
guidance_scale	float	Optional	2.5	The degree of consistency between the model output and the prompt, i.e., the freedom of the generated image; the larger the value, the smaller the freedom of the model, and the stronger the correlation with the user’s input prompt. Range [1, 10].
negative_prompt	string	Optional	-	Negative prompt, used to specify content that you do not want to appear in the generated image
response_format	string	Optional	”url”	Specifies the format of the generated image returned, default is `url`, can be `b64_json`

Response Parameters

Field Name	Type	Description
created	`integer`	Unix timestamp (in seconds) of when the request was created.
data	`array`	Information about the output images, including URLs or Base64 for image download. • When the format of the generated image is specified as url, the subfield of the corresponding parameter is url; • When the format of the generated image is specified as b64_json, the subfield of the corresponding parameter is b64_json. Note: The link will expire 7 days after generation, please be sure to save the image in time.
error	`Object`	Error information object
error.code	`string`	Error code
error.message	`string`	Error message
error.param	`string`	Request id

Example

OPENAI Compatible Interface

POST https://api.umodelverse.ai/v1/images/generations

Synchronous Request


curl --location 'https://api.umodelverse.ai/v1/images/generations' \
--header "Authorization: Bearer $MODELVERSE_API_KEY" \
--header 'Content-Type: application/json' \
--data '{
    "model": "black-forest-labs/flux-kontext-pro/multi",
    "prompt": "Convert to quick pencil sketch",
    "images": [
        "https://umodelverse-inference.cn-wlcb.ufileos.com/ucloud-maxcot.jpg",
        "data:image/png;base64,{image_base64_string}"
    ]
}'


import os
from openai import OpenAI
 
client = OpenAI(
    base_url=os.getenv("BASE_URL", "https://api.umodelverse.ai/v1"),
    api_key=os.getenv("API_KEY", "$MODELVERSE_API_KEY")
)
 
response = client.images.generate(
    model="black-forest-labs/flux-kontext-pro/multi",
    prompt="Convert to quick pencil sketch",
    extra_body={
        "images": [
            "https://umodelverse-inference.cn-wlcb.ufileos.com/ucloud-maxcot.jpg",
            "data:image/png;base64,{image_base64_string}"
        ]
    }
)
 
print(response.data[0].url)

Response


{
  "created": 1750667997,
  "data": [
    {
      "url": "https://xxxxx/xxxx.png",
      "b64_json": "data:image/png;base64,{image_base64_string}"
    }
  ],
  "usage": {
    "input_tokens_details": {}
  }
}


{
  "error": {
    "message": "error_message",
    "type": "error_type",
    "param": "request_id",
    "code": "error_code"
  }
}