For those who don’t know the tool: Adobe Firefly is Adobe’s browser-based generative AI studio within the Adobe ecosystem, complementing Creative Cloud tools. The Firefly Video Editor adds AI-assisted video editing in the cloud, positioned for fast-turnaround content and lightweight workflows.

From blank timeline to first cut

Adobe has introduced Quick Cut in beta for the Firefly Video Editor. The company describes it as an AI-supported feature that generates a structured first-draft edit from a natural-language description. According to Adobe’s documentation, users describe their video concept in natural language. Quick Cut then creates an initial sequence that serves as a starting point for further refinement. The stated goal is to reduce the time spent reviewing footage and assembling a first edit.

Adobe positions this as a response to a common bottleneck in video production: the initial review and assembly phase that precedes narrative refinement. The feature is presented as particularly relevant for formats such as social media videos, product demos, interviews and event recaps. The beta is available from today.

Text prompts as edit instructions

Adobe specifies that users can describe the intended structure or concept of a video, such as an interview or event recap. Quick Cut uses these inputs to automatically generate a structured draft edit. The resulting edit can be refined and adjusted by the user. Adobe states that creators retain control over parameters including aspect ratio, pacing and B-roll organisation.

There is no published information on supported codecs, maximum timeline length, track limits, or interchange formats. It is also not specified whether sequences can be exported to other Creative Cloud applications such as Premiere Pro.

Positioned for fast-turnaround content

Adobe explicitly frames Quick Cut as optimised for “creator workflows,” particularly for social videos, product demos, vlogs, and event recaps. The documentation highlights use by hobby editors and time-constrained creators who want a structured starting point without engaging in a complex editing process.

This positioning indicates a focus on rapid content production rather than high-end broadcast or feature post pipelines. There is no mention of advanced editorial controls such as multi-cam handling, script-based editing, EDL export, or collaborative review workflows. Whether Quick Cut will expand beyond these use cases has not been announced.

Firefly as a creative AI hub

Quick Cut is part of Adobe Firefly, which Adobe describes as its all-in-one creative AI studio. Firefly spans image, video and other generative workflows within Adobe’s broader Creative Cloud strategy. Adobe states that Quick Cut integrates with the existing Firefly Unlimited offering. The company presents this as enabling greater iteration speed and flexibility. As with other Firefly features, Adobe emphasises commercial safety in relation to its own Firefly image and video models.

Unlimited Firefly and model access

Adobe is offering access to Quick Cut beta through the Firefly app. Users can register until 16 March to benefit from what Adobe describes as unlimited image and Firefly video generations at resolutions up to 2K.

The offer applies to customers on Firefly Pro, Firefly Premium, 4,000-credit, 7,000-credit and 50,000-credit plans. Adobe states that this includes unlimited generations using image models such as Google Nano Banana Pro, GPT Image Generation and Runway Gen-4 Image, alongside Adobe’s own Firefly image and video models. No detailed technical comparison between these third-party models is included in the announcement. Adobe does not specify which models are used by Quick Cut for edit generation versus image or video asset generation.

What is not specified

The currently available documentation does not clarify several points relevant to professional pipelines. There is no explicit statement about media ingest limits, storage quotas, or project retention policies within Firefly Video Editor. Integration with on-prem or MAM systems is not mentioned. There is no information about API access, automation hooks, or enterprise deployment models.

Colour management, LUT handling, audio track control, and support for professional camera formats are not described in the Quick Cut overview. These omissions may reflect the current scope of the beta, but they are not addressed in the official text. Professionals considering use in production environments should evaluate these factors directly within the beta before committing deadlines or client deliverables.

Beta status and production caution

Quick Cut is explicitly labelled as beta. As with any beta feature, stability, performance and feature completeness may evolve. New tools and innovations should always be tested before use in production.

// https://helpx.adobe.com/de/firefly/web/firefly-video-editor/create-quick-cut/quick-cut-overview.html

The post Adobe adds Quick Cut to Firefly Video Editor first appeared on DIGITAL PRODUCTION and was written by Bela Beier.

Adobe has introduced three new adjustment layers to Photoshop: Clarity, Dehaze and Grain. These controls were previously available only through Camera Raw and the Camera Raw Filter. They are now accessible as standard, non-destructive adjustment layers within the main Photoshop layer stack.

According to Adobe, the new layers behave like other adjustment layers. They can be masked, reordered, blended and revisited at any time without altering the underlying image data. This brings parity between Camera Raw based workflows and traditional Photoshop compositing, reducing the need to commit early to contrast or texture decisions.

Clarity adjusts midtone contrast, Dehaze targets low-frequency contrast loss caused by atmospheric scatter, and Grain applies a controllable film-style noise pattern. Adobe does not specify whether the underlying algorithms are identical to those in Camera Raw, only that the controls are now natively available in Photoshop.

Generative tools move to higher resolution

Adobe has updated several Firefly-powered features in Photoshop, including Generative Fill, Generative Expand and the Remove tool. Output resolution has been increased to up to 2K. Adobe states this results in sharper detail, fewer visible artefacts and improved alignment with text prompts.

The company also highlights improvements to Reference Image support. When a reference is supplied, the generative system is intended to better preserve object identity, including scale, orientation, lighting, colour and perspective. Adobe positions this as a way to reduce iterative prompting when compositing generated elements into existing plates.

Dynamic Text enters beta

A new Dynamic Text feature, currently labelled as beta, allows users to transform text layers into predefined shapes such as circles, arcs and curves with a single action. The text remains editable and automatically conforms to the chosen shape without requiring manual path creation.

Adobe frames this as a productivity feature for layout and graphic design tasks. The company does not indicate whether the system supports custom shapes or whether it exposes underlying typographic controls beyond the provided presets. As a beta feature, behaviour and availability may change.

Availability and platforms

These updates are available now in Photoshop on desktop. The improved generative tools are also available in Photoshop on the web. No changes to pricing or subscription structure are mentioned. Photoshop remains available exclusively via Adobe’s subscription model.

As with all new or updated tools, Adobe recommends testing features in non-critical projects before integrating them into production workflows. New tools and innovations should always be validated in real-world conditions before use on actual client work.

// Adobe blog announcement on new Photoshop features
// https://blog.adobe.com/en/publish/2026/01/27/new-photoshop-innovations-provide-creative-pros-more-control-realism-precision

The post Photoshop gets less destructive and slightly less vague first appeared on DIGITAL PRODUCTION and was written by Bela Beier.

Object Mask: Click, Click, Done

Premiere’s new AI Object Mask tool aims to end frame-by-frame rotoscoping. Hover over a subject, click once, and Premiere builds a mask that automatically tracks that object through the scene. You can use it to blur faces, relight subjects, or isolate areas for colour grading. Six coloured overlays make selections easy to read, while the lasso and rectangle tools handle manual tweaks. Tracking runs both forward and backwards, with near real-time previews and a frame-track editing mode for fine-tuning. Feather and expansion controls help blend the result into your shot without visible edges.

Mask tracking is now powered by a rewritten core that runs locally on the machine. Adobe says the new object selection models don’t require cloud processing, keeping footage on the device and preserving user privacy. Tracking performance is substantially faster in real use, especially on newer GPUs.

Shape Masks Grow Up

Traditional ellipse, rectangle, and pen masks have been rebuilt. The tracking engine is up to 20 times faster, bezier curves supposedly behave more predictably, and on-screen controls finally feel modern. Each mask supports blend modes for combining shapes, including add, subtract, and intersect. There is also a new 3D perspective tracking mode for sticking masks to surfaces that aren’t flat to the camera.

Firefly Boards: From Moodboard to Timeline

Premiere now connects directly to Firefly Boards, Adobe’s collaborative AI workspace for brainstorming and visual planning. Editors can import ideas, concept images, or generative assets directly into a Premiere project without the usual download-and-export routine. The workflow lets teams move from early ideas to polished edits without breaking creative flow.

Workflow Tweaks

Premiere 26.0 also brings a long list of smaller but meaningful improvements. The Frame.io V4 and Adobe Stock panels have been reworked so editors can search, preview, license, and import assets directly in the app. File relinking is smarter, the Effects panel is reorganised for clarity, and startup on macOS is quicker with a smaller install footprint. Windows ARM builds now deliver better responsiveness and longer battery life. Nikon R 3D NE raw video files are supported natively, including from the new Nikon ZR camera.

Beta and Reality Check

Some of the masking features remain in the Premiere beta build, so expect updates and occasional quirks. In tests, the Object Mask handles clear subjects well but can still fumble in noisy or low-contrast footage. Early adopters are advised to test thoroughly before trusting it with client deadlines.

Pricing and availability: Premiere 26.0, After Effects 26.0, and Firefly Boards integrations are now rolling out to all Creative Cloud subscribers. As always, test new tools in controlled environments before letting them loose on paid work. And yes, we’re updating our website tags.

Coming Up Next: After Effects

After Effects 26.0 got its own set of major updates, including native parametric 3D meshes, 1,300 free Substance materials, SVG import with gradient preservation, and variable-font animation. We will be pouring through that one very soon.

The post Premiere drops the “Pro” and picks up some serious AI first appeared on DIGITAL PRODUCTION and was written by Bela Beier.

The use of artificial intelligence in Adobe Photoshop is being increasingly expanded by developers. In the past, the Adobe Photoshop-AI model “Firefly” took centre stage. Two further models have been available in the beta version of the programme for a few weeks now:

• Flux.kontext Pro from Black Forrest Labs
• Nano Banana from Google

Both models have so far been able to prove their efficiency, which is impressively demonstrated by many examples on the Internet. Changing people’s clothes or manipulating the scene view are just two examples. In Photoshop, they are activated via the options in the context-sensitive taskbar. This works after selecting the entire image or an area. In contrast to Firefly, Photoshop only produces one result with the two new models.
Apart from the familiar use cases, the AI provides support when working on projects in the areas of graphic design, matte paint or concept art.

Transforming scenes in Photoshop

The use of stock photos in productions is a normal process. The same motif at a different time of year or day is usually not available. This is where Nano Banana from Google can help. It allows the scene to be quickly adapted to the production management’s specifications. This is achieved with a simple prompt. In the example, a night scene is created from an existing recording:

Turn in a night scene

The method allows the uncomplicated creation of material for virtual TV sets or documentaries.

Transforming Text in Photoshop

“Flux.kontext Pro” is known for changing text in photos without manipulating the font or changing the character of the overall impression. The artist then corrects errors in product designs with just a few mouse clicks. A time-consuming subsequent photo shoot is not necessary. Alternatively, product names with different international designations can be created for motion graphics. These can be used flexibly later in production.

Both steps described with light and fonts can be combined. In practice, it has been shown that changes to the text with the Black Forrest AI should be performed in the first step. Then the lighting of the scene is changed with Google Nano Banana. The results are usually more realistic in this order and errors are avoided.

Photoshop-AI: Quick merging of motifs and objects

Matte painters and concept artists save a lot of time by using AI. Buildings can be inserted into landscapes or objects integrated into existing scenes in no time at all using text input – a single prompt is often enough.
However, the results are not always satisfactory, as the nano-banana model often automatically generates architectural suggestions. Significantly better results are achieved if you use a reference image. This is loaded into a new layer while the selection tool is used to define the target area in the background. If the background layer is active, it is then inserted via the context bar with the prompt:

Place the castle from Layer [Layer name]

If the first attempt fails, you can modify the prompt and possibly add further instructions such as “set on the mountain top”. The AI will then position the object better.

Inline prompts are available when inserting with Nano Banana. These are text layers with the instructions for working with Nano Banana. They are supplemented by graphics such as arrows and frames in a separate layer. These elements help with the exact placement of the object. Only one instruction is then required in the prompt for generative filling:

Complete the prompt in red

In some cases, Nano Banana inserts the prompt text and the corresponding graphic into the result. Then it helps to extend the instruction with “remove the red prompts and elements”.

Context-related fill and replace with Firefly

In Photoshop Beta 27.1.0, Adobe has added the new Firefly model “Fill and Replace (Beta)”. A reference image can be loaded and placed via the context-sensitive taskbar. The function can remove the background in the motif if desired. Free-standing objects with clear edges are ideal for insertion. A clear background usually ensures good results for architectural motifs. Transitions on the ground often need to be reworked, which is easy to do with the existing mask. Any remaining errors can then be corrected with a brush.

Conclusion

Numerous image manipulations are possible with the new AI models in Photoshop Beta. However, the results are not always optimal. In these cases, it helps to work in iterations and approach the final result step by step. This method leads to success in most cases. A reminder: depending on your subscription, it can become costly quickly.

The new technology is a useful tool for quick results. However, Photoshop-Ai cannot replace creativity or the experience of the artist. Rather, it helps to build up a project and can make the work process more efficient.

The post Photoshop AI in practice first appeared on DIGITAL PRODUCTION and was written by Jörn-Erik Burkert.

Adobe has released Premiere for iPhone, a free app that brings multi-track video editing, AI-powered tools, and cross-device workflows to mobile devices. Pre-order opened on the Apple App Store on 4 September. (Well insert the link as soon as we have it ourselves) The app takes its cues from Premiere Pro, but is designed for on-the-go creators. Adobe positions it as a way to capture, edit, and publish without leaving the phone, while still allowing handover to desktop for fine-tuning.

Here is a short overview of the workflow in Premiere for iPhone

Multi-track editing on mobile

Premiere for iPhone features a multi-track timeline with coloured tracks and audio waveforms. Users can trim, layer, and adjust clips with frame-accurate precision. The app supports unlimited video, audio, and text layers, 4K HDR media, and automatic captions with stylised subtitles. Adobe says the UI is simplified compared to desktop but retains familiar concepts for existing Premiere users.

Mobile-to-desktop workflow

Projects can start on iPhone and later open in Premiere Pro on desktop. Exports to TikTok, YouTube Shorts, and Instagram are available in one tap. Automatic resizing keeps subjects framed when switching between aspect ratios.

Firefly assets included

The app integrates Adobe Firefly for generative AI. Users can access millions of stock stickers, images, fonts, and music tracks or generate unique content directly in the app. Adobe states Firefly is trained on data that respects creator ownership. How many creations and uses are possible is not clear at this moment, and we’ll update as well. Premiere for iPhone doubles as a mobile recording studio. It includes the voice-driven sound effect generation and studio-quality voiceover capture from Firefly and the “Enhance Speech” function designed to clean noisy recordings automatically from Adobe Podcast.

The app is free to download and use, without ads. Costs only apply for generative credits and cloud storage. We’ll keep you in the loop on any updates, and if you don’t have an iPhone, but want to test it: Why not visit the Adobe Booth in Hall 7 of IBC? As with all new tools, Adobe’s mobile Premiere should be tested carefully in production environments before integrating into professional workflows.

The post Premiere Pro on iPhone: Adobe goes pocket-sized first appeared on DIGITAL PRODUCTION and was written by Nils Calles.