- Adobe reveals the addition of Gemini 2.5 Flash Image to Firefly and Express
- Firefly -Models are already supported by models from Google, Openai and more
- Gemini 2.5 flash image promises better performance
Google’s Gemini 2.5 flash image is now available in Adobe Firefly for text-to-image functionality and Adobe Express.
Gemini 2.5 Flash Image allows Adobe users to generate stylized graphics in Firefly, then animate, change the size, add captions and publish via Adobe Express, making the entire end-to-end process even slicker.
Other use cases include changes in campaign assets for marketers (such as swaping backgrounds and creating variations) and prototype product concepts for designers.
Adobe Firefly and Express Get Gemini 2.5 Flash Image
Although many of these features were previously available using Adobe’s own Firefly models, the Google Gemini model improves the experience with better context and knowledge, consistency and performance.
Adobe also uses other partner models from companies such as Openai, Black Forest Labs, Runway, Pika, Ideogram, Lue AI, Moonvalley and more to give users the choice. By not limiting them to internal models and giving them more flexibility, it ultimately means that customers are more likely to remain subscribed to Adobe’s platform.
For a limited period, Adobe paid customers offer unlimited generations with Gemini 2.5 Flash Image as a welcome promotion. Even free Firefly users will be able to access up to 20 generations to test the newly added model.
Regardless of model selection, however, Adobe emphasized that user-generated content and uploads will not be used to train generative AI models.
“This has always been the case for Adobe Firefly Generative AI models, and it is a requirement in all our partnership agreements,” wrote VP for New Genai Business Ventures Hannah Elsakr in a blog post.
“With today’s addition of Google’s Gemini 2.5 flash image in Adobe Firefly and Adobe Express, people have even greater flexibility to explore their ideas with industry-leading generative AI models and create a great content with ease,” added Elsakr.
