At its Adobe MAX creator conference, Adobe has introduced new AI tools, models and agents in Adobe Firefly.
Firefly’s new, studio-quality audio and video tools include Generate Soundtrack for creating fully licensed audio tracks, Generate Speech for clear voiceovers and a new timeline-based AI video editor.
New models in Adobe Firefly include the new Image Model 5, which generates photorealistic images in native 4MP resolution an handles prompt-based editing in everyday language, and an expanding ecosystem of partner models that now includes ElevenLabs, Google, Luma AI, OpenAI, Runway, Topaz Labs and more.
Adobe also announced new Firefly Custom Models, which empower creators to generate a series of assets in their own style.
Adobe previewed Project Moonlight in Firefly, a conversational interface powered by agentic AI that can work across Adobe’s apps and draw insights from creators’ social channels to help them brainstorm new ideas and create new content faster. With Project Moonlight, creators can deploy an agent to help them go from concept to creation in minutes, simply by describing – in their own words – what they want to accomplish, or how they want something to look and feel. Creators can ask their AI assistant for personalised advice, suggestions and assistance and stay in ultimate control.
“Adobe Firefly supports your entire end-to-end creative process, from when you first explore ideas to when you bring them to the world with AI-powered video, audio, imaging and design,” said Ely Greenfield, chief technology officer and senior vice president, Adobe. “We built Firefly to be a single place where you can work with the best AI models in the best creative tools, and it’s been amazing to see how creators are using it to bring their ideas from concept to reality.”
Adobe introduced new Firefly tools that streamline the creative process — from brainstorming and visualizing ideas, to image, audio and video generation and editing, to producing fully finished assets at scale.
In Firefly Boards, Adobe’s collaborative, AI-powered ideation surface, creators can now move even faster from inspiration to concept with new features that offer greater control and creative flexibility. New Rotate Object capabilities enable creators to convert 2D images into 3D where they can position objects and people in different poses and rotate them to show different perspectives. New PDF exporting and bulk image downloading streamline the process of organizing and collaborating on visual concepts across projects.
New updates to Firefly Boards add to a suite of new tools Adobe recently introduced, including Presets for generating images in diverse styles with a single click and Generative Text Edit for instantly changing the text in a photo or other visual asset.
Firefly’s new AI creation tools enable creators to generate, edit, and enhance professional-quality content across images, video, and audio — from soundtrack and voiceover generation to timeline-based video editing and more conversational image prompting — all directly within Firefly, including:
Generate Soundtrack (public beta): An AI music generator powered by Adobe’s commercially safe Firefly Audio Model that creates fully licensed, studio-quality instrumental tracks. Generate Soundtrack delivers multiple original track variations in seconds that are synced and timed precisely with creators’ video footage.
Generate Speech (public beta): A text-to-speech tool for creating crystal clear voice-overs, gives creators a choice of voices from Firefly Speech Model and ElevenLabs. Customers can generate lifelike voices in multiple languages and fine‐tune emotion, pacing, and emphasis for natural, expressive delivery.
Firefly video editor (private beta): A fast, intuitive web-based multitrack timeline editor for generating, organizing, trimming, and sequencing clips, with tools to add voiceovers, soundtracks, and titles. Now creators can add all their Firefly creations in the Generation History panel, or generate new clips directly in the editor, with the ability to create start or end frames right from the timeline. Creators can upload their own media to combine captured and generative content in one place and edit with frame-by-frame precision or through a built-in transcript for quick, text- based edits. Includes style presets like claymation, anime and 2D, plus a library of customizable title templates
Prompt to Edit: A conversational editing interface that empowers creators to describe the edits they want to make to an image in everyday language, akin to how they prompt text-to-image tools to create new images. Prompt to Edit is available with Firefly Image Model 5 and partner models from Black Forest Labs, Google and OpenAI.
Adobe delivers new models from across the industry into Firefly as they’re released. Today, Adobe Firefly added new partner models including ElevenLabs Multilingual v2 which excels at generating voiceovers and Topaz Bloom for image upscaling. These join other models from across the industry including Black Forest Labs Flux 1.1, Google’s Veo 3.1, Imagen 4 and Gemini 2.5 Flash Image (Nano Bana), Ideogram 3.0, Luma AI’s Ray3, Moonvalley’s Marey, OpenAI’s GPT Image, Pika, Runway’s Gen-4 and Aleph and more.
Adobe is also bringing Firefly Custom Models (private beta) to creators, directly in the Firefly app, with early access to the beta through the waitlist. First introduced to Firefly enterprise customers, Firefly Custom Models empower creators to easily personalize their own AI models to generate entire series of assets with visual consistency in their own, unique style. Personalizing Firefly Custom Models is as simple as dragging and dropping in images that creators have the rights to use. Custom Models are private by default and require authorization by the person who created them for use by others. Custom Models will be available to use in the
Firefly’s Prompt to Edit capability is generally available to Firefly customers today with Firefly Image Model 5 and partner models from Black Forest Labs, Google and OpenAI. Firefly Image Model 5, Generate Soundtrack and Generate Speech are available in public beta today.
Firefly video editor and Firefly Custom Models are in private beta and will begin rolling out next month; customers can sign up today to join the waitlists for early access. Firefly Creative Production is also in private beta and will begin rolling out to customers who have access to premium generative AI features next month.
Project Moonlight is in private beta and will be available in the coming months; customers can join the waitlist to receive access.
Through December 1, Creative Cloud Pro and Firefly plan subscribers can enjoy unlimited image generations with all Firefly and partner models, plus unlimited video generations with the Firefly Video Model. More on Firefly pricing and plans here.
Staff Reporter
Share this story
