🎉 New Year Sale: Get 20% OFF on all plans — Use code NEWYEAR2026.

Upgrade now
Exterior Restorer thumbnail

ModelsLab/Exterior Restorer

exterior-restorer
This endpoint transforms damaged or unattractive exteriors into beautifully restored, visually appealing versions using AI
API PlaygroundAPI Documentation

API Endpoint URL

Base URL for all API requests to this endpoint.

https://modelslab.com/api/v6/interior/exterior_restorer

API Authentication

Authentication requires a valid API key included in the request. Generate and manage your API keys from your developer dashboard. Include the key in the key parameter for all API requests.

Integration Examples

Production-ready code samples for API integration

{
"prompt": "Redesign the building exterior in a modern minimalist architectural style",
"init_image": "https://assets.modelslab.com/generations/4e717050-bf0c-4579-82fc-dafac50437ea",
"strength": "0.4",
"num_inference_steps": "41",
"negative_prompt": "blurry, low resolution, bad lighting, poorly drawn furniture, distorted proportions, messy room, unrealistic colors, extra limbs, missing furniture, bad anatomy, low detail, pixelated, grainy, artifacts, oversaturated, asymmetry, ugly, cartoonish, out of frame, duplicate objects",
"guidance_scale": "7.5",
"base64": "false",
"seed": "0",
"specific_object": null,
"webhook": null,
"track_id": null,
"key": "YOUR_API_KEY"
}

SDKs

Official SDKs

Production-ready SDKs and client libraries for all major programming languages

API Parameters

Technical specifications for API request parameters.

Field NameParameterTechnical Description
promptpromptA text prompt describing the content you want in the generated image.
init_imageinit_imageA URL to the initial image.
strengthstrengthThe degree to which the prompt influences the initial image. 1.0 corresponds to full destruction of the initial image details.
num_inference_stepsnum_inference_stepsThe number of denoising steps. Acceptable values are 21, 31, or 41.
negative_promptnegative_promptDescriptions of elements to avoid in the image (e.g., NSFW content, poor quality, distorted features).
guidance_scaleguidance_scaleThe scale for classifier-free guidance. Minimum is 1, and maximum is 20.
base64base64Specifies whether the response should be returned as a base64 string. Defaults to false.
seedseedSeed is used to reproduce results, same seed will give you same image in return again. Pass null for a random number
specific_objectspecific_objectSpecific object parameter
webhookwebhookA URL to receive a POST API call once the image generation is complete
track_idtrack_idAn ID returned in the API response, used to identify the webhook request