POST
/
model
/
infer
/
flux
curl --request POST \
  --url https://http.flux.proxy.prod.s9t.link/model/infer/flux \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '{
  "prompt": "Minimalist photography, beautiful mermaid with long hair covered with seashells and seagras, under water, sad face, heterochromia eyes blue and black, 8k, intricate detailed, eyes closed",
  "height": 1024,
  "width": 1024,
  "seed": 129232030,
  "num_inference_steps": 50,
  "num_images_per_prompt": 1,
  "guidance_scale": 7,
  "negative_prompt": "cartoon-like",
  "lora_weights": ""
}'
{
  "images": [
    null
  ],
  "time_taken": 123,
  "duration": 123,
  "seed": 123
}

Authorizations

​
Authorization
string
header
required

JWT token for authentication

Body

application/json
​
prompt
string
required

Text description of the image to generate

​
height
integer
default:1024

Height of the generated image in pixels

Required range: 256 <= x <= 1024
​
width
integer
default:1024

Width of the generated image in pixels

Required range: 256 <= x <= 1024
​
seed
integer

Random seed for reproducible generation

​
num_inference_steps
integer
default:50

Number of denoising steps

Required range: 1 <= x <= 150
​
num_images_per_prompt
integer
default:1

Number of images to generate

Required range: 1 <= x <= 4
​
guidance_scale
number
default:7

How closely to follow the prompt

Required range: 1 <= x <= 20
​
negative_prompt
string

Text description of what to avoid in the generated image

​
lora_weights
string
default:

LoRA weights configuration

Response

200
application/json
Successful image generation
​
images
file[]
required

Array of generated images in base64 format

​
time_taken
number
required

Inference time in seconds

​
duration
number
required

Total processing time including queuing in seconds

​
seed
integer

The seed used for generation