Tweeted By @_akhaliq
ERNIE-ViLG 2.0: Improving Text-to-Image Diffusion Model with Knowledge-Enhanced Mixture-of-Denoising-Experts
— AK (@_akhaliq) October 28, 2022
abs: https://t.co/TYNxPv2K5F
achieves a zero-shot FID-30k score of 6.75 on the MS-COCO dataset pic.twitter.com/VRUeIJRRVR