Skip to main content
POST
/
flux
/
v1
/
{model}
flux generate image
curl --request POST \
  --url https://api.cometapi.com/flux/v1/{model} \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '
{
  "prompt": "Hello"
}
'
{
  "id": "<string>",
  "polling_url": "<string>"
}

​
Overview

The /flux/v1/\{model\} endpoint generates high-quality images from text prompts using Black Forest Labs’ Flux model family. Simply swap the model ID in the URL path to switch between different Flux variants.
Due to significant differences in parameter lists across Flux series models, please refer to the official documentation for detailed usage instructions. The parameter list provided here is for reference only.After generation, use the /flux/v1/get_result endpoint to query generated images or monitor process status.Image URLs returned by BFL’s service expire in approximately 10 minutes. Save the generated results promptly.

Authorizations

​
Authorization
string
header
required

Bearer token authentication. Use your CometAPI key.

Headers

​
Content-Type
string

Must be application/json.

Path Parameters

​
model
string
required

Flux model variant to use, e.g. flux-pro-1.1, flux-pro, flux-dev, flux-pro-1.1-ultra.

Body

application/json
​
prompt
string
default:Hello
required

Text prompt describing the image to generate.

​
image_prompt
string

URL of a reference image to guide the generation style or content.

​
width
integer

Output image width in pixels. Must be a multiple of 32. Range varies by model.

​
height
integer

Output image height in pixels. Must be a multiple of 32. Range varies by model.

​
steps
integer

Number of diffusion steps. Higher values improve quality but increase latency.

​
prompt_upsampling
boolean

When true, automatically enhances the prompt for more detailed results.

​
seed
integer

Random seed for reproducible outputs. Omit for random generation.

​
guidance
number

Guidance scale controlling how closely the output follows the prompt. Higher values increase prompt adherence.

​
safety_tolerance
integer

Safety filter tolerance level. Higher values are more permissive. Range: 0–6.

​
interval
integer

Diversity interval. Higher values produce more varied outputs at the cost of prompt adherence.

​
output_format
string

Output image format. Supported values: jpeg, png.

​
webhook_url
string

URL to receive a POST notification when the task completes.

​
webhook_secret
string

Secret string included in webhook payloads for request verification.

Response

200 - application/json

OK

​
id
string
​
polling_url
string