tomclive/photo-restore-comparison

Restores photos using current SOTA image editing models and outputs a collage

Public

368 runs

Run tomclive/photo-restore-comparison with an API

Use one of our client libraries to get started quickly. Clicking on a library will take you to the Playground tab where you can tweak different inputs, see the results, and copy the corresponding code to use in your own project.

Input schema

The fields you can use to run this model with an API. If you don't give a value for a field its default value will be used.

Field	Type	Default value	Description
image	string		Photo to be restored
openai_api_key	string		Your OpenAI API key (required for GPT Image 1)
collage_width	integer	1200 Min: 800 Max: 2000	Width of the output collage in pixels
include_original	boolean	True	Include original image in collage

{
  "type": "object",
  "title": "Input",
  "required": [
    "image"
  ],
  "properties": {
    "image": {
      "type": "string",
      "title": "Image",
      "format": "uri",
      "x-order": 0,
      "description": "Photo to be restored"
    },
    "collage_width": {
      "type": "integer",
      "title": "Collage Width",
      "default": 1200,
      "maximum": 2000,
      "minimum": 800,
      "x-order": 2,
      "description": "Width of the output collage in pixels"
    },
    "openai_api_key": {
      "type": "string",
      "title": "Openai Api Key",
      "default": "",
      "x-order": 1,
      "description": "Your OpenAI API key (required for GPT Image 1)"
    },
    "include_original": {
      "type": "boolean",
      "title": "Include Original",
      "default": true,
      "x-order": 3,
      "description": "Include original image in collage"
    }
  }
}

Output schema

The shape of the response you’ll get when you run this model with an API.

Schema

{
  "type": "object",
  "title": "Output",
  "required": [
    "comparison_collage",
    "nano_banana_result",
    "flux_restore_result",
    "openai_gpt_image_result",
    "qwen_edit_result",
    "seededit_result"
  ],
  "properties": {
    "seededit_result": {
      "type": "string",
      "title": "Seededit Result",
      "format": "uri"
    },
    "qwen_edit_result": {
      "type": "string",
      "title": "Qwen Edit Result",
      "format": "uri"
    },
    "comparison_collage": {
      "type": "string",
      "title": "Comparison Collage",
      "format": "uri"
    },
    "nano_banana_result": {
      "type": "string",
      "title": "Nano Banana Result",
      "format": "uri"
    },
    "flux_restore_result": {
      "type": "string",
      "title": "Flux Restore Result",
      "format": "uri"
    },
    "openai_gpt_image_result": {
      "type": "string",
      "title": "Openai Gpt Image Result",
      "format": "uri"
    }
  }
}

Example API response

View prediction

{'comparison_collage': 'https://replicate.delivery/xezq/LBRDPffQt8jIfp3fhg5fWEyrJ2Se03eLVkTXwbRw1aJe7vJPVA/restoration_comparison.png',
 'flux_restore_result': 'https://replicate.delivery/xezq/nlAfHQCJxo0EC6l1QnRUWpVNB95E34y97o3dslGywMx93knKA/tmpq4_zxj3_.png',
 'nano_banana_result': 'https://replicate.delivery/xezq/gdtoGNfH9cxdICtW4qXhXHy8e3eqe3266ExAc2ddwpRtfN5pC/tmp7k2iw5mu.png',
 'openai_gpt_image_result': None,
 'qwen_edit_result': 'https://replicate.delivery/xezq/pGqpxav0ijY6CVegO29hlvH7iPJAEHet884t79cWIVk7vJPVA/out-0.png',
 'seededit_result': 'https://replicate.delivery/xezq/wM6fPE4oT6RoaKrcFb9LUOwSrLcSmcNfdR3YJDhXNpT7vJPVA/tmp9e7zzj0d.jpg'}