YandexART 2.0 AI model with support for generating text on images has been introduced

«Yandex has released YandexART 2.0, a new generation image generator. The neural network has learned to create inscriptions on an image and maintain several styles at once in one picture; objects in space and relative to each other are now located more naturally; and when creating images, more query details are taken into account.

Image source: Yandex

A distinctive feature of YandexART 2.0 is its hybrid neural network architecture, combining features of convolutional and transformer models. The convolutional model works like the human eye, identifying key features of an object, such as its shape, texture and edges, but it is limited in the length of the context, so it is assisted by a transformer for long queries. This architecture helps YandexART 2.0 handle multiple genres in a single image—for example, it can depict an anime label on a photorealistic lemonade bottle.

To train the YandexART 2.0 neural network, several hundred million pairs of images and text descriptions for them were used; a more accurate relationship was provided by an additional VLM model, with the help of which the pictures were analyzed and accompanied by detailed text descriptions. The array of training data was expanded to include several hundred thousand images with text – this helped YandexART 2.0 to supplement pictures with inscriptions in Latin letters.

«Yandex also developed its own system for assessing the quality of work for the image generator: the new model beat Midjourney v6.1 in terms of complexity and aesthetics in 66% and 58% of cases, respectively, and also came closer to it in terms of relevance to queries.

Business users can work with YandexART 2.0 on the Yandex Cloud platform – using the API, you can integrate the image generator into any application; It is possible to test its operation in demo mode to select the optimal queries. Corporate clients can generate logos, illustrations for articles, presentations or social networks.

The visual neural network is also available to private users in the web version of Alice and its own virtual assistant application; owners of free accounts can request up to five images per day, and subscribers of the Alice Pro option do not have such a limitation. With YandexART 2.0 you can create an avatar for social networks, an application icon, a print for a T-shirt, a postcard for a friend or an illustration for publication.

admin

Share
Published by
admin

Recent Posts

Despelote — goo-o-o-o-o-o-o-o-o-o-ol! Review

One of my first memories (or perhaps the very first one – is it possible…

8 hours ago

Design and specifications of the flagship smartphone Sony Xperia 1 VII leaked online

A few days before the official presentation, details about the new flagship Sony Xperia 1…

9 hours ago

GTA VI Delay to 2026 Causes New Panic Among Game Developers

Bloomberg journalist Jason Schreier reported on the domino effect triggered by the recent delay of…

9 hours ago

Nintendo warns it will block consoles for users who engage in piracy and hacking

Nintendo has updated its user agreement, formalizing the right to remotely disable Switch consoles if…

10 hours ago

Gigabyte Unveils X870 and B850 Aorus Stealth Motherboards with Back-Side Power Connectors

Gigabyte has unveiled the X870 Aorus Stealth and B850 Aorus Stealth motherboards for Ryzen 7000,…

12 hours ago

Alienware Unveils Thin, Affordable Aurora 16 and 16X Gaming Laptops with Understated Designs

Alienware, a subsidiary of Dell known for its futuristic gaming laptops, has released new high-performance…

1 day ago