POST
/
image_editing
/
inpaint
Image inpainting
curl --request POST \
  --url https://modelslab.com/api/v6/image_editing/inpaint \
  --header 'Content-Type: application/json' \
  --data '{
  "key": "<string>",
  "prompt": "<string>",
  "negative_prompt": "<string>",
  "init_image": "<string>",
  "mask_image": "<string>",
  "width": 512,
  "height": 512,
  "samples": 1,
  "num_inference_steps": 30,
  "safety_checker": "no",
  "guidance_scale": 5,
  "strength": 0.7,
  "instant_response": "false",
  "base64": "false",
  "seed": 123,
  "webhook": "<string>",
  "track_id": 123
}'
{
  "status": "success",
  "generationTime": 123,
  "id": 123,
  "output": [
    "<string>"
  ],
  "proxy_links": [
    "<string>"
  ],
  "meta": {}
}
Together with the image and the mask you can add your description of the desired result by passing prompt and negative prompt.

​
Inpaintin

Inpainting endpoint result

​
Request

Make a POST request to below endpoint and pass the required parameters as a request body.
curl
--request POST 'https://modelslab.com/api/v6/image_editing/inpaint' \

​
Body

json
{  
    "key": "your_api_key",  
    "prompt": "a cat sitting on a bench",  
    "negative_prompt": null,  
    "init_image": "https://raw.githubusercontent.com/CompVis/stable-diffusion/main/data/inpainting_examples/overture-creations-5sI6fQgYIuo.png",  
    "mask_image": "https://raw.githubusercontent.com/CompVis/stable-diffusion/main/data/inpainting_examples/overture-creations-5sI6fQgYIuo_mask.png",  
    "width": "512",  
    "height": "512",  
    "samples": 1,  
    "num_inference_steps": "30",  
    "safety_checker": "no", 
    "guidance_scale": 5,  
    "strength": 0.7,  
    "base64": false,  
    "seed": null,  
    "webhook": null,  
    "track_id": null
}

Body

application/json
​
key
string
required

Your API Key used for request authorization

​
prompt
string
required

Text prompt describing the content you want in the generated image

​
init_image
string<uri>
required

Link to the initial image

​
mask_image
string<uri>
required

Link to the mask image for inpainting

​
negative_prompt
string

Items you do not want in the image

​
width
integer
default:512

The width of the generated images, If not provided, the width of init_image is used

Required range: x <= 1024
​
height
integer
default:512

The height of the generated images, If not provided, the height of init_image is used

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

Number of images to be returned in response

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

Number of denoising steps

​
safety_checker
enum<string>
default:no

A checker for NSFW images

Available options:
yes,
no
​
guidance_scale
integer
default:5

Scale for classifier-free guidance

Required range: 1 <= x <= 5
​
strength
number
default:0.7

Prompt strength when using the initial image

Required range: 0 <= x <= 1
​
instant_response
enum<string>
default:false

Set to true for instant queue response

Available options:
true,
false
​
base64
enum<string>
default:false

Set to true to get response as base64 string

Available options:
true,
false
​
seed
integer

Seed used to reproduce results

​
webhook
string<uri>

URL to receive POST API call when complete

​
track_id
integer

ID for webhook identification

Response

200 - application/json

Inpainting response

​
status
enum<string>
Available options:
success
​
generationTime
number

Time taken to generate the image in seconds

​
id
integer

Unique identifier for the generation request

​
output
string<uri>[]

Array of generated image URLs

​
proxy_links
string<uri>[]

Array of proxy image URLs

​
meta
object

Metadata about the generation process