I was young when I first listened to the song Video Killed the Radio Star by the Buggles. I thought it was a fun and catchy song, almost like a jingle, even though I had no idea what the song was all about. But that was ok, I was just a young boy listening to the radio and watching videos on VCR machines. I didn't really pay much attention to the title or the lyrics. It was much later I realised what the lyrics actually meant. In my mind and in my car We can't rewind, we've gone too far Pictures came and broke your heart Put the blame on VCR The song was part of the Age of Plastic album, which had themes of nostalgia, anxiety of the effects of modern technology. While the album was released more than 40 years ago (it was released in 1980) these themes still ring true and clear.

Generative networks and OpenAI's CLIP are redefining what it means to be an artist.

With the rise of artificial intelligence (AI), we have heard how it will begin taking over many human tasks. This conversation has been largely focused around industries like manufacturing, customer service, and healthcare, where machines can carry out tasks incredibly efficiently. The creative realm was thought to be mostly off limits to machines, at least for now. Many believed they would not be able to paint a picture, create music, or write a book like us. These are tasks that absolutely require the free and creative human mind, and art is fundamental to the human experience.

This article is a write-up on how I built Text2Art.com in a week. Text2Art is an AI-powered art generator based on VQGAN CLIP that can generate all kinds of art such as pixel art, drawing, and painting from just text input. The article follows my thought process from experimenting with VQGAN CLIP, building a simple UI with Gradio, switching to FastAPI to serve the models, and finally to using Firebase as a queue system. Feel free to skip to the parts that you are interested in. If you like the project, you can vote for the project here.

What if we turn the Twitter logo into Mordor, which is an fair metaphor? So that didn't turn out well as the Twitter logo got overpowered by the prompt (you can see outlines of the logo's bottom). However, there's a trick to force the AI to respect the logo: set the icon as the initial image and the target image, and apply a high weight to the prompt (the weight can be lowered iteratively to preserve the logo better). Here's a few more good demos of what VQGAN CLIP can do using the ideas and tricks above: