Researchers from Peking University have Mission XXX Impossibleformed 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]
Related Articles
2025-06-26 05:31
2387 views
NYT Connections hints and answers for May 10: Tips to solve 'Connections' #699.
Connectionsis the one of the most popular New York Times word games that's captured the public's att
Read More
2025-06-26 05:12
2839 views
Kaepernick jersey sales skyrocket following controversy
Colin Kaepernick struck a chord when he sat in protest during the singing of the national anthem bef
Read More
2025-06-26 03:14
2730 views
Single mom wears a fake mustache so her son doesn't miss 'Donuts with Dad'
A single mom went above and beyond during a Donuts with Dad event at her son's school in an attempt
Read More