Easy-to-use AI character generator that can be integrated in any app. It's based on Cloudflare Workers AI.

The code generates a name, back story, description of powers and traits plus the image of the character that is consistent with the description. The only input necessary is a string that contains a minimal description (eg. the the class of the character or its species).

Check out a live demo of how this works: AI Character Generator

First create a Wrangler project for making a Cloudflare Worker. Follow this guide, which in short means:

npm create cloudflare@latest

Input a name for your project (eg. ai-character-generator) and check Yes for everthing except for deployment. We will do that later.

cd ai-character-generator

In wrangler.toml add these lines at the end:

[ai]
binding = "AI"

npm install --save-dev @cloudflare/ai

npx wrangler dev

npx wrangler deploy

After deploying your worker you should get a URL to use for accessing it. The URL looks like https://ai-character-generator.<YOUR-SUBDOMAIN>.workers.dev

This URL is setup to respond to GET requests. Here are the params:

characterType

A string parameter that describes the RPG character you want to create. Include things like gender, race, class, etc. A good example would be female elvish warrior

responseType

Can be either json (default) or html.

When you send a request for JSON, it will return an answer with the following structure:

{
    "characterName": ...,
    "characterGender": ...,
    "characterClass": ...,
    "characterOrigins": ...,
    "characterPowers": ...,
    "image": "data:image/jpeg;base64,..."
}

At its core it is using 2 Cloudflare Workers AI models:

1. LLM - The zephyr-7b-beta-awq is a lightweight and fast text generation model. I use it for creating the textual information for the RPG character
2. Image Generation - The dreamshaper-8-lcm is a text to image generator that is fast and appropriate for generating images (especially in the digital painting style). This is a variation on the Stable Diffusion model, and LCM (Latent Consistency Model) is an optimization of the model which renders quality images with impressive speed.