S
tool
Sora
AI model creating realistic videos from text, images, or existing videos.
Features
- Text-to-video generation
- Image-to-video generation
- Video extension and frame filling
- Generates videos up to one minute long
- Maintains visual quality and prompt adherence
- Simulates physical world in motion
- Generates complex scenes with multiple characters and specific motion
- Deep language understanding for accurate prompt interpretation
- Persists characters and visual style across multiple shots
- Utilizes diffusion model and transformer architecture