Sora is a groundbreaking text-to-video model developed by OpenAI[3]. Introduced in February 2024, it has been designed to convert text inputs into high-definition videos using advanced AI technologie[2]. Sora is built on the diffusion transformer model, the same technology behind DALL·E 3, another OpenAI innovation. The model generates videos by transforming latent space into standard space. Despite its potential, it does have limitations, especially with complex physics and causality. Sora has been widely discussed for its potential to revolutionize video creation processes across various sectors like marketing and entertainment. However, it has also drawn some criticism, particularly around the potential for disinformation[1] and its impact on industries like film.
Sora is an upcoming intelligence artificielle générative model developed by OpenAI, that specializes in text-to-video generation. The model accepts textual descriptions, known as prompts, from users and generates short video clips corresponding to those descriptions. Prompts can specify artistic styles, fantastical imagery, or real-world scenarios. When creating real-world scenarios, user input may be required to ensure factual accuracy, otherwise features can be added erroneously. Sora is praised for its ability to produce videos with high levels of visual detail, including intricate camera movements and characters that exhibit a range of emotions. Furthermore, the model possesses the functionality to extend existing short videos by generating new content that seamlessly precedes or follows the original clip. As of April 2024,[mise à jour] it is unreleased and not yet available to the public.
Developer(s) | OpenAI |
---|---|
Platform | OpenAI |
Type | Text-to-video model |
Site web | openai |