Sber presented a new version of Kandinsky’s model for generating images based on text descriptions. One of the key features was faster generation speed and improved image resolution, the company said.
Join
The updated version of Kandinsky 3.1 was additionally trained on a zoomed-in image dataset, allowing for improved quality of the generations. Artists, designers and bloggers were the first to access Kandinsky 3.1. In the near future it will be available to all users.
One of the key features of the version is a higher image generation speed: the time of one generation has been reduced by almost 10 times and the resolution can now be increased to 4K.
It was also possible to improve text query using a language model. Users will be able to create different image variations, mix images and text, create sticker packs, and make local changes to the image without changing the entire scene composition (ControlNet).
Additionally, a new Kandinsky Video 1.1 model will appear in the near future to generate videos from text descriptions.
Author:
Anastasia Marina
Source: RB
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.
