Adobe, during its Adobe MAX conference on Tuesday, introduced three new generative AI models: Adobe Firefly Image 2 Model, Adobe Firefly Vector Model, and Adobe Firefly Design Model.

Ely Greenfield, Chief Technology Officer, Digital Media at Adobe, spoke about these new additions, stating, "Our rapid, continuous pace of Firefly innovation continues with imaging, design, and vector generation advancements — three new models that set new industry standards for output quality and user control. Firefly continues to offer the world's best combination of visual capabilities, designed to be commercially safe, enabling transformative new creative workflows across Adobe apps."

Firefly Image 2 Model

Firefly's initial model garnered immense popularity, with over three billion generated images since its beta launch in March, as per Adobe. Firefly Image 2 takes this to the next level, offering new Text to Image capabilities. This includes the Generative Match feature, enabling users to apply the style of a reference image to generate content in a specified style. Moreover, Photo Settings provide advanced image adjustments resembling photography techniques, and Prompt Guidance streamlines the prompt generation process.

The model's improvements are seen in its rendering of skin, hair, eyes, hands, and body structure, as well as enhanced colors and dynamic range. Firefly Image 2 is designed to expedite creative visions, providing greater user control over the output.

Firefly Vector Model

According to Adobe, the Firefly Vector Model is the world's first generative AI model focused on vector graphics. It is said to introduce the innovative Generative Match feature, ensuring that vectors align with the existing style. This feature, along with the ability to create editable vector gradients, simplifies vectorisation. The model produces organised and user-friendly output.

Firefly Design Model

The Firefly Design Model is said to enhance the generation of template designs with the Text to Template feature in Adobe Express. This model help users to create fully editable templates for print, social, and web advertising.

Firefly Design Model allows users to easily generate text and images and customise text size, colour, and position. It also facilitates instant end-to-end design, harmonizing images, text, and tones in line with user prompts.

Adobe also said that global brands like Mattel, NASCAR, and NVIDIA are already harnessing the power of Adobe's Firefly models.

Adobe's collaboration with NVIDIA is also opening new opportunities for artists and businesses looking to accelerate generative AI for commercial use.

Also Read: Here is why Meta paying up to $5 million to celebrities for just 6 hours of work