Sora

Sora is an AI model by OpenAI that can create realistic and imaginative video scenes from text instructions. It can generate videos up to a minute long while maintaining visual quality and adherence to your prompt. Sora builds on past research in DALL·E and GPT models, using the recaptioning technique from DALL·E 3 to generate highly descriptive captions for visual training data. The model can follow your text instructions in the generated video faithfully, create multiple shots within a single generated video, and extend or fill in missing frames in an existing video. Sora serves as a foundation for models that can understand and simulate the real world, representing a significant milestone in achieving AGI.