Dream Bigger with Generative Fill - now in the Photoshop (beta) app
This under-construction, revolutionary new AI-powered Generative Fill allows you to create/generate new content in your image or remove objects like never before!
The process is simple: make a selection – any selection, then tell Photoshop exactly what you want placed there. The GenAI models will return an object or scene you described. You can:
Generate objects: Select an area in your image, then describe what you’d like to add.
Generate backgrounds: Select the background behind your subject, then generate a new scene from a text prompt.
Extend images: Expand the canvas of your image, then make a selection of the empty region. Generating without a prompt will create a seamless extension of your scene.
Remove: Select the area you want to remove, then let the GenAI technology make it disappear.
And more… Generative fill is incredibly versatile. Discover new ways to use this powerful feature.
How to use Generative Fill
Rate the results!
Releasing this amazing new technology as a public beta allows Adobe to hear from you!
Let us know if the Generative Fill feature is meeting your expectations!
As you use Generative Fill, please rate each variation image.
Simply hover over the [•••] on the thumbnail and give it a thumbs up, or thumbs down, then follow the link to tell us more.
Report Result option
Prompts may also unintentionally generate problematic or offensive images; in such cases you can use the Report Result option to let us know.
Provide Feedback and help shape Generative Fill
If you would like to provide feedback on the overall experience, report any bugs, or suggest new features please let us know in this thread! If you prefer Discord, you can find us there too!
Not seeing Generative Fill?
1. Both the previous and the most-recent version of the Photoshop Beta are 24.6.
Please check your Help > System Info and verify that on the first line you see: 24.6.0 20230520.m.2181
Ensure you are on the latest by refreshing the updater, please.
2. To use the feature, you must first have an active selection.
Make selections in your composites
Thank you @MeredithStotzner for posting this. As its not clear that just downloading Photoshop (Beta) is not enough. One has to "update" it immediately as well 😛 to be able to access Generative Fill 🙂
It says that it's Up to date, but I have the old version 25. I'm based in Canada, is that why?
Charlotte, I am from Ukraine and I have the same situation as you!
you need to find and install another version of Photoshop. Look for Photoshop beta
If you're using a VPN turn it OFF. I had this problem. My creative cloud was saying there were no updates. But when I turned the VPN off there was 5 updates in total. Including the update for Beta with generative fill.
Mine isn't even showing as installed on the updates tab in my cloud app. It does show in All Apps, however.
When using the new Generative Fill option in Photoshop Beta, it would be very handy if the layer name of the newly generated layer would be the text prompt (if a prompt is used). It can stay, "Generative Layer x" if there's no prompt associated with it.
If the concern is that the layer name might be too long, perhaps just use the main noun? For example, I just generated "a wrought iron birdbath" - having the layer name be "Birdbath" would be wonderful!
Soooo.... are all of these Ai Generative images going to be from Royalty Free sources?!
This may open/close a can of worms for our legal department!
Thank you for your assistance, Pete. Also, I have received unsatisfactory results in the form of crude and cartoonish images that bear little resemblance to the high-quality photos depicted in Adobe's demonstrations. Is there an setting that is lacking, or is it simply a result of this being a beta version?
Is it possible to add my own images, such as skies and backgrounds to the generative fill library? It would be much nicer to use my own work than someine elses.
Simple answer: No. If you upload images to Adobe Stock, your images MIGHT be used to create AI results elsewhere. But you won't be able to pick and choose which images are used to create new results.
Hello @Pete.Green I was wondering the same thing as @paultech. I read the FAQ link but the answears are not very specific. It says that Adobe Stock content is part of Firefly’s training dataset. What are the other parts though? Should we worry the dataset contains copyrighted content like midjourney does?
FAQ also mentions that Adobe is "developing a compensation model for Stock contributors, and we will share the details of this model when Firefly exits beta." but is there really any guarantee Firefly will ever exit beta? There games that have been years in beta version. What holds Adobe back from doing the same thing?
It's very disappointing that the Generative AI images can't even be uploaded to Instagram as part of a photo edit. I'm not going to waste any more time on it until the resulting images are usable in the real world.
I'm not sure if this is really a bug, but it's an issue so I'm sending feedback. I generated a picture of Labrador Reteriver puppies twice using the Generate Fill. The first time one puppy had 3 tongues. The 2nd time one puppy had 2 tails! I'm using Photoshop Beta 24.6.0 on Mac OS Ventura 13.3.1. Sending a screenshot of the puppy with 2 tails.
same here. it is very confusing
It worked! Yay! I'm so happy! Thank you so much!
Welcome to the world of AI. 🙂 Even the best text to image AI software will sometimes give you unexpected results such as mangled hands, extra feet, etc. You just have to keep trying.
I couldn't stand my 4 experiments with this, the manufactured results were worse than awful. So I uninstalled the Beta. I wish I'd taken screen shots of the mangled and garish results I got.