@simplifyinterviews: Sora: More useful than ChatGPT? #software #Tech #ai #computerscience #sora Today, Sora is becoming available to red teamers to assess critical areas for harms or risks. OpenAI is also granting access to a number of visual artists, designers, and filmmakers to gain feedback on how to advance the model to be most helpful for creative professionals. It should be available soon and many people are already excited for the capabilities that it can have in terms of marketing, creating content, education, and more. You can find more detail on OpenAI’s website. At a more granular level, their research paper starts off by stating: “Video generation models as world simulators” We explore large-scale training of generative models on video data. Specifically, we train text-conditional diffusion models jointly on videos and images of variable durations, resolutions and aspect ratios. We leverage a transformer architecture that operates on spacetime patches of video and image latent codes. Our largest model, Sora, is capable of generating a minute of high fidelity video. Our results suggest that scaling video generation models is a promising path towards building general purpose simulators of the physical world. Once it opens up to the general public, I’ll test it out and let you know what I think :)

Jay Jung

Open In TikTok:

Region: US

Friday 16 February 2024 01:00:56 GMT