NÜWA: Visual Synthesis Pre-training for Neural visUal World creAtion

This paper presents a unified multimodal pre-trained model called N\"UWA that can generate new or manipulate existing visual data (i.e., images and videos) for various visual synthesis tasks.

Released in: NÜWA: Visual Synthesis Pre-training for Neural visUal World creAtion

Source: arXiv - NÜWA: Visual Synthesis Pre-training for Neural visUal World creAtion

Contributor:

by

Homepage

Summary

This paper presents a unified multimodal pre-trained model called N\”UWA that can generate new or manipulate existing visual data (i.e., images and videos) for various visual synthesis tasks.

328K

Images in dataset

2017

Year Released

Key Links & Stats

lucidrains / nuwa-pytorch

NÜWA: Visual Synthesis Pre-training for Neural visUal World creAtion

@misc{wu2021nuwa, title = {N\"UWA: Visual Synthesis Pre-training for Neural visUal World creAtion}, author = {Chenfei Wu and Jian Liang and Lei Ji and Fan Yang and Yuejian Fang and Daxin Jiang and Nan Duan}, year = {2021}, eprint = {2111.12417}, archivePrefix = {arXiv}, primaryClass = {cs.CV} }

scenebox

Modalities

  1. Still Image
  2. Video

Verticals

  1. Satellite

ML Task

  1. Image Generation

Related organizations