Text-to-Video Models and Sora in Plastic Surgery: Pearls, Pitfalls, and Prospectives

After the groundbreaking release of the highly acclaimed chatbot ChatGPT, which revolutionized the field of artificial intelligence (AI) last year, OpenAI has once again astounded the world with the unveiling of their latest generative AI model, Sora, on February 16, 2024. This cutting-edge model has the remarkable ability to generate videos up to a duration of 60 seconds solely through text instructions. With a series of AI-generated contents, such as AI chat, AI drawing, and AI music, emerging one after another, the era of "AI revolution" that had a disruptive impact on modern life has arrived. Meanwhile, AI has made significant achievements in the medical field, especially in diagnosing based on medical imaging. This article briefly describes the development history of text-to-video models and provides a detailed introduction to the Sora model, including its portrayal of the human face and contour, inspiring its potential applications in plastic surgery. It also provides a prospect for other AI-generated content technologies, such as text-to-holography and text-to-material objects.

Level of Evidence V This journal requires that authors assign a level of evidence to each article. For a full description of these Evidence-Based Medicine ratings, please refer to the Table of Contents or the online Instructions to Authors www.springer.com/00266.