ai_vqgan

An authenticated client can post a request to VQGAN-CLIP

VQGAN-CLIP stands for Vector Quantized Generative Adversarial Network and Contrastive Language–Image Pre-training. It is an ealier generation AI (pre 2020) for image to image processing

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/vqgan

200: OK The full JSON config file

{
    "engine": "vqgan",
    "name": "VQGAN-CLIP",
    "location": "",
    "ip": "0.0.0.0",
    "port": 5101,
    "version": "1.1.7",
    "description": "Text to Image",
    "github": "https://github.com/nerdyrodent/VQGAN-CLIP",
    "requiresGPU": true,
    "isFree": false,
    "default_cost": 1000,
    "params": [{
        "in": "word",
        "out": "-p",
        "isMandatory": true,
        "type": "string",
        "default": null,
        "ui": {
            "title": "Input (text and/or image)",
            "placeholder": "eg: gold coin from rome 100 BC, full size",
            "widget": "uiEdit",
            "column": 1
        }
    }, {
        "in": "url_upload",
        "out": "-filename",
        "isMandatory": false,
        "type": "string",
        "default": null,
        "accept": {
            "$max": 2048,
            "$ext": [".png", ".jpg", ".jpeg"]
        },
        "ui": {
            "widget": "uiSelectPicture",
            "column": 1
        }
    }, {
        "in": "steps",
        "out": "-i",
        "isMandatory": true,
        "type": "int",
        "default": 25,
        "freeAccess":  {"$max": 100},
        "ui": {
            "title": "Step Count",
            "tooltip": "",
            "min": 1,            
            "max": 200,            
            "unit": "",
            "widget": "uiRangeSlider",
            "column": 1
        }
    }, {
        "in": "saveinterval",
        "out": "-se",
        "isMandatory": true,
        "type": "int",
        "default": 20,
        "freeAccess":  {"$max": 20},
        "ui": {
            "title": "Save every",
            "tooltip": "",
            "min": 1,            
            "max": 20,            
            "unit": "",
            "widget": "uiRangeSlider",
            "column": 1
        }
    }, {
        "in": "width",
        "out": "-width",
        "isMandatory": true,
        "type": "int",
        "default": 384,
        "accept": {
            "$in":[320, 384, 448, 512, 576, 640, 704, 768],
            "display":["320x320", "384x384", "448x448", "512x512", "576x576", "640x640", "704x704", "768x768"]
        },
        "freeAccess":  {"$max": 512},
        "ui": {
            "title": "Output resolution",
            "widget": "uiMultiToggle",
            "unit": "px",    
            "column": 2,
            "autofill": [{"in":"height", "out":"-height"}]
        }
    }, {
        "in": "height",
        "out": "-height",
        "isMandatory": true,
        "type": "int",
        "default": 384,
        "accept": {"$in":[320, 384, 448, 512, 576, 640, 704, 768]},
        "freeAccess":  {"$max": 512},
        "ui": {
            "unit": "px"
        }
    }, {
        "in": "model",
        "out": "-ckpt",
        "isMandatory": false,
        "type": "string",
        "default": "vqgan_imagenet_f16_16384.ckpt"
    }, {
        "in": "yaml",
        "out": "-conf",
        "isMandatory": false,
        "type": "string",
        "default": "vqgan_imagenet_f16_16384.yaml"
    }, {
        "in": "output",
        "out": "-o",
        "isMandatory": true,
        "type": "function",
        "default": "$output_uid.ext"
    }]
}

Post a request to VQGAN via OpenSourceAIs

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

Request Body

Name	Type	Description
width	Number	The width of the output image. Defaults to 320
height	Number	The height of the output image. Defaults to 320
steps	Number	The number of steps requested for generating the output image. High number of steps cost more GPU compute. Defaults to 20. Should not exceed 200.
word*	String	A text input to tell the AI what to generate.
url_upload	String	A well formed URI starting with https://... and accessing a PNG or JPG image. Note that if the image is not of the width and height size passed in parameters, it will be automatically cropped or resized.
saveinterval	Number	A positive number indicating when intermediate images are saved.
model	String	The model used for morphing the image.

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"
}

409: Conflict Could not add request to backlog

{
     data: null,
     status: 409,
     statusText: "Could not add to backlog"
}