SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2402.14797 · CVPR · 2024

Snap Video: Scaled Spatiotemporal Transformers for Text-to-Video Synthesis

Aliaksandr Siarohin, Sergey Tulyakov, Elisa Ricci, Fondazione Kessler, Jian Ren, Tsai-Shien Chen, Anil Kag, Ivan Skorokhodov, Willi Menapace, U Merced, Yuwei Fang, Ekaterina Deyneka, 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. We have no repository linked to it either. That is a statement about our graph, not about the paper.

Abstract

snap-research.github.io/snapvideo "Atop dramatic cliffs, two warriors engage in a sword fight. [...]" "Dust fills the air as off-road vehicles tear through a vast desert landscape. [...]" "[...] a movie set where an otter serves as a film director. [...] raised paws shouting 'Action!' [...] " "[...] corgi dog riding a bike in Times Square. It is wearing sunglasses and a beach hat." "A cowboy panda riding on the back of a lion, hand-held camera." "In the vastness of space, starships engage in a cosmic clash. [...]" "In an empty parking lot, film a professional car drifting exhibition. [...]" "[...] a cat donned in a chef's hat expertly kneads dough [...]" Figure 1. Samples produced by the proposed text-to-video generation method for a selection of prompts. Thanks to joint spatiotemporal video modeling, our generator can synthesize temporally coherent videos with large motion (left) while retaining the semantic control capabilities typical of large-scale text-to-video generators (right). See the Website for additional samples.

For agents

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

get_harvested_code_for_paper("2402.14797")
get_code_for_paper("2402.14797")
have("2402.14797")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/2402.14797.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/2402.14797.svg)](https://syntology.ai/paper/2402.14797)

Connect an agent — have() is free.