Artificial intelligence is taking the tech world by storm, and the latest player in this game is OpenAI with its new Sora video-generation model. This innovative AI tool can create realistic and imaginative scenes from text instructions, allowing users to produce photorealistic videos up to a minute long based on written prompts.

According to OpenAI, Sora is capable of creating complex scenes with multiple characters, specific types of motion, and accurate details of the subject and background. The model can even produce a video from a single still image and fill in missing frames in an existing video or extend its duration.

Although the model may struggle with accurately simulating the physics of a complex scene, the showcased results are quite impressive. OpenAI has made the software accessible for red teaming to pinpoint weaknesses in the AI system, as well as for visual artists, designers, and filmmakers who want to provide feedback on the model.

OpenAI has also revealed plans to add watermarks to its text-to-image tool DALL-E 3 but acknowledges that these watermarks can easily be removed. The company is developing tools to identify misleading content, including a detection classifier capable of recognizing videos generated by Sora.

It’s worth noting that Meta recently upgraded its image generation model Emu by adding two AI-based features that can edit and create videos from text prompts. It seems like the future of AI-generated Reels and short videos is closer than we expected. As we witness these advancements in AI technology, it’s essential for creators and users alike to be mindful of potential repercussions related to fake AI-generated photorealistic videos being mistaken for genuine content.