Skip to main content
POST
/
v1
/
images
/
generations
Text-to-Image Generation
curl --request POST \
  --url https://www.anyfast.ai/v1/images/generations \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '
{
  "model": "flux-2-flex",
  "prompt": "A cute baby polar bear",
  "n": 1,
  "size": "1024x1024",
  "inference_steps": 25,
  "guidance_scale": 5.75,
  "output_format": "jpeg",
  "seed": 123
}
'
{
  "created": 1774002799,
  "data": [
    {
      "b64_json": "<string>"
    }
  ]
}

Authorizations

​
Authorization
string
header
required

Bearer authentication header of the form Bearer <token>, where <token> is your auth token.

Body

application/json
​
model
enum<string>
required

Model ID

Available options:
flux-2-flex
Example:

"flux-2-flex"

​
prompt
string
required

Text description of the image to generate.

Example:

"A cute baby polar bear"

​
n
integer
default:1

Number of images to generate.

Required range: 1 <= x <= 4
​
size
string

Output image size, e.g. 1024x1024. Supports up to 4MP resolution.

Example:

"1024x1024"

​
inference_steps
integer

Number of sampling steps. Low (6–20) for fast prototyping, high (40–50) for maximum fidelity.

Required range: 1 <= x <= 50
​
guidance_scale
number

Guidance scale. Controls how closely the model follows the prompt. Higher values produce more prompt-faithful results.

Required range: 1.5 <= x <= 10
​
output_format
enum<string>

Output image format.

Available options:
jpeg,
png
Example:

"jpeg"

​
seed
integer

Random seed for reproducible generation.

Response

Image generated successfully

​
created
integer
Example:

1774002799

​
data
object[]