Researchers from Peking University have Asian movies Archivesformed a small team that is aiming to “reproduce” OpenAI’s text-to-video generator Sora, according to its project page on GitHub, after the original model took GenAI to the next level following its roll out in February. Collaborating with Shenzhen-based AI firm RabbitPre, China’s top academic institution is seeking resources from the open-source community as they are “unable to conduct full training” due to a lack of video data. However, the team has developed a three-part framework – including a Video VQ-VAE, a Denoising Diffusion Transformer, and a Condition Encoder – and presented its initial progress on GitHub, with four reconstructed video demos offering different resolutions and aspect ratios, ranging from three to 24 seconds in length. [GitHub]
(Editor: {typename type="name"/})
Notre Dame vs. Georgia football livestreams: kickoff time, streaming deals, and more
Sharks vs. Warriors 2024 livestream: Watch United Rugby Championship for free
Elon Musk's changes to blocking on X is a dangerous gamble
Should you buy sex toys from Shein?
Apple, Tesla, Spotify: The tech announcements that never happened in 2024
Best Samsung Galaxy deal: Save $300 on Galaxy Z Fold 6
Best gaming headset deal: Save $50 on HyperX Cloud II
Patriots vs. Jaguars 2024 livestream: How to watch NFL for free
Blockchain Explained: How It Works, Who Cares and What Its Future May Hold
NYT Strands hints, answers for October 20
Trump says he represents Pittsburgh, not Paris, but, um, well...
Michigan vs. Illinois livestream: Kickoff time, streaming deals, and more
接受PR>=1、BR>=1,流量相当,内容相关类链接。