microsoft/NUWA: A unified 3D Transformer Pipeline for visual synthesis - NUWA

A unified 3D Transformer Pipeline for visual synthesis

Перейти к файлу

Nan Duan a8242f0e67 Update README.md		2023-05-29 17:07:41 +08:00
assets	update	2022-07-22 15:23:23 +08:00
NUWA.md	update NUWA-Infinity	2022-07-21 10:29:54 +08:00
NUWAInfinity.md	update project page.	2022-07-21 10:42:11 +08:00
README.md	Update README.md	2023-05-29 17:07:41 +08:00
SECURITY.md	Microsoft mandatory file	2022-07-25 18:58:44 +00:00

README.md

This is the official repo for the following papers:

NÜWA: Visual Synthesis Pre-training for Neural visUal World creAtion. (ECCV 2022)
NUWA-Infinity: Autoregressive over Autoregressive Generation for Infinite Visual Synthesis. (NeurIPS 2022)
NUWA-LIP: Language Guided Image Inpainting with Defect-free VQGAN. (CVPR 2023)
Learning 3D Photography Videos via Self-supervised Diffusion on Single Images. (IJCAI 2023)
NUWA-XL: Diffusion over Diffusion for eXtremely Long Video Generation. (ACL 2023)

Update 2022/7/13: NUWA-Infinity

[Project page] [Paper]

NUWA-Infinity is a generative model for infinite visual synthesis, which is defined as the task of generating arbitrarily-sized high-resolution images or long-duration videos.

Update 2021/11/26: NÜWA

NÜWA is a unified multimodal pre-trained model that can generate new or manipulate existing visual data (i.e., images and videos) for 8 visual synthesis tasks (as shown above).