How to use the latest language model from OpenAI to help write lyrics for original songs — I have been writing about the various iterations of OpenAI’s large language models for the last three years, including using GPT-3 [1] to compose music and ChatGPT [2], a.k.a. GPT-3.5, to write poetry. After experimenting with the latest language model, GPT-4 [3], I found that it can write song lyrics…

Finally, a way to let your pets tell you what they think about your dance moves — Have you ever wondered what your pets think about your questionable life choices? Or perhaps you’re dying to know if they secretly laugh at your dance moves? Well, the day has finally come when our beloved pets can openly communicate with us and even with each other, thanks to the…

How LAION used more data and new ML training techniques to improve image and text embeddings for various applications — I have been using and writing about OpenAI’s CLIP system since it came out in 2021 [1]. It consists of image and text encoding models that can be used for various forms of cross-modal comparison, like using a text query to find the best matching image in a library quickly. …

How the latest language model from OpenAI can help you write children’s books and create illustrations with Midjourney — This is the third and final installment of my series of three articles on using OpenAI’s ChatGPT language model [1] for creative writing. In the first article, I described using ChatGPT for writing prose, poetry, novels, and screenplays. In the second article, I showed how to use the system to…

How the latest language model from OpenAI can help you compose chords for new songs, with music by Band-in-a-Box — In my previous post, I discussed using ChatGPT, the large language model from OpenAI [1], as a writing partner for various types of prose. In this article, I will show how the system can be used to help compose music by generating chords from text prompts. After a brief overview…

How the latest language model from OpenAI can help write poetry, fiction, and screenplays — If you have been reading my posts on Medium, you will know that I have been writing about creative uses of AI since August 2020. I often write about generating digital art, but I occasionally write about using AI for other creative purposes, like writing prose and composing music. When…

A deep dive into the features and options for the popular text-to-image creation system — In my article last month, I tested three text-to-image generation systems, Stable Diffusion, DALL-E, and Midjourney, to see which was the best for creating digital art. [spoiler alert] Midjourney won the showdown. For the most part, I only used the default options for the three systems, even though many features…

A comparison of popular AI diffusion models for creating new works from text prompts — I have previously written about using the latest DALL-E [1] model from OpenAI to create digital art from text prompts. In this article, I will compare DALL-E to two other popular text-to-image models, Stable Diffusion from the CompVis group at LMU Munich [2] and Midjourney [3], by the research lab…

Since the Colab was slow, I upgraded to Pro. Each limerick cost me a dime. — In March 2022, I explored using AI to write poetry with a specific meter for my Deep Haiku article. For that project, I trained the GPT-J [1] language model to pay attention to the number of syllables in phrases to generate short poems given a subject. I didn’t take on…