DALL·E: Creating Images from Text

A little bit of fun…

Dall.E Mini has been trending on social media recently. It’s a text-to-image AI app that allows anyone to use machine learning technology to create fascinating and often bizarre art.

“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.”

Here’s my attempt: A tui in a tree wearing socks. On hindsight, some punctuation may have helped! Some turn out better than others…
Give it a go at huggingface.co - you may need to submit a few times before it works, the servers are working overtime.