Image

Generate image from text prompt

post

Generate an image from a text prompt using FLUX models.

Available Models: black-forest-labs/FLUX-2-pro

Required Parameters

Parameter	Type	Description
prompt	string	Text description of the image

Optional Parameters

Parameter	Type	Default	Description
model	string	black-forest-labs/FLUX-2-pro	Image generation model
width	integer	1024	Image width (min 64, multiple of 32)
height	integer	1024	Image height (min 64, multiple of 32)
seed	integer	-	Random seed for reproducibility
safety_tolerance	integer	2	Safety level (0=strictest, 6=least strict)
output_format	string	png	Output format: png or jpeg
input_image	string	-	Reference image 1 as base64
input_image_2	string	-	Reference image 2 as base64
input_image_3	string	-	Reference image 3 as base64
input_image_4	string	-	Reference image 4 as base64

Response

{
  "images": ["base64_encoded_image..."],
  "model": "black-forest-labs/FLUX-2-pro",
  "width": 1024,
  "height": 1024
}

Async Mode

Set async: true to get a task_address immediately and poll for results.

Header parameters

x-api-keyany ofOptional

stringOptional

or

nullOptional

Body

application/json

Request schema for FLUX image generation.

Uses Black Forest Labs FLUX models for high-quality text-to-image generation.

promptstring · min: 1 · max: 4000Required

Text description of the image to generate

Example: A red fox in autumn forest

modelany ofOptional

Image generation model. Available: 'black-forest-labs/FLUX-2-pro' (default)

Example: black-forest-labs/FLUX-2-pro

stringOptional

or

nullOptional

widthany ofOptional

Image width in pixels (min 64, must be multiple of 32)

Default: 1024Example: 1024

integer · min: 64 · max: 2048Optional

or

nullOptional

heightany ofOptional

Image height in pixels (min 64, must be multiple of 32)

Default: 1024Example: 1024

integer · min: 64 · max: 2048Optional

or

nullOptional

seedany ofOptional

Random seed for reproducible results

integerOptional

or

nullOptional

safety_toleranceany ofOptional

Safety tolerance level (0=strictest, 6=least strict)

Default: 2

integer · max: 6Optional

or

nullOptional

output_formatany ofOptional

Output image format

Default: png

string · enumOptionalPossible values:

or

nullOptional

input_imageany ofOptional

Reference image as base64 string

stringOptional

or

nullOptional

input_image_2any ofOptional

Second reference image as base64 string

stringOptional

or

nullOptional

input_image_3any ofOptional

Third reference image as base64 string

stringOptional

or

nullOptional

input_image_4any ofOptional

Fourth reference image as base64 string

stringOptional

or

nullOptional

modeany ofOptional

Routing mode: 'auto' or 'direct' (FLUX is direct-only)

Default: auto

string · enumOptionalPossible values:

or

nullOptional

asyncany ofOptional

Return task_address immediately, poll /v2/tasks/{task_address} for result.

Default: false

booleanOptional

or

nullOptional

Responses

200

Successful Response

application/json

202

Task accepted (async mode). Poll the poll_url for status.

application/json

422

Validation Error

application/json

post

/v2/image/flux/generate

HTTPcURLJavaScriptPython

POST /v2/image/flux/generate HTTP/1.1
Content-Type: application/json
Accept: */*
Content-Length: 39

{
  "prompt": "A red fox in autumn forest"
}

Simple RequestDetailed RequestReproducible GenerationWith Reference Images

{
  "images": [
    "text"
  ],
  "model": "text",
  "width": 1,
  "height": 1,
  "task_address": "text",
  "done": true,
  "ANY_ADDITIONAL_PROPERTY": "anything"
}

Generate image from text prompt using FLUX.1-schnell

post

Generate an image from a text prompt using FLUX.1-schnell.

Model: black-forest-labs/FLUX.1-schnell

Required Parameters

Parameter	Type	Description
inputs	string	Text prompt for image generation

Optional Parameters

Parameter	Type	Default	Description
width	integer	1024	Image width in pixels
height	integer	1024	Image height in pixels
seed	integer	-	Random seed for reproducibility
num_inference_steps	integer	4	Denoising steps (more = higher quality)
guidance_scale	float	0.0	Prompt adherence (higher = more literal)

Response

{
  "images": ["base64_encoded_image..."],
  "model": "black-forest-labs/FLUX.1-schnell",
  "width": 1024,
  "height": 1024
}

Async Mode

Set async: true to get a task_address immediately and poll for results.

Header parameters

x-api-keyany ofOptional

stringOptional

or

nullOptional

Body

application/json

Request schema for FLUX.1-schnell image generation.

Uses the HuggingFace text-to-image format with inputs/parameters structure. Supports both direct and opengpu modes.

inputsstring · min: 1 · max: 4000Required

Text prompt for image generation

Example: A red fox in autumn forest

modelany ofOptional

Image generation model. Default: 'black-forest-labs/FLUX.1-schnell'

Example: black-forest-labs/FLUX.1-schnell

stringOptional

or

nullOptional

widthany ofOptional

Image width in pixels

Default: 1024Example: 1024

integer · min: 64 · max: 2048Optional

or

nullOptional

heightany ofOptional

Image height in pixels

Default: 1024Example: 1024

integer · min: 64 · max: 2048Optional

or

nullOptional

seedany ofOptional

Random seed for reproducible results

integerOptional

or

nullOptional

num_inference_stepsany ofOptional

Number of denoising steps (more steps = higher quality, slower)

Default: 4

integer · min: 1 · max: 50Optional

or

nullOptional

guidance_scaleany ofOptional

How closely to follow the prompt (higher = more literal)

Default: 0

number · max: 20Optional

or

nullOptional

modeany ofOptional

Routing mode: 'auto' (default), 'direct', or 'opengpu'

Default: auto

string · enumOptionalPossible values:

or

nullOptional

asyncany ofOptional

Return task_address immediately, poll /v2/tasks/{task_address} for result.

Default: false

booleanOptional

or

nullOptional

Responses

200

Successful Response

application/json

202

Task accepted (async mode). Poll the poll_url for status.

application/json

422

Validation Error

application/json

post

/v2/image/flux-1/generate

HTTPcURLJavaScriptPython

POST /v2/image/flux-1/generate HTTP/1.1
Content-Type: application/json
Accept: */*
Content-Length: 121

{
  "inputs": "cute kitten playing with a ball of yarn",
  "width": 128,
  "height": 128,
  "num_inference_steps": 20,
  "guidance_scale": 0
}

{
  "images": [
    "text"
  ],
  "model": "text",
  "width": 1,
  "height": 1,
  "task_address": "text",
  "mode": "text",
  "done": true,
  "ANY_ADDITIONAL_PROPERTY": "anything"
}

Generate image from text prompt using Gemini

post

Generate an image from a text prompt using Google Gemini models.

Available Models: google/gemini-3-pro-T2I

Required Parameters

Parameter	Type	Description
prompt	string	Text description of the image

Optional Parameters

Parameter	Type	Default	Description
model	string	google/gemini-3-pro-T2I	Image generation model
aspect_ratio	string	1:1	Aspect ratio (1:1, 2:3, 3:2, 3:4, 4:3, 4:5, 5:4, 9:16, 16:9, 21:9)
image_size	string	1K	Output resolution: 1K, 2K, or 4K

Response

{
  "images": ["base64_encoded_image..."],
  "model": "google/gemini-3-pro-T2I",
  "aspect_ratio": "1:1",
  "image_size": "1K"
}

Async Mode

Set async: true to get a task_address immediately and poll for results.

Header parameters

x-api-keyany ofOptional

stringOptional

or

nullOptional

Body

application/json

Request schema for Gemini image generation.

Uses Google Gemini 3 Pro for high-quality text-to-image generation.

promptstring · min: 1 · max: 4000Required

Text description of the image to generate

Example: A serene mountain landscape at golden hour

modelany ofOptional

Image generation model. Available: 'google/gemini-3-pro-T2I' (default)

Example: google/gemini-3-pro-T2I

stringOptional

or

nullOptional

aspect_ratioany ofOptional

Image aspect ratio

Default: 1:1

string · enumOptionalPossible values:

or

nullOptional

image_sizeany ofOptional

Output image resolution: 1K (~1024px), 2K (~2048px), 4K (~4096px)

Default: 1K

string · enumOptionalPossible values:

or

nullOptional

modeany ofOptional

Routing mode: 'auto' or 'direct' (Gemini is direct-only)

Default: auto

string · enumOptionalPossible values:

or

nullOptional

asyncany ofOptional

Return task_address immediately, poll /v2/tasks/{task_address} for result.

Default: false

booleanOptional

or

nullOptional

Responses

200

Successful Response

application/json

202

Task accepted (async mode). Poll the poll_url for status.

application/json

422

Validation Error

application/json

post

/v2/image/gemini-3/generate

HTTPcURLJavaScriptPython

POST /v2/image/gemini-3/generate HTTP/1.1
Content-Type: application/json
Accept: */*
Content-Length: 55

{
  "prompt": "A serene mountain landscape at golden hour"
}

Simple RequestDetailed Request

{
  "images": [
    "text"
  ],
  "model": "text",
  "aspect_ratio": "text",
  "image_size": "text",
  "task_address": "text",
  "done": true,
  "ANY_ADDITIONAL_PROPERTY": "anything"
}

Generate image from text prompt using Qwen

post

Generate an image from a text prompt using Qwen models.

Available Models: Qwen/qwen-image

Parameters

Parameter	Type	Default	Description
prompt	string	required	Text description of the image
size	string	512x512	Output size in WxH format

Header parameters

x-api-keyany ofOptional

stringOptional

or

nullOptional

Body

application/json

Request schema for Qwen text-to-image generation.

promptstring · min: 1 · max: 4000Required

Text description of the image to generate

Example: A beautiful sunset over mountains

modelany ofOptional

Image generation model. Available: 'Qwen/qwen-image' (default)

Example: Qwen/qwen-image

stringOptional

or

nullOptional

sizeany ofOptional

Output image size in WxH format

Default: 1024x1024Example: 512x512

stringOptional

or

nullOptional

seedany ofOptional

Random seed for reproducibility

integerOptional

or

nullOptional

modeany ofOptional

Routing mode: 'auto' or 'direct' (Qwen is direct-only)

Default: auto

string · enumOptionalPossible values:

or

nullOptional

asyncany ofOptional

Return task_address immediately, poll /v2/tasks/{task_address} for result.

Default: false

booleanOptional

or

nullOptional

Responses

200

Successful Response

application/json

202

Task accepted (async mode). Poll the poll_url for status.

application/json

422

Validation Error

application/json

post

/v2/image/qwen/generate

HTTPcURLJavaScriptPython

POST /v2/image/qwen/generate HTTP/1.1
Content-Type: application/json
Accept: */*
Content-Length: 46

{
  "prompt": "A beautiful sunset over mountains"
}

Simple RequestWith Custom Size

{
  "urls": [
    "text"
  ],
  "model": "text",
  "size": "text",
  "task_address": "text",
  "done": true,
  "ANY_ADDITIONAL_PROPERTY": "anything"
}

Edit image using Qwen

post

Edit an image using Qwen models.

Available Models: Qwen/qwen-image-edit

Parameters

Parameter	Type	Default	Description
prompt	string	required	Text description of the edit
image	string	required	URL of source image
size	string	512x512	Output size in WxH format

Header parameters

x-api-keyany ofOptional

stringOptional

or

nullOptional

Body

application/json

Request schema for Qwen image editing.

promptstring · min: 1 · max: 4000Required

Text description of the edit to apply

Example: Convert to pencil sketch

imagestringRequired

Source image as URL or base64 encoded string

Example: https://picsum.photos/id/10/1024/1024.jpg

modelany ofOptional

Image editing model. Available: 'Qwen/qwen-image-edit' (default)

Example: Qwen/qwen-image-edit

stringOptional

or

nullOptional

sizeany ofOptional

Output image size in WxH format

Default: 1024x1024Example: 512x512

stringOptional

or

nullOptional

seedany ofOptional

Random seed for reproducibility

integerOptional

or

nullOptional

modeany ofOptional

Routing mode: 'auto' or 'direct' (Qwen is direct-only)

Default: auto

string · enumOptionalPossible values:

or

nullOptional

asyncany ofOptional

Return task_address immediately, poll /v2/tasks/{task_address} for result.

Default: false

booleanOptional

or

nullOptional

Responses

200

Successful Response

application/json

202

Task accepted (async mode). Poll the poll_url for status.

application/json

422

Validation Error

application/json

post

/v2/image/qwen/edit

HTTPcURLJavaScriptPython

POST /v2/image/qwen/edit HTTP/1.1
Content-Type: application/json
Accept: */*
Content-Length: 89

{
  "prompt": "Convert to pencil sketch",
  "image": "https://picsum.photos/id/10/1024/1024.jpg"
}

{
  "urls": [
    "text"
  ],
  "model": "text",
  "size": "text",
  "task_address": "text",
  "done": true,
  "ANY_ADDITIONAL_PROPERTY": "anything"
}

Generate image from text (GPT Image 1.5)

post

Generate image from text using openai/gpt-image-1.5-T2I.

Header parameters

x-api-keyany ofOptional

stringOptional

or

nullOptional

Body

application/json

Request schema for GPT Image text-to-image generation.

promptstring · min: 1 · max: 4000Required

Text description for image generation

nany ofOptional

Number of images to generate (1-4)

Default: 1

integer · enumOptionalPossible values:

or

nullOptional

sizeany ofOptional

Image size

Default: 1024x1024

string · enumOptionalPossible values:

or

nullOptional

qualityany ofOptional

Image quality

Default: medium

string · enumOptionalPossible values:

or

nullOptional

output_formatany ofOptional

Output format

Default: png

string · enumOptionalPossible values:

or

nullOptional

output_compressionany ofOptional

Compression level (0-100)

Default: 100

integer · max: 100Optional

or

nullOptional

modeany ofOptional

Routing mode

Default: auto

string · enumOptionalPossible values:

or

nullOptional

asyncany ofOptional

Return task_address immediately for polling

Default: false

booleanOptional

or

nullOptional

Responses

200

Successful Response

application/json

202

Task accepted (async mode).

application/json

422

Validation Error

application/json

post

/v2/image/gpt-image/generate

HTTPcURLJavaScriptPython

POST /v2/image/gpt-image/generate HTTP/1.1
Content-Type: application/json
Accept: */*
Content-Length: 46

{
  "prompt": "A beautiful sunset over mountains"
}

SimpleDetailed

{
  "images": [
    "text"
  ],
  "model": "openai/gpt-image-1.5-T2I",
  "size": "text",
  "task_address": "text",
  "mode": "text",
  "done": true,
  "ANY_ADDITIONAL_PROPERTY": "anything"
}

Edit image (GPT Image 1.5)

post

Edit image using openai/gpt-image-1.5-I2I.

Header parameters

x-api-keyany ofOptional

stringOptional

or

nullOptional

Body

application/json

Request schema for GPT Image image-to-image editing.

promptstring · min: 1 · max: 4000Required

Text description for image editing

imagestringRequired

Source image as base64 encoded string

maskany ofOptional

Mask image as base64 encoded string (optional)

stringOptional

or

nullOptional

nany ofOptional

Number of images to generate (1-4)

Default: 1

integer · enumOptionalPossible values:

or

nullOptional

sizeany ofOptional

Image size

Default: 1024x1024

string · enumOptionalPossible values:

or

nullOptional

qualityany ofOptional

Image quality

Default: medium

string · enumOptionalPossible values:

or

nullOptional

output_formatany ofOptional

Output format

Default: png

string · enumOptionalPossible values:

or

nullOptional

output_compressionany ofOptional

Compression level (0-100)

Default: 100

integer · max: 100Optional

or

nullOptional

modeany ofOptional

Routing mode

Default: auto

string · enumOptionalPossible values:

or

nullOptional

asyncany ofOptional

Return task_address immediately for polling

Default: false

booleanOptional

or

nullOptional

Responses

200

Successful Response

application/json

202

Task accepted (async mode).

application/json

422

Validation Error

application/json

post

/v2/image/gpt-image/edit

HTTPcURLJavaScriptPython

POST /v2/image/gpt-image/edit HTTP/1.1
Content-Type: application/json
Accept: */*
Content-Length: 70

{
  "prompt": "Add a rainbow to the sky",
  "image": "<base64_encoded_image>"
}

SimpleWith mask

{
  "images": [
    "text"
  ],
  "model": "openai/gpt-image-1.5-I2I",
  "size": "text",
  "task_address": "text",
  "mode": "text",
  "done": true,
  "ANY_ADDITIONAL_PROPERTY": "anything"
}