Skip to main content
POST
/
img2img
Image-to-Image
curl --request POST \
  --url https://modelslab.com/api/v6/images/img2img \
  --header 'Content-Type: application/json' \
  --data '
{
  "key": "<string>",
  "model_id": "<string>",
  "prompt": "<string>",
  "init_image": "<string>",
  "negative_prompt": "<string>",
  "strength": 0.7,
  "width": 2048,
  "height": 2048,
  "samples": 1,
  "num_inference_steps": 30,
  "guidance_scale": 7.5,
  "safety_checker": "yes",
  "scheduler": "DPMSolverMultistepScheduler",
  "use_karras_sigmas": "yes",
  "algorithm_type": "sde-dpmsolver++",
  "clip_skip": 2,
  "seed": 123,
  "webhook": "<string>",
  "track_id": "<string>"
}
'
{
  "generationTime": 123,
  "id": 123,
  "output": [
    "<string>"
  ],
  "proxy_links": [
    "<string>"
  ],
  "meta": {},
  "nsfw_content_detected": true,
  "webhook_status": "<string>",
  "tip": "<string>"
}

Documentation Index

Fetch the complete documentation index at: https://docs.modelslab.com/llms.txt

Use this file to discover all available pages before exploring further.

The dimensions of the generated image will be the same as the dimensions of the init_image.
Transform existing images with text guidance using Pony models.
See available schedulers for Pony models.

​
Request

Make a POST request to the endpoint below with the required parameters. 
POST https://modelslab.com/api/v6/images/img2img

​
Body

json
{
    "key": "your_api_key",
    "model_id": "pony_realism",
    "prompt": "a cat sitting on a bench, oil painting style",
    "negative_prompt": "blurry, low quality",
    "init_image": "https://raw.githubusercontent.com/CompVis/stable-diffusion/main/data/inpainting_examples/overture-creations-5sI6fQgYIuo.png",
    "strength": 0.7,
    "width": 2048,
    "height": 2048,
    "samples": 1,
    "num_inference_steps": 31,
    "safety_checker": "no",
    "seed": null,
    "guidance_scale": 7.5,
    "scheduler": "DPMSolverMultistepScheduler",
    "use_karras_sigmas": "yes",
    "algorithm_type": "sde-dpmsolver++",
    "clip_skip": "2",
    "webhook": null,
    "track_id": null
}

Body

application/json
​
key
string
required

Your API Key used for request authorization.

​
model_id
string
required

The ID of the Pony model to be used. Use pony_realism for the Pony Realism model.

​
prompt
string
required

A text description of what you want in the generated image.

​
init_image
string<uri>
required

URL of the initial image to be used as a reference.

​
negative_prompt
string

Items you don't want in the image.

​
strength
number
default:0.7

How much to transform the init image. 0.0 = no change, 1.0 = complete transformation.

Required range: 0 <= x <= 1
​
width
integer
default:2048

The width of the image in pixels. Must be between 1024-2048 and divisible by 8.

Required range: 1024 <= x <= 2048
​
height
integer
default:2048

The height of the image in pixels. Must be between 1024-2048 and divisible by 8.

Required range: 1024 <= x <= 2048
​
samples
integer
default:1

The number of images to be returned in response. Maximum is 4.

Required range: x <= 4
​
num_inference_steps
integer
default:30

Number of denoising steps. Higher values produce more detailed images but take longer.

Required range: 20 <= x <= 50
​
guidance_scale
number
default:7.5

How closely to follow the prompt. Higher values = more literal interpretation.

Required range: 1 <= x <= 20
​
safety_checker
enum<string>
default:yes

Enable NSFW content filter.

Available options:
yes,
no
​
scheduler
string
default:DPMSolverMultistepScheduler

Scheduler to use for denoising.

​
use_karras_sigmas
enum<string>
default:yes

Apply Karras sigmas to the scheduler.

Available options:
yes,
no
​
algorithm_type
string
default:sde-dpmsolver++

Algorithm type for the scheduler.

​
clip_skip
integer
default:2

Number of CLIP layers to skip. Affects style interpretation.

Required range: 1 <= x <= 4
​
seed
integer | null

Random seed for reproducible results. Pass null for a random number.

​
webhook
string<uri>

URL to receive a POST API call once image generation is complete.

​
track_id
string

Unique ID used in webhook response to identify the request.

Response

Image-to-image generation response

​
status
enum<string>

Status of the image generation.

Available options:
success
​
generationTime
number

Time taken to generate the image in seconds.

​
id
integer

Unique identifier for the image generation request.

​
output
string<uri>[]

Array of generated image URLs.

​
proxy_links
string<uri>[]

Array of proxy image URLs.

​
meta
object

Metadata about the image generation including all parameters used.

​
nsfw_content_detected
boolean

Indicates if NSFW content was detected in the generated image.

​
webhook_status
string

Status of the webhook notification.

​
tip
string

Additional information or tips for the user.