Create text-to-image task - Flux API

This is provided as part of the Flux API from PiAPI. available models:

Qubico/flux1-dev

Qubico/flux1-schnell

Qubico/flux1-dev-advanced
Check Flux with LoRA and Controlnet to learn how to send Flux with LoRA and Controlnet task.
Check Flux with Redux and Fill to learn how to send Flux with variation, inpaint and out paint task.

Below is an example of a text-to-image request and response.

Request

Header Params

X-API-Key

string

required

Your API KEY used for request authorization

Body Params application/json

model

enum<string>

required

the model name, can be Qubico/flux1-dev or Qubico/flux1-schnell or Qubico/flux1-dev-advanced

Allowed values:

Qubico/flux1-schnellQubico/flux1-devQubico/flux1-dev-advanced

task_type

enum<string>

required

Allowed values:

txt2imgimg2imgtxt2img-loraimg2img-lorafill-inpaintfill-outpaintredux-variationcontrolnet-lora

input

object

required

the input param of the flux task

prompt

string

required

negative_prompt

string

optional

denoise

number

optional

<= 1> 0

Default:

0.7

guidance_scale

number

optional

Guidance scale for image generation. High guidance scales improve prompt adherence at the cost of reduced realism.

>= 1.5<= 5

width

integer

optional

can be used in txt2img ONLY, width*height cannot exceed 1048576

height

integer

optional

can be used in txt2img ONLY, width*height cannot exceed 1048576

batch_size

number

optional

number of images, only works for schnell at the moment. Price will be
batch_size * (price for one generation)

>= 1<= 4

Default:

lora_settings

array [object {2}]

optional

Check Flux with LoRA and Controlnet

control_net_settings

array [object {2}]

optional

Check Flux with LoRA and Controlnet

config

object

optional

webhook_config

object

optional

Webhook provides timely task notifications. Check PiAPI webhook for detail.

service_mode

enum<string>

optional

This allows users to choose whether this specific task will get processed under PAYG or HYA mode. If unspecified, then this task will get processed under whatever mode (PAYG or HYA)
the user chose on the workspace setting of your account.

public means this task will be processed under PAYG mode.

private means this task will be processed under HYA mode.

Allowed values:

publicprivate

Example

{
  "model": "Qubico/flux1-dev",
  "task_type": "txt2img",
  "input": {
    "prompt": "a little cat",
    "width": 1024,
    "height": 1024
  }
}

Request samples

Shell

JavaScript

Java

Swift

PHP

Python

HTTP

Objective-C

Ruby

OCaml

Dart

Responses

🟢200Success

application/json

Body

code

integer

required

data

object

required

task_id

string

required

model

string

required

task_type

string

required

status

enum<string>

required

Hover on the "Completed" option and you coult see the explaintion of all status: completed/processing/pending/failed/staged

Allowed values:

CompletedProcessingPendingFailedStaged

input

object

required

output

object

required

meta

object

required

detail

null

required

logs

array [object]

required

error

object

required

message

string

required

If you get non-null error message, here are some steps you chould follow:

Check our common error message

Retry for several times

If you have retried for more than 3 times and still not work, file a ticket on Discord and our support will be with you soon.

Example

{
    "code": 200,
    "message": "success",
    "data": {
        "task_id": "0f647527-12bd-48b1-b813-111111111",
        "model": "Qubico/flux1-dev", 
        "task_type": "txt2img",
        "status": "", // pending/processing/failed/completed
        "input": {}, 
        "output": {}, 
        "meta": { 
        },
        "logs": [],
        "error": {
            "code": 1100,
            "message": ""
        } 
    }
}

Text to Image

Request

Request samples

Responses