From Open-AI blog: DALL-E is a 12-billion parameter version of GPT-3 trained to generate images from text descriptions, using a dataset of text–image pairs. We’ve found that it has a diverse set of capabilities, including creating anthropomorphized versions of animals and objects, combining unrelated concepts in plausible ways, rendering text, and applying transformations to existing images.
Some of the images created from text are incredible:
You can request to join the waitlist here
I have waited a few weeks and have not heard back.
I proposed to research cybersecurity and AI through general exploration. The concept would be to apply behavioral analysis and technique to identify trends, anomalies before they become disruptive. I'm sure there are many more ideas. What are yours?