OpenAI introduced Sora, its first generative Text-to-Video model that transforms text instructions into photorealistic videos.
For the moment it is not open to the public but only to a selected group of security experts (who must test its reliability) and creators, and is capable of generating videos of up to 60 seconds in HD quality starting from a simple text, exactly as happens for images with Dall-E 3 (also from OpenAI), Midjourney or Stable Diffusion.
In introducing Sora, OpenAI published several example videos that show what the new generative model is capable of.
However, the company has not released technical specifications describing in more detail how the model works, has not given journalists access to test its capabilities and has not specified when it will be opened to the public.
Meanwhile, what can be understood by analyzing the images made public is that, although they are not perfect, they still seem to be a significant step forward compared to other generative text-to-video models currently available, such as Runaway (now in Gen2) or Pika.
We talk about it during the seventh episode of the podcast "La Fabbrica della Realtà", with Massimo Sebastiani and Alessio Jacona, which you can listen to on Spreaker, Spotify, Apple Podcasts or even watch on Youtube.
And then also on Instagram, in this video for Instagram created by Alessio Jacona.
Reproduction reserved © Copyright ANSA