Adobe introduces Firefly AI tool for generating images via text

Adobe has announced Firefly, an AI tool that can generate images and text effects based on text descriptions. According to Adobe, it is a “new family of creative generative AI models” that will continue to be expanded over time.

David Wadhwani from Adobe explains that the first Firefly model, which is now in beta, could be particularly valuable for those looking to create content for commercial use. He points to the fact that the machine learning models are trained on hundreds of millions of licensed images in Adobe Stock, combined with openly licensed and copyright-expired content. According to Adobe users can therefore be assured that no content is generated based on the rights of others.

Adobe says it has added a style engine to the model, allowing users to experiment with creating photo art, graphics and text effects with a variety of styles, colors, lighting and compositional variations. The company plans to also create models where creators can train on their own style.

Adobe says everything is designed to integrate with other applications such as Adobe Creative Cloud, Adobe Expresss and Document Cloud. The company plans to make Firefly available via an API as well, so it can appear on other platforms as well. It is unknown when that API will be ready.