Adobe adds Gemini 2.5 Flash Image to Firefly and Adobe Express, enabling text-to-image generation with downstream editing like animation, resizing, captions, and publishing.

The company states that user-generated content and uploads will not be used to train generative AI models, regardless of the model chosen.

For a limited time, paid customers get unlimited generations with Gemini 2.5 Flash Image, while free Firefly users can test up to 20 generations.

Gemini 2.5 is integrated into Adobe’s ecosystem alongside partner models from OpenAI, Black Forest Labs, Runway, Pika, Ideogram, Lume AI, Moonvalley and others, expanding model choices to keep subscribers engaged.

Gemini 2.5 Flash Image delivers better context, consistency, and performance over prior Firefly, boosting end-to-end campaign asset creation and iteration, including background swaps, variations, and concept prototyping.