Yandex introduced a new version of artificial neural networks to users by introducing YandexART 1.3. This new version better understands text-based commands and produces more realistic images. Here are all the details…
What does YandexART 1.3 bring?
With an improved technology, latent diffusion, YandexART 1.3 opens a new way to create images. This technology requires fewer computational resources and makes it easier to create higher quality graphics. The process begins by developing an intermediate image representation known as a secret code. The neural network then converts this code into a high-resolution image in a single step.
To help the model better understand user prompts, Yandex also added detailed image descriptions generated by the neural network, known as synthetic texts, to the training dataset. This dataset has been expanded, allowing YandexART to take into account more details from user requests.
Yandex introduced mapping solutions for Turkish businesses
Yandex introduced its mapping, geolocation and navigation solutions for businesses in Turkey under the Yandex Maps API brand.
The updated YandexART allows users to create images in various formats and makes these images usable in different media. Internal evaluations reveal that YandexART 1.3 performs better than previous versions. This allows users to obtain more accurate and realistic results.
YandexART 1.3 is currently available in the Shedevrum application all over the world, including Türkiye. In this way, users can unleash their creativity by creating various images and animations with text-based commands.
What do you think about this issue? Don’t forget to share your opinions with us in the comments!