Sora is a text-to-video model that can also take existing still images and generate videos from them
OpenAI, the creator of ChatGPT, said it is developing software called Sora that can generate minute-long videos based on text prompts.
The Microsoft-backed company says Sora is a text-to-video model that can also take existing still images and generate videos from them.
About ChatGPT Creator OpenAI’s Sora
Sora can generate videos up to a minute long while maintaining visual quality and complying with user prompts.
Sora can also generate complex scenes with multiple characters, specific types of movement, and accurate details of subjects and backgrounds.
OpenAI, led by Sam Altman, says the new tool can understand not only what users ask for in prompts, but also how those things exist in the physical world.
OpenAI says Sora’s deep understanding of language allows it to accurately interpret cues and generate compelling characters that express vibrant emotions.
Sora can also create multiple shots within a single generated video, accurately preserving character and visual style.
The software follows in the footsteps of OpenAI’s ChatGPT chatbot, which was released in 2022 and generated buzz around GenAI for its ability to compose emails, write code, and write poetry.
OpenAI also published results on some hints on X. It includes a short video of the animated scene, which features a close-up of a furry little monster kneeling next to a melting red candle.
Another photo shows “a stylish woman walking down a Tokyo street filled with warm neon lights and animated city signage.”
Introducing Sora, our text-to-video model.
Sora can create videos up to 60 seconds long with highly detailed scenes, complex camera movements, and multiple characters full of vibrant emotions. https://t.co/7j2JN27M3W
Tip: “Beautiful, snowy… pic.twitter.com/ruTEWn87vf
— OpenAI (@OpenAI) February 15, 2024
Prompt: “A stylish woman walks down a Tokyo street filled with warm neon lights and animated city signs. She wears a black leather jacket, a long red skirt and black boots, and carries a black purse. She wears sunglasses and red lipstick. She Walking confidently and casually… pic.twitter.com/cjIdgYFaWq
— OpenAI (@OpenAI) February 15, 2024
However, OpenAI said the current model has weaknesses, adding that it may struggle to accurately model the physics of complex scenarios and may not understand specific instances of cause-and-effect relationships. For example, a person may take a bite of a cookie, but the cookie may not show a bite mark afterwards.
OpenAI partners with “red team” to develop Sora
OpenAI said it will take several important security measures before launching Sora.
The creators of ChatGPT say it is building tools to help detect misleading content, such as a detection classifier that can tell when Sora has generated a video.
The company also said it is working with red team members – experts in areas such as misinformation, hateful content and bias – who will adversarially test the new text-to-video model.
