OpenAI may use 3D engine/Unreal Engine to train video model Sora

OpenAIRecently published severalSoraThe resulting videos, which showcase stunning 3D effects, include everything from diving to exploring a shipwreck to dioramas depicting serene scenes from Japan’s Edo period.

In addition, Sora also demonstrated some new features, such as seamless transitions. This means that the two input videos can be gradually interpolated to present a smoother transition effect. Some netizens began to discuss the source of the training data behind Sora's generated videos. The mainstream view is that Sora may have used3D EngineorUnreal EngineConduct training.

OpenAI may use 3D engine/Unreal Engine to train video model Sora

Source Note: The image is generated by AI, and the image is authorized by Midjourney

These newly released videos once again highlight OpenAI's leading position in the field of artificial intelligence and their continuous efforts in developing cutting-edge technologies. Through continuous optimization and updates, Sora's generative video technology has reached an amazing level, bringing users a more vivid and attractive visual experience.

OpenAI's Sora video generation technology not only demonstrates its innovative capabilities in the field of artificial intelligence, but also shows us the potential of the future in digital media and visual effects. These videos are not only visually stunning, but also spark people's imagination of the infinite potential of artificial intelligence technology in the fields of creation and entertainment.

statement:The content is collected from various media platforms such as public websites. If the included content infringes on your rights, please contact us by email and we will deal with it as soon as possible.
Information

Microsoft and former Google CEO back AI startup Synth Labs to make AI systems work as humans expect

2024-3-1 9:32:02

Information

OpenAI CEO Sam Altman is under SEC investigation for allegedly misleading investors

2024-3-1 9:33:27

Search