Adobe Photoshop gets new AI image generation AI features
One of the key features of the beta Image to Video tool is the ability for creators to specify specific parameters to get more fine-tuned results. Using the sidebar menu, users can tell the AI what camera angle and motion to use in the conversion. However, Adobe is taking a different stance on AI than platforms like DALL-E. While Adobe Firefly now has the ability to generate both photos and videos from nothing but text, a majority of today’s announcements focus on using AI to edit something originally shot on camera.
The creative industry has been rocked by the advance of generative AI, which has become increasingly commonplace in creative software — and increasingly controversial among professional creators, Adobe’s primary users. While some artists are taking legal action against AI companies, particularly around copyrightinfringement concerns, others are trying to discern what uses, if any, there are for AI in creative spaces. Adobe certainly seems to think there are some, as AI powers many of its product updates and was one of the main focuses of this year’s event. Photoshop users won’t have to wait long to try out the new features for themselves. Much like Adobe recently implemented new-and-improved noise reduction in Photoshop, Adobe Camera Raw, and Lightroom, the company is also putting an AI spin on sharpness with Enhance Detail.
You must also have a selection drawn with the lasso or selection tool around a body of pixels in your image. Generative Fill is part of the new Adobe Photoshop hotness coming as a result of Adobe’s Firefly and Sensei artificial intelligence (AI) efforts. The company has released Photoshop with generative AI (gen AI) features, available to anyone with a Creative Cloud subscription. ZDNET’s recommendations are based on many hours of testing, research, and comparison shopping. We gather data from the best available sources, including vendor and retailer listings as well as other relevant and independent reviews sites.
The company has also responded to ethical concerns, such as removing AI imitations following a complaint from the Ansel Adams estate. Adobe made the announcement at the opening keynote of this year’s MAX conference and plans to add this new Firefly generative AI model to Premiere Pro workflows (more on those later). Kicking off their annual Adobe MAX conference in Miami, Florida this year, Adobe has announced that their Firefly video model is finally ready to release to the public and is available to try out today. Adobe further mentions that Firefly was trained on licensed content, such as Adobe Stock, and public domain content.
It is available today through a limited public beta to garner initial feedback from a small group of creative professionals, which will be used to continue to refine and improve the model, according to Adobe. Adobe has also released more info about its own promises for “responsible innovation” for Firefly and this new generative AI video model. Adobe promises that its Firefly generative AI models are trained only on licensed content, such as Adobe Stock and public domain content. For Illustrator, Adobe is bringing a beta version of Project Neo into the program. Project Neo is a web app that was first teased at last year’s Max, and it’s meant to help designers and illustrators work and edit 3D designs.
These new features run the gamut from design to production, and all are designed to help reduce the amount of time creatives spend on the tedious details of their creations so they can spend more time on the creative part. There is a lot to like with these updates from Adobe and their overall approach to generative AI. The company continues to focus on integrating AI capabilities into its existing products while maintaining the creative integrity of professional workflows and balancing automation with user control. The Adjustment Brush Tool now allows users to apply adjustments like brightness, exposure and saturation directly to specific parts of an image.
The Firefly Video Model, now in limited public beta, is the first publicly available video model designed to be “commercially safe,” Adobe said. Illustrator is introducing new tools including all-new Generative Shape Fill (beta) to empower designers to quickly add detailed vectors to shapes by entering text prompts directly in the Contextual Taskbar. Generative Shape Fill is powered by the latest Firefly Vector Model (also beta) which Adobe reckons adds additional speed, power and precision into the mix. Additional innovations in Illustrator including the Dimension Tool, Mockup (beta), Contextual Taskbar, Retype, enhanced selection tools, Text to Pattern (beta), Style Reference, and more.
Generate Background automatically replaces the background of images with AI content Photoshop 25.9 also adds a second new generative AI tool, Generate Background. Generative Workspace is using Adobe Firefly 3 during the beta, but by the time it is released for public use, Adobe may already be working on Firefly 4 or higher. Photoshop was already no slouch in the artificial intelligence department, filled with tools that streamline editing workflows – so, we were intrigued to see the latest servings for Adobe users. Even if you get the technical details right in your photos, you may sometimes need to fix blemishes and other marks.
Nearly a year after adding generative AI-powered editing capabilities to Photoshop, Adobe is souping up its flagship product with even more AI. On Tuesday, the company announced that Photoshop is getting the ability to generate images with simple text prompts directly within the app. There are also new features to let the AI draw inspiration from reference images to create new ones and generate backgrounds more easily.
New generative AI features still in beta Regular readers may have spotted that this isn’t the first time that Adobe has referred to a new version of Photoshop as Photoshop 25.9. To use the Adjustment Brush, select it within the Brush Tool in the Tools Panel. From there, choose your adjustments and paint where you’d like them to be applied.
You can get the Beta version or update your existing Beta app in the Adobe Cloud app. The new caption generator lets you take the hard work out of writing social captions. Provide a short prompt, choose a writing style or tone of voice, and you can even apply it to specific words or sections of the caption rather than the entire thing (if you only need a small change). Then you can use the content scheduler to set your post to publish automatically. It works incredibly well, even tracking objects that move against similarly toned or colored backgrounds.
While the list of new features is a long one that includes new color editing tools, a fresh look for Premiere Pro, plus quick actions tool for Lightroom on mobile, the most significant features arriving to the software are those powered by AI. The push to build in more generative AI tools is hardly a surprising one, with several of company’s recent announcements centered on the same theme. Adobe introduced the feature in 2023, and it makes it much easier to get rid of grain if that isn’t your preferred photographic style. All you have to do is select Denoise, choose how much you want to add, and let the app create a DNG.
Alongside the Adjustment Brush, the new Photoshop beta also includes an improved font browser that will allow direct access to fonts stored in the cloud without requiring the user to leave the program. To Generate Similar AI art, first follow the steps in this article’s second subheading to generate an AI image from scratch. Then, select your image and click on Generate Similar from either the Contextual Task Bar or under the three dots icon in the Variations Panel. “We’ve invested in making this model reach the level of quality and prompt understanding that videographers expect. We’ve invested in making sure we really pay attention to the prompt … respecting guidance from videographers much better than other (AI video) models,” Costin told Reuters in an interview. It is also now possible to flip or rotate images from the contextual task bar, and to change the color and width of strokes and fills on shapes.
That’s the better option for removing something from a photo, where generative fill is the best choice for creating something entirely new in an image. However, the more I’ve experimented with Photoshop generative fill, the more I’ve realized there’s a trick to getting the best results from the generative AI. Photoshop also has new and intuitive features to accelerate core creative workflows and streamline repetitive tasks by using the Selection Brush Tool, Adjustment Brush Tool and enhancements to the Type Tool and Contextual Taskbar. Adobe says these tools can unlock new levels of productivity and precision, as well providing better control when selecting, compositing, adjusting images or simply working with type. Another AI tool that builds on existing original content rather than creating something entirely from scratch is Adobe Firefly’s ability to turn a still image into a video.
An existing AI-powered feature called Generative Fill that previously let you add, extend or remove specific parts of an image has been upgraded too. It now allows users to add AI-generated images to an existing image that blend in seamlessly with the original. In a demo shown to Engadget, an Adobe executive was able to circle a picture of an empty salad dish, for instance, and ask Photoshop to fill it with a picture of AI-generated tomatoes. She was also able to generate variations of the tomatoes and choose one of them to be part of the final image. In another example, the executive replaced an acoustic guitar held by an AI-generated bear with multiple versions of electric guitars just by using text prompts, and without resorting to Photoshop’s complex tools or brushes.
The company also implements Content Credentials, a metadata system that provides transparency about AI usage in created images. “A big, blank canvas can sometimes be the biggest barrier,” Erin Boyce, Photoshop’s senior marketing director, told Engadget in an interview. We’re very likely to see even more advancements in generative AI technologies for all types of content creation, including video, announced here soon as—if anything—the pace looks to be picking up as of late rather than slowing down. This integration of Generate Image will shorten the distance between the blank page and AI-generated results so users at pretty much every skill level have the tools they need to jumpstart their projects. Adobe has some language included that appears to be a holdover from the initial launch of Firefly.
The Text to Pattern beta feature and Style Reference have also been improved, enabling scalable vector patterns and outputs that mirror existing styles. To accelerate creative workflows, Illustrator is introducing new tools including all-newGenerative Shape Fill (beta) to empower designers to quickly add detailed vectors to shapes by entering text prompts directly in the Contextual Taskbar. Generative Shape Fill is powered by the latest Firefly Vector Model (beta) which is designed to support creators with additional speed, power and precision.
Coming to you from Unmesh Dinda with PiXimperfect, this informative video breaks down the latest addition to Photoshop’s suite of editing tools. Dinda walks you through how the new “Remove Tool” and its AI capabilities have simplified the process of cleaning up images. The video shows how, with just a few clicks, you can get rid of distractions like wires, people, and even reflections.
Depending upon the resources and capabilities of your computer… this might become burdensome as everything becomes more and more complex. You can always flatten your layers to a single pixel layer if this occurs to free up additional resources. Generative Fill, when used in this manner to expand an image, works best by selecting portions to expand bit by bit rather than all the expanded areas at once. It is also beneficial to select parts of the original image you want to expand from.
5 Reasons Why Photoshop’s Generative Workspace Will Be Adobe’s Best Feature.
Posted: Mon, 11 Nov 2024 08:00:00 GMT [source]
The tools help across all design workflows from creating variations of advertising and marketing graphics to digital drawings and illustrations, adding patterns to fashion silhouettes, inspiration and mood boarding. Designers can test product packaging spanning multiple pattern and design options, explore ads in different seasonal variations and produce their designs across product mockups in countless combinations. Photoshop is introducing intuitive features to accelerate core creative workflows and streamline repetitive tasks with the Selection Brush Tool, Adjustment Brush Tool and enhancements to the Type Tool and Contextual Taskbar. These tools unlock new levels of productivity, precision and control when selecting, compositing, adjusting images and working with type. Photoshop is also introducing new ways to ideate and create with Generate Image, powered by Adobe Firefly Image 3 Model.
Dinda highlights cases where the Remove Tool struggled to maintain texture or clarity, particularly in heavily populated scenes or intricate backgrounds. But even in these situations, it provides a solid foundation for more manual touch-ups. You can further refine areas using the same tool, or switch to other tools like the Clone Stamp for added accuracy. “Our commitment to creatives is at the core of everything we do, with generative AI features designed to serve as a creative companion that streamlines your creative process,” Clark’s post reads.
Another new feature related to Firefly Image 3 is the ability to utilize reference photos. You can either upload your own (Adobe warns you that you need the right to use the image) or use suggested Adobe Stock images. It tends to stick to that reference image pretty closely, though, paying more attention to that than your text prompt. Then, when I selected a randomly suggested stock image of a painted windmill, it completely ignored the photorealistic part and created a very painterly style image. For the images above, I used the prompt “photorealistic grizzly bear lounging in a hot tub outside of a Spanish-style mansion with palm trees and a beach in the background.” I then tested out the ability to choose options that influence style.
