Photoshop adds new AI tools for image generation and editing

Adobe has integrated several generative AI features into Photoshop, powered by its Firefly model, to streamline image creation and editing tasks. These tools, accessible on desktop, web, and mobile, aim to assist beginners and save time on projects. Users must agree to Adobe's AI terms of service before accessing them.

Adobe's Photoshop now incorporates a range of AI-powered tools designed to enhance creativity and efficiency in image editing. The centerpiece is Firefly, Adobe's AI image model, which supports generating new images directly within the software. To create AI images, users open a project, navigate to Edit > Generate image or use the toolbar icon, enter a detailed text prompt—prioritizing key elements—and optionally upload reference images. Variations appear for selection, with options to refine prompts or provide feedback.

Beyond generation, generative editing features allow modifications to existing projects. Generative fill enables users to select a region with the selection brush, input a prompt, and generate content for that area via Edit > Generative fill. For expanding images, the generative expand tool uses the crop tool to extend the canvas; users can add a prompt to fill the new space seamlessly. Generative remove acts as an advanced eraser: select an object and use generative fill with the prompt 'remove,' or highlight with the dedicated remove tool under Spot healing.

Additional tools include sky replacement, accessed via Edit > Sky replacement, offering presets like sunsets or blue skies with adjustable brightness. Generate background simplifies product shots by removing and creating new backdrops from the contextual taskbar. Other options, such as neural filters for detailed edits and the curvature pen for consistent arcs, cater to specific needs. Adobe plans further AI enhancements, including audio tools and an assistant for layer renaming.

Testing shows these features perform well for tasks like resizing photos or erasing distractions, though results vary by image type. They suit beginners parsing complex edits but may not replace expert workflows entirely.

Relaterte artikler

Illustration of Google's Nano Banana Pro AI image model launch, featuring a smartphone with AI-generated banana images in the Gemini app, surrounded by users and global elements.
Bilde generert av AI

Google launches Nano Banana Pro AI image model

Rapportert av AI Bilde generert av AI

Google has introduced Nano Banana Pro, an upgraded AI image-generation model powered by Gemini 3 Pro, offering improved accuracy and editing capabilities. The tool is now available globally in the Gemini app, though with usage limits for free users. It also includes enhanced features for detecting AI-generated content.

Adobe has introduced four new generative AI tools to its Acrobat suite, building on last year's PDF Spaces feature. These updates allow users to create presentations and podcasts from documents, streamline editing, and improve collaboration. The enhancements aim to save time, particularly for students and professionals handling large volumes of material.

Rapportert av AI

Microsoft has rolled out a new AI feature in Paint that lets users create coloring book pages from text prompts. The tool is currently available only to Windows Insiders on Copilot+ PCs. This update aims to demonstrate practical applications of AI in everyday software.

Google has launched an experimental 'Personal Intelligence' feature for its AI Mode in Search, allowing users to connect Gmail and Google Photos for more tailored responses. The opt-in tool, powered by Gemini 3, aims to make search results more relevant by drawing on personal data without training models on full inboxes. It rolls out first to paid subscribers in the US.

Rapportert av AI

Google has begun rolling out an experimental feature called Me Meme in its Photos app, allowing users to create personalized memes using their photos. Powered by Google Gemini, the tool recreates meme templates with user images but is initially limited to Android users in the US. It will expand to iOS devices in the coming weeks.

Google has launched Personal Intelligence, a new feature for its Gemini AI that integrates data from Gmail, Photos, Search, and YouTube to deliver more tailored responses. Available initially to paid subscribers in the US, the opt-in tool emphasizes user privacy controls and avoids direct training on personal data. The rollout begins in beta, with plans for broader access in the future.

Rapportert av AI

Apple has announced Apple Creator Studio, a new subscription service bundling its professional creative and productivity apps for $13 per month or $129 per year. The package includes tools like Final Cut Pro and Logic Pro, with premium features for Keynote, Pages, and Numbers, launching on January 28. Mac users can still purchase apps individually, while iPad versions require the subscription.

 

 

 

Dette nettstedet bruker informasjonskapsler

Vi bruker informasjonskapsler for analyse for å forbedre nettstedet vårt. Les vår personvernerklæring for mer informasjon.
Avvis