The new version of the model has significantly increased the quality and speed of video rendering compared to previous versions. Users will now be able to create videos up to 12 seconds long in HD resolution (1280×720). The mockup allows you to create videos with different aspect ratios for different needs. One of the most important improvements was the high clarity of the frames and realistic movements of the created objects, achieved by the joint work of the scientific and engineering teams.
For accelerated video production, Kandinsky 4.0 Video Flash was introduced, which creates up to 12-second video sequences at 480p resolution in 15 seconds. This version is especially suitable for quickly creating short videos.
The Kandinsky 4.0 Video model was developed by the Sber AI team in collaboration with the AIRI Institute, and artists, designers and filmmakers will be the first to access it. In 2025, the neural network will be available to a wide audience.
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.
