1 min to read
Neural Topic Modeling with Continual Lifelong Learning
New statistical challenges from decentralized data
Description
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. I’ll introduce the method and implementational details of DALL·E.
Video
References
- A. Ramesh et al, “Zero-Shot Text-to-Image Generation”, Arxiv, 2021
- Official Blog Post
Comments