Skip to main content
POST
/
v3
/
async
/
flux-1-kontext-dev
FLUX.1 Kontext Dev
curl --request POST \
  --url https://api.novita.ai/v3/async/flux-1-kontext-dev \
  --header 'Authorization: <authorization>' \
  --header 'Content-Type: <content-type>' \
  --data '
{
  "prompt": "<string>",
  "images": [
    "<string>"
  ],
  "fast_mode": true,
  "size": "<string>",
  "num_inference_steps": 123,
  "guidance_scale": 123,
  "num_images": 123,
  "seed": 123,
  "output_format": "<string>"
}
'
{
  "task_id": "<string>"
}

Documentation Index

Fetch the complete documentation index at: https://novita.ai/docs/llms.txt

Use this file to discover all available pages before exploring further.

FLUX.1 Kontext dev is a model with greatly improved prompt adherence and typography generation meet premium consistency for editing without compromise on speed.

​
Request Headers

​
Content-Type
string
required
Enum: application/json
​
Authorization
string
required
Bearer authentication format, for example: Bearer {{API Key}}.

​
Request Body

​
prompt
string
required
The prompt to generate an image from.
​
images
string[]
The images to generate an image from. Limit to a maximum of 4 images.
​
fast_mode
boolean
Whether to enable fast mode, which will generate videos more quickly but may reduce quality and lower the price.Default: false.
​
size
string
The size of the generated media in pixels (width*height). Range [256 ~ 1536 per dimension].
​
num_inference_steps
integer
The number of inference steps to perform. Default is 28. Range [1 ~ 50].
​
guidance_scale
number
The guidance scale to use for the generation. Default is 2.5. Range [1.0 ~ 20.0].
​
num_images
integer
The number of images to generate. Default is 1. Range [1 ~ 4].
​
seed
integer
The random seed to use for the generation. Default is -1. -1 means a random seed will be used. Range [-1 ~ 2147483647].
​
output_format
string
The format of the output image. Default is jpeg.
Enum: jpeg, png, webp

​
Response

​
task_id
string
required
Use the task_id to request the Task Result API to retrieve the generated outputs.