- Judith Akatugba
- 0 Comments
- 181 Views
OpenAI, which is sponsored by Microsoft, is developing software capable of producing minute-long videos in response to text commands, the company announced on Thursday.
Read Also: How to Prepare Party Jollof Rice and Plantain
The company stated in a statement that the Sora software is presently accessible for red teaming, which aids in the detection of AI system faults, and for visual artists, designers, and filmmakers to obtain feedback on the model.
“Sora is capable of generating intricate scenes featuring numerous characters, distinct types of motion, and precise subject and background details,” the statement continued, adding that the software is also capable of producing multiple shots within a single video.
As stated in a blog post by the company, Sora is capable of animating still images in addition to generating videos based on text prompts.
The video generation software succeeds OpenAI’s ChatGPT chatbot, whose capability to compose emails, codes, and poems generated excitement around GenAI when it was introduced in late 2022.
Last year, Meta Platforms, a social media behemoth, enhanced its Emu image generation model with two AI-powered capabilities that enable the generation and editing of videos in response to textual commands.
Furthermore, the Facebook parent company aims to contend with Microsoft, Alphabet’s Google, and Amazon in the realm of generative AI, which is undergoing a rapid transformation.
The company further stated that Sora is an ongoing development and could potentially struggle to track a specific camera trajectory and miss spatial details within a prompt.
OpenAI has also stated that it is developing tools capable of determining whether a video was produced by Sora.
