CogView2 checkpoints are now publicly available! A huge win for open ML research and the first time a text-to-image model of this quality has been publicly released
github.com/THUDM/CogView2
CogView2: Faster and Better Text-to-Image Generation via Hierarchical Transformers
abs: arxiv.org/abs/2204.14217
CogView2, shows very competitive generation compared to concurrent state-of-the-art DALLE-2, and naturally supports interactive text-guided editing on images.
Distill will be taking a one year hiatus starting today, which may be extended indefinitely. Our editorial team has written some reflections on what we've learned over the past five years, and the factors that led to this decision.
distill.pub/2021/distill-h…