Image to Image

For more detailed information on the available image-to-image models, please refer to Image to Image section.

Image to Image API

POST /getImagetoImage

Headers

Name Value

Name	Value
Content-Type	`application/json`
Authorization	`Bearer <token>`

Content-Type

application/json

Authorization

Bearer <token>

Body

Name Type Description

Name	Type	Description
app_id	string	-> Each model is uniquely characterized by its own `app_id`.
image	string	-> The `image` parameter specifies the URL of an existing image that will be used as a reference for the generation process. -> If the original image dimensions exceed 1536x1536 pixels, the image will be adjusted to fit within this size while preserving the original aspect ratio.
prompt	string	-> The `prompt` parameter is the textual input that guides the image generation process. This prompt serves as an artistic compass, shaping the visual output.
guidance_scale	float	-> The `guidance_scale` parameter determines how closely the generated image adheres to the provided prompt. Higher values result in the model following the prompt more closely, while lower values allow for more creative deviation. -> The valid range for the `guidance_scale` parameter is between 1 and 30.
batch	int	-> The `batch` parameter allows you to specify the number of images to generate at once. -> The valid range for this parameter is between 1 and 8.
strength	float	-> The `strength` parameter specifies the degree of transformation applied to the reference image. -> A higher `strength` value (up to 1) results in the generated image deviating more from the initial reference image, as more noise is introduced. A `strength` of 1 completely disregards the initial image.
height	int	-> The `height` parameter represents the vertical dimension of an image. -> The valid range for the parameter is between 256 and 1536 pixels. -> This parameter is only applicable for the SDXL API, as it requires specific `height` and `width` values.
width	int	-> The `width` parameter represents the horizontal dimension of an image. -> The valid range for the parameter is between 256 and 1536 pixels. -> This parameter is only applicable for the SDXL API, as it requires specific `height` and `width` values.
negative_prompt	string	-> The `negative_prompt` parameter allows you to specify content that you want the image generation model to avoid or minimize in the output. This can be useful for excluding certain visual elements or styles that you do not want to be present in the generated image.
celery	bool	-> The `celery` parameter is used for queuing tasks that require extended processing time. When you enqueue a task, you receive a unique `task_id`. This `task_id` allows you to check the task's status later using the task status API, which is useful for managing and tracking long-running tasks.
inference_type	string	-> The `inference_type` parameter allows you to specify the GPU to be used for the image generation task. The supported values are: `a10g` `a100` `h100` This parameter is only applicable for Qolaba-deployed models, including Turbo Vision, Qolaba Style, Cartoon, Realistic, and Anime Style. The different GPU options provide varying levels of performance and capabilities, allowing you to choose the most suitable GPU based on your requirements and the demand for the task.

app_id

string

-> Each model is uniquely characterized by its own app_id.

image

string

-> The image parameter specifies the URL of an existing image that will be used as a reference for the generation process.

-> If the original image dimensions exceed 1536x1536 pixels, the image will be adjusted to fit within this size while preserving the original aspect ratio.

prompt

string

-> The prompt parameter is the textual input that guides the image generation process. This prompt serves as an artistic compass, shaping the visual output.

guidance_scale

float

-> The guidance_scale parameter determines how closely the generated image adheres to the provided prompt. Higher values result in the model following the prompt more closely, while lower values allow for more creative deviation.

-> The valid range for the guidance_scale parameter is between 1 and 30.

batch

int

-> The batch parameter allows you to specify the number of images to generate at once.

-> The valid range for this parameter is between 1 and 8.

strength

float

-> The strength parameter specifies the degree of transformation applied to the reference image.

-> A higher strength value (up to 1) results in the generated image deviating more from the initial reference image, as more noise is introduced. A strength of 1 completely disregards the initial image.

height

int

-> The height parameter represents the vertical dimension of an image.

-> The valid range for the parameter is between 256 and 1536 pixels. -> This parameter is only applicable for the SDXL API, as it requires specific height and width values.

width

int

-> The width parameter represents the horizontal dimension of an image.

-> The valid range for the parameter is between 256 and 1536 pixels. -> This parameter is only applicable for the SDXL API, as it requires specific height and width values.

negative_prompt

string

-> The negative_prompt parameter allows you to specify content that you want the image generation model to avoid or minimize in the output. This can be useful for excluding certain visual elements or styles that you do not want to be present in the generated image.

celery

bool

-> The celery parameter is used for queuing tasks that require extended processing time. When you enqueue a task, you receive a unique task_id. This task_id allows you to check the task's status later using the task status API, which is useful for managing and tracking long-running tasks.

inference_type

string

-> The inference_type parameter allows you to specify the GPU to be used for the image generation task. The supported values are:

a10g
a100
h100

This parameter is only applicable for Qolaba-deployed models, including Turbo Vision, Qolaba Style, Cartoon, Realistic, and Anime Style.

The different GPU options provide varying levels of performance and capabilities, allowing you to choose the most suitable GPU based on your requirements and the demand for the task.

APP ids for different Image to Image styles

App ID Model Name Height and Width Constraints

App ID	Model Name	Height and Width Constraints
ap-Jf2aKs8dPqXzRb1Yv6hN7L	Turbo Vision	The `height` and `width` of input image must be multiples of 8 pixels.
ap-vcbg1l7bBuScbDuUOk3Shl	Qolaba Style	The `height` and `width` of input image must be multiples of 8 pixels.
ap-Rgtph3LFS9rRT5X7XREazo	Cartoon Style	The `height` and `width` of input image must be multiples of 8 pixels.
ap-nM68b4WwQ6VzdNwwXBrOHE	Realistic Style	The `height` and `width` of input image must be multiples of 8 pixels.
ap-Zj2zfXKq52zvpib7jGqYFp	Anime Style	The `height` and `width` of input image must be multiples of 8 pixels.
ap-eRSyl0imzrUrbvgdAYwDTl	SDXL Style	The SDXL API supports the following combinations of `height` and `width` parameters: 1024x1024 1536x640 1344x768 1216x832 1152x896 896x1152 832x1216 768x1344 640x1536 Please ensure that the values you provide for `height` and `width` match one of these supported combinations.
ap-F7gH2jPzV5xQ8eT3kLb9Yn	SDXL3 Style	The `height` and `width` of input image must be multiples of 8 pixels.

ap-Jf2aKs8dPqXzRb1Yv6hN7L

Turbo Vision

The height and width of input image must be multiples of 8 pixels.

ap-vcbg1l7bBuScbDuUOk3Shl

Qolaba Style

The height and width of input image must be multiples of 8 pixels.

ap-Rgtph3LFS9rRT5X7XREazo

Cartoon Style

The height and width of input image must be multiples of 8 pixels.

ap-nM68b4WwQ6VzdNwwXBrOHE

Realistic Style

The height and width of input image must be multiples of 8 pixels.

ap-Zj2zfXKq52zvpib7jGqYFp

Anime Style

The height and width of input image must be multiples of 8 pixels.

ap-eRSyl0imzrUrbvgdAYwDTl

SDXL Style

The SDXL API supports the following combinations of height and width parameters:

1024x1024
1536x640
1344x768
1216x832
1152x896
896x1152
832x1216
768x1344
640x1536

Please ensure that the values you provide for height and width match one of these supported combinations.

ap-F7gH2jPzV5xQ8eT3kLb9Yn

SDXL3 Style

The height and width of input image must be multiples of 8 pixels.

Response

{
  "time_required": "",
  "error": "",
  "error_data": "",
  "input": "",
  "output": "",
  "app_id": "",
  "task_id": "",
  "status": ""
}

{
  "time_required": "",
  "error": "",
  "error_data": "",
  "input": "",
  "output": "",
  "app_id": "",
  "task_id": "",
  "status": ""
}

Run the API

To test this API, please use the following link:

https://app.theneo.io/api-runner/qolaba/ml-apis/api-reference/image-to-image

PreviousText to Image NextControlNet

Last updated 5 months ago