Canva unveils Brush, its first vision-language model built for design

Share

Canva launched Brush on October 29, 2026, an in-house vision-language model that analyzes layouts, layers, and visual styles to edit designs alongside users. Its outputs remain fully editable, and the model refines its work by analyzing the live design canvas as it operates. Canva says Brush performs editing tasks up to 69% faster than its previous agents and reduces their costs by 46%. Developed by Canva’s 160-person AI research lab, the model was trained on real design tasks and anonymized user data. Brush is initially available to Canva Pro subscribers as part of the company’s shift from relying on external models to building proprietary systems tailored to its creative workflows.

Source: Read the original article

Disclaimer: this content is for information purposes only and is not financial advice. Cryptocurrencies are highly volatile: you may lose all of your capital. Always do your own research. Legal notice
Telemac
Telemachttp://cryptoinfo.ch
Passionné de nouvelles technologies, j’explore l’univers de la blockchain et des cryptomonnaies pour partager l’actualité et les innovations du secteur.

Read More

Items