Generative AI is the hype of technology, and many tech companies are adopting it to enhance their offerings.
Since OpenAI introduced ChatGPT, the trends of generative AI is going no where but up. Adobe piggybacked the trend, and entered the generative AI race with an image generator it calls the 'Firefly' to power its design tools.
After bringing the AI tool to Photoshop, this time, it's time for Illustrator to gain the benefit.
Illustrator is Adobe’s vector graphics tool for graphic artists, and that it'
Whereas Photoshop deals with raster images, Illustrator is a popular tool for creating vector graphics.
Adobe announced the support of the generative AI during the launch of the Firefly Vector Model at Adobe’s MAX conference.
Check out Adobe Illustrator’s NEW Text to Vector Graphic feature! Create stunning, scalable vector graphics - including icons, scenes, and patterns - with a simple text prompt. Learn more: https://t.co/4TrUmyrn46 #AdobeMAX pic.twitter.com/W3e2xjIuKd
— Adobe Creative Cloud (@creativecloud) October 10, 2023
Adobe describes the model as "the world’s first generative AI model focused on producing vector graphics."
Like Firefly for creating images and photos, Firefly for Illustrator is meant to aid users create entire vector graphics from scratch.
By just describing what to create, the AI can help users generate vector images on the fly, complete the mathematical equations to define the images' shapes, lines, and curves. The images can also consist of multiple objects, meaning that users can manipulate them individually, just like any other group or layer in Illustrator.
And like the other Firefly models, the vector model was also trained on data from Adobe Stock.
In a blog post, Alexandru Costin, Adobe’s VP for generative AI and Sensei, said that the company used tens of millions of vector images in Adobe Stock to train Firefly to enable this capability.
Costin described the process as “a journey.”
Besides the Firefly Vector Model, Adobe introduced two more new AIs.
The first is Firefly Image 2 Model, the successor of the company's initial take on text-to-image generators. This more-advanced successor introduces increased quality of renditions, which boast enhanced photographic quality for high-frequency details, higher resolutions, more vivid colors, and improved human renderings, according to Adobe.
The model also has new capabilities, including: Generative Match, which allows users to upload or select an image they'd like the new generation to resemble; Photo Settings, which allows a user to adjust and apply photo settings that resemble those of manual camera lens controls; and Prompt Guidance, which helps users get the results they desire while writing their prompts.
Next, is the new Firefly Design AI model, which powers a new text-to-template capability.
This tool allows users to use text to generate fully editable templates that meet their exact design needs.
For example, users can input text saying they need a flyer for a real-estate open house, in which the model will generates different design template options that fit the theme.
The model can generate all kinds of outputs, including designs for print, social, and online advertising, such as social posts, posters, flyers, digital cards, and more.