- OpenAI’s new AI video generator, Sora, can generate realistic videos from natural language commands.
- Sora’s capabilities range from generating animated content to creating hyper-realistic videos that are indistinguishable from reality.
- The technology uses a diffusion model, creating videos from static noise until it resembles the desired image.
- Sora’s training involves compressing images and videos into “lower-dimension latent space”, then breaking that down further into “spacetime” patches.
- The generated videos are so convincing that they can easily be mistaken for real footage, raising concerns about the potential misuse of such technology.
- The feature is currently being tested and may not be available to all users.
Read more at: https://lifehacker.com