@fazza/gpti v1.0.0

GPTI

This package simplifies your interaction with various GPT models, eliminating the need for tokens or other methods to access GPT. It also allows you to use three artificial intelligences to generate images: DALL·E, Prodia, and Lexica, all of this without restrictions or limits

Installation

You can install the package via NPM

npm i gpti

CDN Links

If you'd rather not install the package via NPM, you can also include it directly from a Content Delivery Network (CDN).

Once you've included the script, you can use the package like this:

const { gpt, dalle, lexica, prodia } = gpti;

UNPKG:

To include the package from UNPKG, add the following script tag to your HTML file:

<script src="https://unpkg.com/gpti@1.0.5/gpti.js"></script>

jsDelivr:

To include the package from jsDelivr, add the following script tag to your HTML file:

<script src="https://cdn.jsdelivr.net/npm/gpti@1.0.5/gpti.js"></script>

esm.sh

For esm.sh, include the following script tag in your HTML file:

<script src="https://esm.sh/gpti@1.0.5/gpti.js"></script>

Skypack:

If you prefer using ES6 modules, you can import the package from Skypack as follows:

<script type="module">
    import { gpt, dalle, lexica, prodia } from 'https://cdn.skypack.dev/gpti@1.0.5';

    // Now you can use the 'gpti' package in your JavaScript code
</script>

These CDN options allow you to include the package in your web project with ease. Simply choose the one that fits your project's requirements.

Usage GPT

// import { gpt } from "gpti";
const { gpt } = require("gpti");

gpt({
    prompt: "hello gpt, tell me what your version is?",
    model: "gpt-4",                         // code or model
    type: "json"                            // optional: "json" or "markdown"
}, (err, data) => {
    if(err != null){
        console.log(err);
    } else {
        console.log(data);
    }
});

JSON

{
    "api": "gpti",
    "code": 200,
    "status": true,
    "model": {
        "code": 1,
        "type": "gpt-4"
    },
    "gpt": "Hello there! I'm GPT-4, the fourth version of the Generative Pre-trained Transformer (GPT) model. As an AI language model, I'm designed to generate human-like text based on the given inputs and previous context. I'm constantly trained on vast amounts of text data from the internet, books, and other sources to improve my understanding and generate more accurate responses. How can I assist you today?"
}

Models

Usage DALL·E

// import { dalle } from "gpti";
const { dalle } = require("gpti");

dalle({
    prompt: "starry sky over the city",
    type: "json"                            // optional
}, (err, data) => {
    if(err != null){
        console.log(err);
    } else {
        console.log(data);
    }
});

JSON

{
    "api": "dalleai",
    "code": 200,
    "status": true,
    "prompt": "starry sky over the city",
    "ul": "https://..."
}

Usage Lexica

// import { lexica } from "gpti";
const { lexica } = require("gpti");

lexica({
    prompt: "the sky is dyed with soft tones as the sun bids farewell",
    type: "json"                            // optional
}, (err, data) => {
    if(err != null){
        console.log(err);
    } else {
        console.log(data);
    }
});

JSON

{
    "api": "lexicaai",
    "code": 200,
    "status": true,
    "prompt": "the sky is dyed with soft tones as the sun bids farewell",
    "images": [
        {
            "ul": "https://..."
        },
        {
            "ul": "https://..."
        },
        ...
    ]
}

Usage Prodia

// import { prodia } from "gpti";
const { prodia } = require("gpti");

prodia({
    prompt: "the sun bids farewell in a warm sky, painting soft colors as the clouds dance",
    model: "Realistic_Vision_V5.0.safetensors [614d1063]",                          // code or model
    sampler: "Euler",                                                               // code or sampler
    steps: 25,                                                                      // 1-30
    cfg_scale: 7,                                                                   // 0-20
    negative_prompt: "",                                                            // optional
    type: "json"                                                                    // optional
}, (err, data) => {
    if(err != null){
        console.log(err);
    } else {
        console.log(data);
    }
});

JSON

{
    "api": "prodiaai",
    "code": 200,
    "status": true,
    "model": {
        "model": {
            "code": 25,
            "type": "Realistic_Vision_V5.0.safetensors [614d1063]",
            "name": "Realistic Vision V5.0"
        },
        "sampler": {
            "code": 1,
            "type": "Euler",
        }
        "steps": 25,
        "cfg_scale": 7,
        "prompt": "the sun bids farewell in a warm sky, painting soft colors as the clouds dance",
        "negative_prompt": ""
    },
    "ul": "https://..."
}

Models

Samplers

API Reference

Currently, the API has no access restrictions or usage limits.

For more details and examples, refer to the complete documentation

Success

The API can return the following success response code:

• 200 OK: The request was successful, and the response data is provided.

Errors

The API can return the following error codes:

• 400 Bad Request: Incorrect or insufficient parameters.
• 404 Not Found: The requested resource was not found.