SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2305.10474 · ICCV · 2023

Preserve Your Own Correlation: A Noise Prior for Video Diffusion Models

Jia-Bin Huang, Songwei Ge, David Jacobs, Seungjun Nah, Ming-Yu Liu, Andrew Tao, Nvidia Guilin, Liu Nvidia, Tyler Poon, Nvidia Bryan, Catanzaro Nvidia, Nvidia Yogesh, and 1 more

arXiv · PDF · Open in the Atlas

Code that ran

We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. If it links a repository, it is listed below.

Abstract

A very happy fuzzy panda dressed as a chef eating pizza in the New York street food truck. The supernova explosion of a white dwarf in the universe, photo realistic. A high-quality 3D render of hyperrealist, super strong, multicolor stripped, and fluffy bear with wings, highly detailed. * Work done during an internship at NVIDIA. model, Preserve Your Own COrrelation (PYoCo), attains SOTA zero-shot text-to-video results on the UCF-101 and MSR-VTT benchmarks. It also achieves SOTA video generation quality on the small-scale UCF-101 benchmark with a 10× smaller model using significantly less computation than the prior art. The project page is available at https: //research.nvidia.com/labs/dir/pyoco/.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2305.10474")
get_code_for_paper("2305.10474")
have("2305.10474")

Connect an agent — have() is free.