ai_vtoonify

An authenticated client can post a request to vtoonify

This AI has the ability to produce cartoon-like pictures of a fac, and also video animations from a single image upload

GitHub - williamyang1991/VToonify: [SIGGRAPH Asia 2022] VToonify: Controllable High-Resolution Portrait Video Style TransferGitHub

vToonify github page

This AI can run AI alongside a Daemon on GPU only

Get the JSON config file for this AI

GET https://opensourceais.com/api/v1/public/config/vtoonify

200: OK The full JSON config file

{
    "engine": "vtoonify",
    "name": "VToonify",
    "location": "http://0.0.0.0",
    "port": 5308,
    "version": "1.0.5",
    "description": "Image to Image",
    "github": "https://github.com/williamyang1991/VToonify/",
    "requiresGPU": true,
    "isFree": false,
    "default_cost": 1000,
    "params": [{
        "in": "url_upload",
        "out": "-filename",
        "isMandatory": false,
        "type": "string",
        "default": null,
        "ui": {
            "widget": "uiSelectPicture",
            "column": 1
        }
    }, {
        "in": "padding",
        "out": "--padding",
        "isMandatory": false,
        "type": "int",
        "default": 200,
        "accept": {
            "$in":[200, 400, 600],
            "display":["200px", "400px", "600px"]
        },
        "freeAccess": {"$max": 200},
        "ui": {
            "title": "padding in px to the eye center",
            "unit": "px",
            "widget": "uiMultiToggle",
            "column": 2
        }
    }, {
        "in": "scale_image",
        "out": "--scale_image",
        "isMandatory": true,
        "type": "boolean",
        "default": true
    }, {
        "in": "model",
        "out": "--ckpt",
        "isMandatory": true,
        "type": "string",
        "default": "vtoonify_d_cartoon/vtoonify_s_d.pt"
    }, {
        "in": "backbone",
        "out": "--backbone",
        "isMandatory": true,
        "type": "string",
        "default": "dualstylegan"
    }, {
        "in": "output",
        "out": "--output",
        "isMandatory": true,
        "type": "function",
        "default": "$output_uid.ext"
    }]
}

Post a request to AI vtoonify via OpenSourceAIs

POST https://opensourceais.com/api/v1/private/client/ai/vtoonify

Request Body

Name	Type	Description
padding	Int	Number of pixels left, right, top, bottom from the nose (automatically detected) in the image uploaded
url_upload*	String	A well formed URI starting with https://... and accessing a .PNG or .JPG file. Note that this file has a limit of 2Mb. You should only upload files of at most 15sec of sample voice.

201: Created Confirmation that the request was processed

{
    "data": {
        "uid": 1678361974000,
        "created_at": "2023-03-09T11:39:44.000Z"
    }
}

400: Bad Request This error should not happen unless authentication is tampered with

{
     data: null,
     status: 400,
     statusText: "A client token is required"
}