Each generation takes about 2 seconds, but the clips can be connected to longer scenes. Voyager works with two key technologies. First, it creates data and depth data at the same time. Secondly, it uses a number of 3D world cache ”, one of the previous squares that help maintain the image of the image while changing the angles.
For training, the model “watched ısız more than 100 thousand videos, including scenes in the Unreal engine. This allows the camera to simulate how it moves in games and movies. However, the system is not perfectly cope, while the media writes.
Voyager is already available on the Huging Face platform, but requires strong systems between 60 to 80 GB video memory. You can only use the model in commercial projects with a large audience for a separate license.
Source: Ferra
I am a professional journalist and content creator with extensive experience writing for news websites. I currently work as an author at Gadget Onus, where I specialize in covering hot news topics. My written pieces have been published on some of the biggest media outlets around the world, including The Guardian and BBC News.
