Sber has introduced a free test version of Kandinsky Video 1.1. The neural network was developed by Sber AI in collaboration with scientists from the Artificial Intelligence Institute AIRI on a combined dataset from Sber AI and SberDevices. The updated version can create 6-second videos based on text and images.
The improved Kandinsky Video 1.1 neural network opens up new possibilities:
- video sequence lasting up to six seconds with a frame rate of 8 and 32 per second;
- selection of the required video format at the output - 16:9, 9:16 or 1:1 (screen aspect ratio);
- control of video dynamics is due to the motion score parameter.
It is worth recalling that the first version of Kandinsky Video waspresented in November 2023.
Less than a year has passed since the launch of the first version of the neural network, and during this time our team has significantly improved indicators such as the quality and speed of generating full-fledged videos, thereby opening up limitless horizons for creativity.
The opportunity to test the neural network is open to all users. This can be done on thefusionbrain.ai platform or using a Telegram bot.
Read materials on the topic:
Sber expands access to the GigaChat chatbot in Telegram for all users
The first real Russian competitor to ChatGPT? Sber introduced GigaChat
Now on home
TUSUR and JINR Join Forces to Develop Radiation Protection Materials
The cargo aircraft belongs to Sky Gates Airlines
Director of ZNPP spoke about plans to restore the "Dneprovskaya" line
SMK filed a lawsuit against the Moscow enterprise JSC "MMZ Skorost"
Roscosmos approves final schedule: the first ROS module will go into orbit in 2 years
The test flight will take place in June 2026
Ivan Khamin proposed an engine design with coupled turbines
Aircraft No. 96115 completed a flight from Zhukovsky to Novosibirsk and back
The platform allows you to send short videos to random people and watch other people's video messages