Feature Requests

Right now the default is Background and when working with batch of photos and we need to crop-extend the image edges it requires repetetive task of changing fill type. Not only that. After chenging the fill type, arrow keystrokes don't move the crop grid/frame anymore but they navigate between the fill type.Please add option to set default Fill as:- Background- Content Aware- Generative (additionally with no pop-up text field when we don't want to add anything extra).Thanks.

Currently when you make a selection and do generative fill it does not respect your selection, what it does is it generates from within the selection and blends in outside of the selection.It would be nice to have a checkbox or a way to configure generative fill so that it respects your selection. It would generate  and blend inside your selection instead of blending outside of your selection.I understand why it blends outside of your selection currently because it makes it easier for people to make quick selections and makes it more beginner friendly, but it would be nice to have a strict option so that professionals can apply it exactly where they want it. After all photoshop is still a tool to be used by professionals correct?

Seeing that in the Photoshop Beta the Actions panel is apparently starting to get an overhaul, I'd like to reinforce a request I think everyone would love to see: Nested folders / sets of actions.   Especially when downloading lots of actions online, they can really start to get cluttered even with the current ability to put them into a single level down in folders. It would be a game changer simply to be able to organize them further.   (Side Note: The forum is requiring me to choose a topic for the post but the only option is "Generative Fill" for some reason)

Thank you for including AVIF (and JPEG XL) file save support. Upon final implementation can they be shuttled to appear in the drop down below the Photoshop and Large Document Format options (ahead of BMP)?(ignore GenFill topic, it would not offer anything else for me to select)

With Generative Fill, the generated images fill up the property's window quickly, adding to the file size. It's too tedious to remove each one manually, so I have to start over on a new layer after a few attempts. It would be useful to have a "remove all" button, which would remove all generations at once from a layer, but keep the layer and mask. (or, perhaps, it could remove all generations, but keep the last generated one.)

Extend Generative Fill (Firefly) to understand natural language to text-method alignments in addition to text-image alignments. I.e. in addition to "what" kind of imagery to generate, "how" it should be accomplished.   I'm sure that already happens to some extent in just "what", so in pics: "very smooth transition/morph/blend/mix between <left and right textures described in detail>" or whatever else you try:   = Not good.Proposal: Generative Fill would have some understanding of what I'm trying to achieve when I'm specifying methods to be applied to already-existing imagery, rather than new content/imagery. I hope this is understandable.It's a generic problem in state-of-the-art AI-image generators, but in my mind addressing it would be particularly beneficial for Adobe.

I'm sure this applies to other use-cases as well, but to me it appears most evident in dark backgrounds when using a text-prompt. Generative Fill applies a relatively strong tone-difference, where you can easily see the edges of the Generative Fill, whereas Content-Aware fill does much better job. Observe 2 x Generative Fill vs. 2 x Content-Aware Fill:   Idea: include a dataset of Content-Aware background fills in Firefly training data for better handling of near-solid backgrounds, or just utilize Content-Aware Fill with Generative Fill in low-detailed areas.

Generative fill used to respect selections a lot more than it currently does.Now it seems to have an extreme "feather" where it edits areas that are not selected. And not just a tiny bit on the edge but pretty far into it. I understand it needs to blend but cant it generate that blend on the outside rather than the inside? I mean it used to do that.I understand they want people without photoshop skills to be able to use generative fill so for those who are bad at making selections can roughly circle and area and generate something there. But can we have an option for professionals to be able to respect your selection bounds and only generate within the selection?TLDR: Have a preference setting to allow Generative Fill to respect selection bounds.

Subject: Idea for Adobe Photoshop - AI Learning and Batch Editing Dear Adobe Team, I hope this message finds you well. I am writing to propose an innovative idea that could transform Adobe Photoshop into an even more efficient and indispensable tool for creative professionals like myself. The concept revolves around integrating AI-driven learning and batch editing capabilities into Adobe Photoshop. Here are the key aspects of this idea: 1. **AI Learning:** Adobe Photoshop could incorporate an AI learning system that analyzes the edits made by users during their daily creative work. The AI would recognize patterns in the editing process, such as specific adjustments, filters, or enhancements frequently applied to images. 2. **Seamless Application:** Once the AI has learned from a user's editing style, it can seamlessly apply similar edits to a batch of similar photos. For instance, if a user edits a series of images with the same model or background but different perspectives or posture

Hi,I just started using the generative workspace, maybe few ideas that I would find really useful and that I was hoping for.If I understand correctly, what's in it is a local cache as firefly web, but might be worth providing options to organize that local cache.Tried to phrase the ideas as "user stories", so don't take the tone as a sign of entitlement or exigence 🙂 - Organization in "All Images"I want to create folders/collections structure in which generated content from the timeline view can be placed so it's easier for me to organize and easier to integrate with personal workflow.- TaggingI want to be able to tag certain content so I can filter later based on the tags I'm using.- Synthetic views in timeline viewI want a datagrid-like view so I can quickly browse visually to a specific generation based on textual informations.I want a denser grid based view with one square by generation containing an overview of the visuals and minimal textual information so I can quic

I'd like to see a feature where we can toggle the number of images PhotoShop makes at a time. Sometimes I do try to "push the edge," which was fine in the old PhotoShop - It would display the 1 or 2 attempts that did work - but now it doesn't. And it's getting really frustrating because I'm waiting upwards of 2 minutes to find out that my prompt doesn't work. But it doesn't have to be an edge thing either - I find if there's an element I'm really focussing on, I run it 2-3 times before I settle on one I want to use. So even say, getting to make 9 images at a time would be useful too. PhotoShop is really good, but these frustrating issues are driving me nuts.

Right now it uses 100% of the CPU and sometimes can freeze the entire system... simple tasks like dust/scratch removing can take a few seconds to finish because it relies on the CPU   I assume it uses something similar to the Llama cleaner, but that one run mainly on GPU so there's no reason Photoshop's Remove tool shouldn't be able to too.

Now that AI is in full swing would it be possible to use it to make selection based on a text description. For example. A landscape image with a pond: 'Select the water' or 'Select the river'? This would be incredible useful and since Photoshop is using AI to analyze the image it might not be too big of a stretch to have it accomplish this task. It would be amazingly useful: select people, select cars, select animals, select water etc.

please make the beta versions for adobe audition photoshop and more free forever  like free install    like fl studio free update 

Hi dear developers,I would like to thank you for allowing people to use the products you create and support!I have a comment about the changes in the PS interface. I noticed that in the latest beta versions you have changed the appearance of the Single Adjustments block by adding the names of adjustment layers. In my opinion, this is inconvenient, it takes up extra space in the workspace, which I would use to greater advantage, for example, enlarging the window with layers. I think most of the users of your products are already very familiar with each of the adjustment layers and there is no need to display its names in this form. It is enough to have a pop-up window that will not steal precious space, which is not very much, considering the huge number of tools that I use on a regular basis.I'm sure the adobe community would appreciate it if the new PS and PS beta versions would keep the classic, concise look of the toolbar. I really hope that my appeal will meet with a caring agent w

Reference image is very useful, but couldn't it be even more useful if we had some sliders or checkboxes to specify how much influence the reference image has on generations?   Color, for instance. Reference image greatly influences colors. What if I don't want that? What if I just want the ref image to influence shape/form/detail, and not determine coloration? How about an overall influence strength slider?

Option to control generated results that consist of just a single isolated object image, on either a solid color or even rendered on alpha transparency.   _________________   Despite being call Generative "Fill", it's not always desirable to get results with complete filled backgrounds that look like complete scenes.   Often you want just iterations of object designs or character designs and do not want a fully detailed background complicating the results. When I'm lucky I can get results with minimal or no background, but it's very tricky, basically random.   Futuristic vehicle design ideas, for instance. I tend to get complete scenes with fully colored/rendered city backgrounds, etc. My intent is to simply generate concepts for futuristic vehicles to work from, not fully illustrated or photographic scenes/panoramas. 

Favorites list for Generataive Fill effects.   _________________   Concerning Generative Fill, it's important which "Effects" you have selected, and so far I tend to keep using mostly the same few effects when fine-tuning text prompts to achieve the results I'm after.   It feels like a missing feature that there's no way to quickly select recently used effects (like how the Brushes panel keeps a list of recently used brushes settings) or to be able to "star" an effect so it's saved in a "favorites" list I can quickly access and apply. Instead, I must tediously navigate to each needed effect, even though I only ever use ~2 of the available effects (which I expect is common use case).   (Sidenote: it's rather awkward that if I click on a generation variation thumbnail, my selected effects are  arbitrarily overwritten. I understand why the ui works this way, but it's not always desired. Not sure how to best address this.)

Generative fill is a great tool for patching 360 photos, typically to remove the tripod at nadir.  But it currently can't be applied directly to an image in equirectangular format.  If I use the prompt 'equirectangular 360' it does seem to get the equirectangular perspective sort of right.  But it clearly does not understand how pixels are distorted as you approach the pole.  So the result has bogus detail in that area, and  lots of 'cat butt' distortion. If this coud be fixed, it would dramatically speed up patching 360 photos, compared to the method I use now: extract a rectilinear image with a 3rd party tool; patch that in Photoshop; use the external too to re-insert the patch  and re-render the equirectangular image.

In FF2, we could save the links after we generated an image. Having a link could be useful.

Upon opening a new file, you are presented with a bar that says "Image Import" and "Generate Image." When you click to generate an image, a very organize and visually appealing dialog box comes up with everything needed to  to generate (and looks very much like Adobe Firefly's options). After you generate an image, the original import / generate goes away and turns into the older style input field and a button next to it for reference. Even when adding a new layer, the bar doesnt switch back to the import / generate bar. I think the dialog box should pop up everytime and should also be per layer (In cases when I want to generate and review multiple images in one document)    

Hi, I noticed that when using the clone tool, brush smoothing is unavailable. I would like to see brush smoothing available when using the clone tool. A small amount of smoothing helps to keep your brush going where you need it to. Please consider this! Thanks!

I love this tool; however, I get occasional blotching in the resampled version if the brush head is any sort of proportionally large size. This seems like something that could be improved but I don't want to be picking nits either.    

For those of us who use similar prompts repeadedly, is it possible to have PS remember our last five or ten choices and give us a drop down menu in the prompt bar to re-choose those prompts?

It would be great to have a similar effect of krea or magnífic where you can just improve a base image with AI adding extra details to the images.