catacolabs/codeformer | API reference

Robust face restoration algorithm for old photos

Public

22 runs

GitHub

Run catacolabs/codeformer 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
images	array		Input image(s) - up to 4 images
codeformer_fidelity	number	0.5 Max: 1	Balance the quality (lower number) and fidelity (higher number).
runtime_profile	None	baseline	Runtime profile
stability_mode	None	safe	Execution mode: safe for maximum reliability on Replicate, optimized for maximum speed
compile_backend	None	eager	torch.compile backend used only when stability_mode=optimized

{
  "type": "object",
  "title": "Input",
  "required": [
    "images"
  ],
  "properties": {
    "images": {
      "type": "array",
      "items": {
        "type": "string",
        "format": "uri"
      },
      "title": "Images",
      "x-order": 0,
      "description": "Input image(s) - up to 4 images"
    },
    "stability_mode": {
      "enum": [
        "safe",
        "optimized"
      ],
      "type": "string",
      "title": "stability_mode",
      "description": "Execution mode: safe for maximum reliability on Replicate, optimized for maximum speed",
      "default": "safe",
      "x-order": 3
    },
    "compile_backend": {
      "enum": [
        "none",
        "eager",
        "aot_eager",
        "inductor"
      ],
      "type": "string",
      "title": "compile_backend",
      "description": "torch.compile backend used only when stability_mode=optimized",
      "default": "eager",
      "x-order": 4
    },
    "runtime_profile": {
      "enum": [
        "baseline",
        "fast",
        "max_speed"
      ],
      "type": "string",
      "title": "runtime_profile",
      "description": "Runtime profile",
      "default": "baseline",
      "x-order": 2
    },
    "codeformer_fidelity": {
      "type": "number",
      "title": "Codeformer Fidelity",
      "default": 0.5,
      "maximum": 1,
      "minimum": 0,
      "x-order": 1,
      "description": "Balance the quality (lower number) and fidelity (higher number)."
    }
  }
}

Output schema

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

Schema

{
  "type": "array",
  "items": {
    "type": "string",
    "format": "uri"
  },
  "title": "Output"
}