"Debating the Future of OpenAI's Sora: From Photorealistic Videos to Flaws and Criticisms"
OpenAI's new app Sora uses AI to generate photorealistic videos based on text prompts, showcasing impressive cinematic storytelling capabilities and photorealism. The app, powered by a version of the diffusion model used by OpenAI’s Dalle-3 image generator and the transformer-based engine of GPT-4, can produce longer clips than other models and demonstrates an emergent grasp of cinematic grammar. While the app is still in the research phase, it has the potential to revolutionize video production and storytelling, although OpenAI is cautious about the potential for misuse, such as deepfakes and misinformation.
