No elephants: Breakthroughs in image generation

DALL·E 2 currently has a very limited ability to render legible text. When it does, text may sometimes be nonsensical and could be misinterpreted. It’s important to track this capability as it develops, as image generative models may eventually develop novel text generation capabilities via rendering text.

7 ways to use ChatGPT's new image AI

Cartoons

I've always wanted to draw cartoons but never had the skill. Now I can quickly prototype visual sequences. While human cartoonists bring unique creativity that AI can't replicate, this tech allows anyone to experiment.

To test continuity I generated multiple versions of the same cartoon in the same ChatG... See more

Finally, once these models become faster, you can imagine a truly generative UI, where the model produces the next frame of the app you are using based on events sent to the LLM (which can do all the normal things like using tools, thinking, etc). However, I also believe that diffusion models can do some of this, in a much faster way.