Open-AI made a lot of buzz last year with the introduction of GPT-3. It was able to perform some very unique and beautiful things like building sites and designs, writing essays and stories, articles beating human authors, which are listed in my posts given below
It was also able to write movie scripts
This year OpenAI has started the year with a bang by debuting DALL-E. It is a transformer based neural network to make images based on text prompt and image prompt. It is named using a portmanteau of the artist Salvador Dalí and Pixar’s WALL·E.
According to 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 examples of images generated from DALL-E using text prompts are shown below -
You can check more details about it here.