OpenAI's latest model takes text messages and turns them into “complex scenes with multiple characters, specific types of movement” and more.
OpenAI is launching a new video generation model, and it's called Sora. AI -company says that Sora “can create realistic and imaginative scenes from text instructions.” The text-to-video model allows users to create photorealistic videos up to one minute long – all based on prompts they've written.
Sora can create "complex scenes with multiple characters, specific types of movement, and precise details of the subject and background," according to OpenAI's introductory blog post. The company also notes that the model can understand how objects "exist in the physical world," as well as "accurately interpret props and generate convincing characters that express vivid emotions."
The model can also generate a video based on a still image, as well as fill in missing frames of an existing video or extend it. The Sora-generated demos included in the OpenAI's blog posts include an aerial view of California during the gold rush, a video that looks like it was taken from inside a Tokyo train, and others. Many have some signs of AI — like a suspiciously moving floor in a video of a museum — and OpenAI says the model "may struggle to accurately simulate the physics of a complex scene," but the results are overall quite impressive.
A couple of years ago, it was text-to-image generators like Midjourney that were at the forefront of models' ability to turn words into images. But recently, video has begun to improve at a remarkable pace: companies like Runway and Pika have demonstrated their own impressive text-to-video models, and Google's Lumiere figures to be one of OpenAI's main competitors in this area as well. Similar to Sora, Lumiere provides users with text-to-video tools and also allows them to create videos from a still image.
Sora is currently only available to "red teamers" who assess the model for potential damage and risk. OpenAI also offers access to some visual artists, designers and filmmakers for feedback. It notes that the existing model may not accurately simulate the physics of a complex scene and may not correctly interpret some cases of cause and effect.
Earlier this month, OpenAI announced that it is adding watermarks to its text-to-image tool DALL-E 3, but notes that they "can be easily removed." Like its other AI products, OpenAI will have to contend with the consequences of mistaking fake, AI photorealistic videos for the real thing.
English 
Svenska