Tag: gpt3

Process

Unity Integration for Stable Diffusion & ChatGPT for AI Image + Speech Generation

By Alex Inglewood | by Alex Inglewood

There are other tools out there that allow the integration of Stable Diffusion, ChatGPT, and Text to Speech (TTS) into Unity, but this guide is intended to make integrating them all very simple. The below script doesn’t have the best coding practices, but it is an easy place to start with Unity AI integrations. Start By Getting All the Service Keys You of course will have to get your own keys from each service: Get…

Continue reading

Process

Story Generation using GPT4 vs. GPT3.5-turbo (ChatGPT)

By Alex Inglewood | by Alex Inglewood

GPT4 for stories is a vast improvement. The coherency of 3 wasn’t all that good, and 3.5-turbo (also known as ChatGPT) still left something to be desired. The upgrade for GPT4 over ChatGPT (3.5-turbo) is a larger upgrade than the DaVinci 2 to 3 change for GPT3. Some of the issues with 3 and 3.5-turbo that are better in GPT4 An Example with GPT4 vs. GPT3.5-turbo (ChatGPT) Prompt: Write a long chapter in the following…

Continue reading

Process

GPT3’s DaVinci 3 vs 2 Models

By Alex Inglewood | by Alex Inglewood

Recently OpenAI has released a new model version in GPT3, Davinci-3. This model greatly improves on the formerly most powerful model, Davinci-2. However it also has some oddities that are worth knowing. You can select Davinci-3 in the Model drop down menu on the right side of the Playground web interface. Poetry and the Concept of Rhyming First, the concept of rhyming is much more advanced in the Davinci-3 model, with every couplet having a…

Continue reading