Sber is actively developing the Kandinsky neural network and will soon present its updated version. This was announced by Alexander Vedyakhin, a senior employee of the bank, at the Financial Congress of the Bank of Russia.
According to Vedyakhin, the new version of the Kandinsky neural network will give users more options for working with images and significantly improve the quality of creation.
At the same time, it will retain all the benefits of the previous version, including the neural network, combining multiple drawings, creating infinite canvases, completing missing image elements, and other useful features.
The Kandinsky 2.1 neural network has attracted 1 million users just four days after its launch, making it the fastest growing network in the world. In three months, more than 70 million images were created with his help.
The development and training of the neural network was carried out by Sber AI researchers with the support of scientists from the AIRI Institute of Artificial Intelligence, based on a joint dataset of Sber AI and SberDevices.
You can evaluate the capabilities of the neural network in the Salyut mobile application by using the “Start the artist” command on the special demo page of the model, on the Fusion Brain platform, on the Telegram bot, on Sber smart devices. and on the ML Space platform in the DataHub hub of pre-trained models and datasets.
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.
