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

Nissan Leaf EV to Become NACS-Ported Compact Crossover in Third Generation

Nissan Leaf can rightfully be considered a long-liver of the electric car market, since the…

3 days ago

OpenAI expects to more than triple its revenue this year and then double it next year.

OpenAI, the market leader in generative artificial intelligence systems, remains nominally a startup, its financial…

3 days ago

OpenAI Decides to Hold 4o Image Generation Launch for Free Users

OpenAI has been forced to delay the release of ChatGPT's built-in image generator for free…

3 days ago

1440p and 240Hz for just $200: Xiaomi updates the 27-inch Redmi G27Q gaming monitor

Xiaomi continues to update its Redmi G27Q gaming monitor every year. The model was first…

3 days ago

Beware, Android is shutting down: OS development will cease to be public, but there is no reason to panic

Android device makers can significantly customize the look and feel of the operating system, but…

3 days ago

Fake GeForce RTX 4090s with RTX 3090 chips have started popping up in China — craftsmen are even changing the GPU markings

In China, scammers have started selling GeForce RTX 3090 graphics cards, passing them off as…

3 days ago