Adobe Introduces AI Assistant in Photoshop, New AI Audio and Video Tools in Firefly

Adobe announced several new artificial intelligence (AI) features and tools at the Adobe Max 2025 event on Tuesday. Among them, the biggest highlight is the new AI assistants being added to Photoshop, Express, and Firefly platforms. The company is also adding new AI-powered audio and video generation tools in Firefly. Apart from this, the San Jose, California-based software giant is also bringing a new Firefly model as well as integrating new partner models to give users more choice in their daily workflows.

Adobe Introduces New AI Tools and Features Across Platforms

Over the last couple of years, Adobe has invested heavily in integrating new AI tools and features into its platform. The company has also created a new Firefly platform that offers a range of AI capabilities, both from its native models as well as third-party models. Now, at the Adobe Max 2025 event, it introduced several new features across existing and newer modalities to bring new functionalities to its platforms.

Starting with the core technology, Adobe introduced the new Firefly Image Model 5. The company says it combines native 4-Megapixel resolution, photorealistic quality, and prompt-based editing capabilities into a unified large language model (LLM). The main focus of the next generation of Firefly Image is multi-layered editing.

Essentially, once an image has been generated, users will have the option to either touch and edit the elements for granular control or write a prompt and let AI handle the task. The AI model treats every asset in an image as a separate layer and can edit them separately.

Apart from first-party models, Adobe is also integrating new third-party AI models into its existing catalogue. The biggest addition is ElevenLabs' audio generation models and Topaz's image generation models.

Adobe said another new area the company is focusing on is custom Firefly models. So far, this was only available to its enterprise clients, but now it will be available to individual users as well. Essentially, this allows users to bring their images and train the Firefly models on the user's style to ensure visual consistency. It is currently in beta, and early access can be gained by signing up for its waitlist.

Coming to the new tools, the software giant said that it has focused on the audio space to bring new functionalities to users. There is now a new Generate Soundtrack tool that can generate studio-quality, fully-licensed music tracks, a Generate Speech tool for voice-over generation, and a Firefly video editor tool that can generate, organise, trim, and sequence clips. The first two are available in beta, while the video editor has a waitlist that interested users can sign up for.

There is also the Prompt-to-Edit tool that was mentioned above, which supports Firefly Image Model 5, Google's Nano Banana, and Black Forest Labs' Flux.1 Kontext model.

How the Generate Soundtrack works is interesting. Users will first upload the video for which they want to generate soundtrack. The underlying AI model processes the video to recommend the vibe, tempo, and genre of music that would work with it. All of these are shared in a text box, where users will have the option to manually change any of the elements. Once the user is satisfied with the choice, the AI tool will generate and sync the soundtrack.

Next, Adobe is introducing agentic AI assistants across all Adobe apps, including Photoshop, Express, and Firefly platforms. The functionality allows users to ask the chatbot to make specific edits or changes to a creative asset, and the assistant can directly make them on the user's behalf. The company says that users will have full control over the AI's actions at all time and they can switch back whenever they want. The Express AI assistant is currently available in beta, whereas a waitlist is available for the AI assistant for Photoshop.

Finally, the company also previewed Project Moonlight, a new initiative that allows all the AI assistants across Adobe apps to seamlessly work together, eliminating the need for the user to manually switch between the platforms. A private beta of the capability was showcased during the event.