Researchers from Peking University have eroticize arrobicsformed 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"/})
Donald Trump talked about space and Buzz Aldrin's face says it all
Study finds brain tissue 'changes' in kids who played one season of football
Delta Air Lines now lets you obsessively track your luggage in real
Here's proof that Ellie Goulding would definitely beat you in a fight
Best fitness deal: The Merach R50 rowing machine is 35% off at Amazon
Flying 'Harry Potter' brooms come to 'Destiny' for Halloween
Apple updates macOS with bug fixes ahead of big MacBook event
Moving film calls for the protection of the 'I' in LGBTIQ
Creators talk accessibility and building inclusive spaces at VidCon 2025
Emma Watson really wishes she could vote in the U.S. elections
Instant Pot Duo Plus deal: $69.99 at Amazon
This poster mocking refugees was taped in Parliament's kitchen
接受PR>=1、BR>=1,流量相当,内容相关类链接。