(Reuters) – Microsoft-backed OpenAI is developing software that can generate one-minute videos based on text prompts, the company said on Thursday.
The software, called Sora, is now available to red teams to help identify flaws in AI systems, and can be used by visual artists, designers and filmmakers to get feedback on models, the company said in a statement. .
“Sora can generate complex scenes with multiple characters, specific types of motion, and precise details of the subject and background,” the statement said, adding that it can create multiple shots within a single video. .
The company said in a blog post that apart from generating videos from text prompts, Sora can animate still images.
The video generation software follows OpenAI’s ChatGPT chatbot, which was released in late 2022 and created buzz around GenAI for its ability to compose emails and write code and poetry.
Last year, social media giant Meta Platforms enhanced its image generation model Emu with two AI-based features that can edit and generate videos from text prompts. Facebook’s parent company is trying to compete with Microsoft, Alphabet Inc.’s Google and Amazon in the rapidly changing world of generative AI.
Sora is in development, and the company adds that this model can confuse the spatial details of the prompts and make it difficult to follow certain camera trajectories.
OpenAI said it is also developing tools that can identify whether a video was generated by Sora.
(Reporting by Juveria Tabassum; Editing by Anil D’Silva)
