OpenAI's New Model 'Sora' Can Create Video From Text

OpenAI, the company behind ChatGPT and DALL-E, has announced a new text-to-video model called Sora. The model is able to generate videos up to a minute long from a simple text prompt.

How it Works

Sora is a diffusion model, which is a type of generative model that is trained on a massive dataset of text and images. When you give Sora a text prompt, it uses its knowledge of the world to create a video that matches your description.

The Results

The results from Sora are impressive. The model is able to generate high-quality videos with a wide range of subjects, from realistic depictions of people and animals to fantastical scenes.

The Implications

Sora has the potential to revolutionize the way we create and consume video. It could be used to create everything from short films and music videos to educational content and marketing materials.

The Future of Video

Sora is still in its early stages, but it's a clear sign of the power of generative AI. As these models continue to improve, we can expect to see even more amazing and creative applications of text-to-video technology.