Adobe launches Firefly, an all-in-one application to create content with AI

Firefly, the latest development of Adobe, empowers creators to generate images, video, audio and vectors from a single place based on AI models compatible with commercial applications and open to third-party services such as Google and OpenAI.

The application Firefly includes all commercially safe creative AI models Adobe, including the new modelo Firefly Image 4, for creating realistic images; the new Firefly Image 4 Ultra, aimed at processes that require significant attention to detail, or the model Firefly Video, which generates sequences from text prompts and images. The platform also offers creative professionals the ability to explore in different aesthetic styles using partner models, with models of Google Cloud y OpenAI, as well as other models of partners as fal.ai, Ideogram, Luma, Pika and Runway available in the coming months. In the words of David Wadhwani, president of digital media at Adobe: "With Firefly, we set out to transform the creator experience by bringing together image, video, audio and vector generation in a single platform for AI-assisted creativity. The new Firefly models and the integration of partner models give our users the ultimate option when it comes to bringing their visions to life."

By unifying the generation of images, video, audio and vectors, Firefly aims to enable creative professionals to work “more productively and with an unmatched degree of precision.” Integrated with Photoshop, Premiere Pro, Express and other Adobe creative applications, offers support AI based in all phases of the content creation process: from ideation to production. With the ability to generate results with a resolution of up to 2K, creative professionals can crop and recompose images with greater precision and print in larger formats without sacrificing quality. From a video perspective, professionals will be able to create clips at 1080p from text or image prompts, fine-tune any video with detailed camera parameters using intuitive controls that provide new levels of precision, create atmospheric elements, develop custom motion design elements, and more.

Adobe Vector ModelAdditionally, it includes the new Text to Vector feature, which allows designers to create fully editable vector-based illustrations, logo variations, product packaging, icons, scenes, patters and much more with simple prompts written in everyday language.

Firefly: a third-party compatible ecosystem

To give creative professionals the flexibility to use AI in the way that suits them best, the Firefly app includes the ability to try with models created by partners with different aesthetic styles, starting with the imaging capabilities of OpenAI, Image 3 and Google Spy 2 and Flux 1.1 Pro. Adobe also plans to integrate additional models from partners such as fal.ai, Ideogram, Luma, Pika and Runway in the coming months. Kevin Weil, head of product at OpenAI, celebrates the openness of Adobe's platform: "We are delighted to work with Adobe to bring OpenAI's imaging capabilities to its creators. Now, even more people will be able to create consistent, context-sensitive images using the Adobe creative suite they already know and use, opening up more ways to share ideas visually."

Creators can easily switch between models, with full transparency about which model is being used in each step. The content credentials are automatically attached to AI-generated content, clearly indicating whether it was created with an AI model. Adobe Firefly or with a partner model.

Firefly Boards and other Firefly services

The new Firefly Boards, available in public beta on the Firefly app, equips creators with an AI-powered interface to make mood boards, storyboards, brainstorm, explore creative concepts, iterate on hundreds of variations at once, and collaborate on ideation with the ability to go straight to production. Initially introduced as Project Concept, Firefly Boards make it faster and easier for creative teams align ideas before jumping into production.

Likewise, Adobe has confirmed that it will promote Firefly Services, a collection of Creative APIs bringing Adobe AI innovations directly into content production workflows so businesses can accelerate repetitive tasks. Leading brands and agencies such as Accenture, dentsu, Gatorade/PepsiCo and The Estée Lauder Companies have been using Firefly Services to shorten campaign launch time and engage new audiences with personalized experiences by enabling generative AI to simplify content production workflows.

Additionally, the company is introducing new APIs a Firefly Services driven for its commercially safe Firefly models. Available in beta, the Photoshop API helps businesses accelerate large-scale image editing workflows, and the Text to Image API and Image to Video API transform text and photos into live-action clips. The latest Text to Image API, which is based on the Firefly Image 4 Model, and the Avatar API, which allows teams to create engaging video content to explain products and more, will be available soon.

The Firefly Image 4 Model, Firefly Image 4 Ultra Model and the new Firefly Video Model are now available through Firefly on the web. Firefly Boards, on the other hand, is available in public beta on the Firefly app.