openai

Sora 2

text-to-videoimage-to-video
Generates physics-accurate, multi-shot videos with synchronized audio, precise camera control, and realistic cameos from real-world faces and voices.
Input
No image provided.
An optional image to use as the first frame. The image must be the same aspect ratio as the target (Portrait is 720x1280, landscape is 1280x720).
Output
Your creation will appear here 🪄
History
Generated images and videos will be saved to a dataset for later reference.