NÜWA: Visual Synthesis Pre-training for Neural visUal World creAtion
abs: arxiv.org/abs/2111.12417
presents a unified multimodal pretrained model that can generate new or manipulate existing visual data (i.e., images and videos) for various visual synthesis tasks
NÜWA achieves state-of-the-art results on text-to-image generation, text-to-video generation, video prediction, etc. Furthermore, it also shows surprisingly good zero-shot capabilities on text-guided image and video manipulation tasks
Sketch-to-Video (S2V)
Text-Guided Video Manipulation (TV2V)
Image Completion (I2I)
Text-Guided Image Manipulation (TI2I)
github: github.com/microsoft/NUWA
Text-to-Image
Sketch to Image
Sketch to Image
Image Completion
Image Completion
research talk:
Share this Scrolly Tale with your friends.
A Scrolly Tale is a new way to read Twitter threads with a more visually immersive experience.
Discover more beautiful Scrolly Tales like this.
