Adobe’s Promising Generative AI Tools Have Room to Grow for Photographers
Sneak peeks: Adobes Project Perfect Blend and Project Scenic
Adobe, on two separate occasions in 2013 and 2019, has been breached and lost 38 million and 7.5 million users’ confidential information to hackers. Our goal is to deliver the most accurate information and the most knowledgeable advice possible in order to help you make smarter buying decisions on tech gear and a wide array of products and services. Our editors thoroughly review and fact-check every article to ensure that our content meets the highest standards. If we have made an error or published misleading information, we will correct or clarify the article. If you see inaccuracies in our content, please report the mistake via this form.
It uses the same Adobe Firefly model to generate the resulting images as Adobe already uses in Photoshop to extend an image or generate infill content. I think sketch-to-image is a better use case for Firefly in Photoshop than generative fill. Project Hi-Fi (High Fidelity) takes an image from anywhere on your computer, a text prompt, and renders it.
The promise of a couple of clicks saving as much as an hour or two is appealing for obvious reasons. When Adobe debuted the Firefly-powered Generative Remove tool in Adobe Lightroom and Adobe Camera Raw in May as a beta feature, it worked well much of the time. However, Generative Remove, now officially out of its beta period, has confusingly gotten worse in some situations. CNET was on site in Miami at this year’s event covering all the latest creator and AI news — includingadvanced previews of special projects.
Can you get the perfect score on this photography quiz?
RedFishBlack refers specifically to Generative Fill in Photoshop, but the problems extend to other tools, including Generative Remove, a tool tailor-made for helping photographers clean up photos and remove distractions. A new feature called objects on path will save creators time while rearranging objects on a set path, helping keep them aligned without manually adjusting each piece. Image trace, one of the most popular Illustrator features, is also getting a major overhaul to hopefully make it easier to convert images to vectors. That’s a key distinction, as Photoshop’s existing AI-based removal tools require the editor to use a brush or selection tool to highlight the part of the image to remove.
Once you have created content, you can plan, preview, and publish it to TikTok, Instagram, Facebook, and Pinterest without leaving the app. It is now easier than ever to do common tasks like removing unwanted objects from an image in Photoshop. The generative fill tool, powered by Adobe’s Firefly generative AI model, does a great job understanding both your text prompts and the context of the original image. As the disgruntled photo editor adds, there is no simple way to roll back to an older version of the Firefly tools. Images are processed server-side, so there is not much available by way of user control.
The updated model also improves the Text to Pattern beta feature, which can be used to create scalable, customized vector patterns for things like wallpapers; and Style Reference, which generates outputs that mirror existing styles. Photoshop is widely regarded as a powerful and versatile image editing tool. Due to its extensive features and continuous updates, it is worth the investment for professionals and serious hobbyists. However, its subscription model and steep learning curve may prevent beginners or casual users who might find more user-friendly alternatives like Fotor or Photoleap better suited to their needs. 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.
Variety of Prompt Input and Batch Production
Adobe has announced Reflection Removal, a new tool that uses AI technology to remove reflections from photographs taken through a window. The new feature is in beta and is now available for Adobe Bridge and Photoshop with Lightroom support coming soon. Adobe’s Generative Fill and Expand tools can be frustrating, but with the right techniques, they can also be very useful. Experimenting with selections, context, and prompts can play a big role in getting a quality result.
I’ve found that limiting the expand or fill areas to 1024 pixels improves results. There is a range for this, and you don’t need to measure pixels if you roughly know what a 1024×1024 block in your image looks like. Even if you are trying to do something like add a hat to a man’s head, you might get a warning if there is a woman standing next to them. In either case, adjusting the context can help you work around these issues. Always duplicate your original image, hide it as a backup, and work in new layers for the temporary edits.
This is especially the case if you’re trying to avoid paying the Adobe corporation as a whole, whether it’s a subscription or a longer-term license. Both Photoshop and Photoshop Elements can be accessed from a desktop app, web browser, or mobile app for the same major operating systems and platforms, but the cost is different for each. “For best results when using Gen Remove is to make sure you brush the object you’re trying to remove completely including shadows and reflection. Any leftover fragments, no matter how small, will cause the AI to think it needs to attach a new object to that leftover piece.
Rounding out the Photoshop updates are improvements to some other Photoshop features and functions. With the full-blown release of generative text-to-image AI in Photoshop, Adobe has also redoubled its efforts to be clear about its views concerning AI. While Firefly text-to-image has been in Photoshop since last year in one form or another, there is something substantially different about it being out of beta — ready to do real, commercial work (and presumably cost generative credits). In addition to Text to Pattern, Generative Shape Fill is coming to Photoshop and Illustrator, as well. This is another generative AI feature that lets you create a shape and then type a text prompt to fill it with whatever your imagination can come up with.
Selection Brush Tool
Adobe has announced new AI-powered tools being added to their software, aimed at enhancing creative workflows. The latest Firefly Vector AI model, available in public beta, introduces features like Generative Shape Fill, allowing users to add detailed vectors to shapes through text prompts. The Text to Pattern beta feature and Style Reference have also been improved, enabling scalable vector patterns and outputs that mirror existing styles. Generative Shape Fill is powered by the latestFirefly Vector Model (beta) which is designed to support creators with additional speed, power and precision. Adobe’s Firefly cloud service, which provides access to AI-based design tools, is also receiving new video editing capabilities. One of the additions is a feature that generates five-second clips based on text prompts.
Whether I want to erase something and fill in the background texture or replace an element with something different (e.g. using the text-to-image prompt) Generative Fill makes it so easy. The Object Selection tool highlights in red the proposed area that will become the selection before you confirm it. Don’t get me started on services, doctors, and anyone else who bar access unless you giving up your personal information. Big companies just don’t seem to respect keeping folks’ identities safe.
The model learned how to remove window reflections from a photo by doing this repeatedly. However, the company notes that its model isn’t perfect and that if the reflection is so strong that a human still struggles to see through it, the model will too. The gallery below shows the original image followed by a version with an added «seagull flying in the distance.»
If you’re someone who uses a lot of AI imagery in your work, this tool is set to be your new favorite Adobe feature. If you’re someone who uses generative AI in Adobe programs often, then the ability to customize your generated images can be valuable. There are many customizable options within Adobe’s Generative Workspace, and it works so quickly that it’s easy to change small variations of the prompt, filters, textures, styles, and much more to fit your ideal vision.
Illustrator’s Retype Tool
So when someone tells me that ChatGPT and its ilk are tools to ‘support writers’, I think that person is at best misguided, at worst being shamelessly disingenuous. Adobe Illustrator’s Recolor tool was one of the first AI tools introduced to the software through Adobe Firefly. This tool takes the guessing out of creating new color schemes or colorways for your vectors. At the time of writing, the Retype tool only works for Adobe fonts rather than all fonts, but it’s a game changer when you’ve used an Adobe font and created outlines in an older project and can’t remember which font you’ve used. While there are plenty of places online where you can identify fonts, Illustrator’s Retype tool scans the font directly in the software for you to select and add to your live project.
Adobe’s FAQ page says that the generative credits available to a user can be seen after logging into their account on the web, but PetaPixel found this isn’t the case, at least not for any of its team members. One thing that hasn’t improved since the previous generation of Firefly AI is the resolution of the images created. If the image in which a background is being replaced is larger than 1,500 x 1,500, the generated image will effectively be stretched.
Illustrator’s update includes a Dimension tool for automatic sizing information, a Mockup feature for 3D product previews, and Retype for converting static text in images into editable text. Photoshop enhancements feature the Generate Image tool, now generally available on desktop and web apps, and the Enhance Detail feature for sharper, more detailed large images. The Selection Brush tool is also now generally available, making object selection easier. Luminar Neo and Photoshop offer powerful AI features that speed up editing tasks, including object selection and background removal.
There are multiple selection tools settings, and you can see changes to your selection in a live preview. Generative Expand can sometimes provide enough additional context for generative fill in another area to work better. Cropping problematic or unwanted elements out of the image can remove potential guideline violation triggers.
The other features are «generally available» in the Illustrator and Photoshop apps today. Adobe’s new «Project Hi-Fi» is an interesting project that lets designers take an idea from a simple sketch and turn it into a fully rendered digital image using artificial intelligence. Currently a prototype, it could one day become a core Photoshop feature — and I’ve been given an advance look at it. Further down the line, both Photoshop and Illustrator will integrate with another generative AI tool called Project Concept. Adobe says that the upcoming tool will enable designers to automatically apply the style of one image to another. In the new Photoshop beta, Adobe is adding an Adjustment Brush that enables users to apply non-destructive adjustments to specific areas of an image, similar to tools already available in Lightroom and Adobe Camera Raw.
Our choice for realistic and intuitive digital drawing with thick oils and delicate watercolours. It’s available for desktop and mobile platforms, with mobile apps sold separately. This is a great tool for emulating traditional painting techniques such as watercolours. It offers the ability to control drips, water usage, and tilt direction.
However, other options are more affordable, user-friendly, and provide excellent features. Despite its complexity, many tutorials and online resources make it accessible, allowing even those with basic skills to learn and experiment. I can’t tell you how much I’ve learned for free from Photoshop tutorials on YouTube!
Best Free AI Generative Fill Online Alternative in 2025 – Perfect Corp.
Best Free AI Generative Fill Online Alternative in 2025.
Posted: Wed, 08 Jan 2025 08:00:00 GMT [source]
Everything from the initial conception of an idea through to final production is getting a helping hand from AI. Adobe is using AI to make the creative process of designing graphics much easier and quicker, … [+] leaving users of programs like Illustrator and Photoshop free to spend more time with the creative process. Adobe has some language included that appears to be a holdover from the initial launch of Firefly.
Adobe insists that its AI has only been trained on “commercially safe” images, such as photos stored in its own stock library. That can create problems when it comes to generating specific types of images. Even if image resolution requires further improvement, the sheer quality of the images generated by Firefly AI has improved almost beyond recognition since it was first unveiled a little over a year ago. I think we’re about to see a revolution in how we pick out furniture, design our living spaces and create content as Adobe brings these new sketch and AI features to more mainstream products. If Project Hi-Fi finds its way into Adobe Express expect to see pink wallpaper and furniture everywhere in your Facebook feed or For You Page.
If you cancel or choose not to renew your plan, you’ll lose access to the software. However, at the moment, these latest generative AI tools, many of which were speeding up their workflows in recent months, are now slowing them down thanks to strange, mismatched, and sometimes baffling results. Generative Remove and Fill can be valuable when they work well because they significantly reduce the time a photographer must spend on laborious tasks. Replacing pixels by hand is hard to get right, and even when it works well, it takes an eternity.
Photoshop’s Select Subject and Object Selection tools aren’t obvious AI features, but they use Adobe Sensei AI technology and is one of the most helpful AI tools you can find—and that you’ll actually use often. The features are available in the latest versions of both desktop apps starting today. The two brushes in particular — Selection Brush in Illustrator and Adjustment Brush in Photoshop — both feel that they could easily find applications within a video workflow. And while there will be challenges in porting the Enclosed Rectangular Marquee Selection, once you get through the difficulties of tracking multiple objects from frame to frame that could have some interesting uses too.
- This approach stands out though thanks to the ability to use photographs, layers and more than just a quick drawing on a canvas.
- On the other hand, everything is processed locally, it’s largely not censored, and you don’t have to deal with Adobe’s frequent false positive guideline violation warnings.
- GIMP is a complicated but perfectly capable photo editor that is completely free and open-source.
- 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.
«We train the model by gathering thousands of photographs of varying subjects that contain no reflections.» Adobe said in a press release. «We then add pairs of them together to form millions of simulated photographs that appear to be polluted by reflections.» Photoshop Elements’ Quick Tools allow you to apply a multitude of edits to your image with speed and accuracy. You can select entire subject areas using its AI selection, then realistically recolor the selected object, all within a minute or less. “The generative fill was almost perfect in the previous version of Photoshop to complete this task. Since I updated to the newest version (26.0.0), I get very absurd results,” the user explains.
