“Firefly Image 3 is a considerable level up from the already high-performing Firefly Image 2 model,” said Matt Arcaro, IDC research director for computer vision and AI, with notable improvements to image quality and coherence with user prompts.
Firefly Image 3 also gives users greater control over images produce by the AI model, said Liz Miller, vice president and principal analyst at Constellation Research. “If Firefly Image 1 and 2 focused on the ability to generate, Firefly Image 3 is about focusing and controlling generative AI models to extract the idea in a creator’s mind onto the initial canvas,” she said.
Adobe is one of numerous tech firms that offer genAI image models, including Canva, Midjourney, OpenAI, Stability AI, and others. IDC predicts that global spending on genAI tools (including software and infrastructure) will reach $143 billion in 2027, up from $16 billion in 2023.
“Firefly Image 3 may be in beta, but feels less experimental compared to some of Adobe’s rivals,” said Miller. The latest Firefly model is more photo realistic and addresses some of the problems creators have experienced with generative AI tools around structure, she said – producing images of arms with two hands, for instance.
Firefly Image 3 is available now in beta via the Firefly web app.
New Firefly features in Photoshop
Another strong point for Adobe’s generative AI capabilities is integration across its products, said Arcaro. “Adobe is all-in on bringing genAI capabilities to users across its product portfolio,” he said.
