Feature Requests

Creating images is great for illustrations, but it is essential, especially in academic areas, to be able to cite the source correctly, so it would be nice to have a way to reformat the citation in different styles to be able to say:I created this image using Adobe Firefly with this prompt and these settings. 

A vector technique and style to create icons on Firefly would be very useful.

Ich vermute, mein Verbesserungsvorschlag sprengt im Moment die technischen Möglichkeiten von Adobe Firefly, aber in ferner Zukunft sollte dies möglich sein. Ein Effekte-Vorschau-Fenster, um im Vorfeld die Auswirkungen der angebotenen Effekte besser beurteilen zu können. 

Was hoping that Adobe can update Firefly to produce high esolution bump and displament maps using the Gen AI functions? It would be very powerful and efficient for quick 3D models.

Please can you do zzom-out option like Midjourney? Thanks

While Firefly is very impressive and have rendered some cool images for me then i feel like I am wasting a lot of "credits" on getting the camera angle correct most of the time. It may be my formulations or descriptions which could use work but I do feel that the current camera angles dont work at all even wyhen selected like the AI just ignores them. Would be nice we could could "hardlock" the angle so the AI dont just ignore it and get more angles like side view, isometric view, working panorama view and so on. Not sure how it could be done but having something that force the AI to actually use the camera angle we  want to use would really be helpful if we are looking for a speciffic camera result without having to spend time/credits when it generates something wrong.

I am mixing one design and two images in Freepik, but it doesn't work exactly the same in Adobe. The sample image can provide inspiration, and by taking the color from the other image and blending them, a beautiful result can emerge.

Quiero que añadan la opcion de control z, porque hay veces que se comenten errores 

A simple search funtion in the gallery so we can look for specific types of images and styles etc

نرجوا من التطبيق توفير خاصية صنع فيديوهات بحيث يكتب المستعمل السيناريو وذكاء اصطناعي يصممه له عن طريق نوع رسم الذي يريده مستعمل 

In it's current state, I have to view samples before I'm able to unfavorite an image from the Favorites page. In rare cases, the image I favorited doesn't track to the same set of samples, making it impossible to unfavorite the image. It would be great to have the ability to edit/remove/organize favorites directly on the Favorites page 🙌

we need to be able to select a size not just ratio.  We also may need to adjust this size where the image stays clear and doees not pixelate.  some type of vector or something

I get confused to what effects or colors in firefly do so I have to prompt every single affect to know what doing what. It nice to have a more details and description for each of it.

PROVIDE A LIKE OR FAVORITE THAT SERVES THE END USER NOT for the people to know how much people like there stuff. No its a gallery of favorites that can be found so much easier vs having to scroll all over again if you go back to the gallery. Here I was clicking likes only to find they are for serving the creator which makes sense but from a sense of creating likes or favorties for me to go back to check out instead of having to go back Seems like a simple toggle would allow all my favorites to show up in once place while still provideing alghrithm for the creator! Understand what Im requesting?

Let the AI look on the web for refrences on waht you're trying to make. Thats all. 😛

If there is one truly "silver bullet" problem that gen AI should be solving -- and specifically Firefly should strive towards -- for creatives, especially those in archviz, interior design, environment concepting, etc. is to make Firefly brilliant at understanding how to populate an image, render, photo of a space and fill it with accurate crowd imagery, and provide controls on how dense to populate the scene.To accurately account for lighting, perspective, have controls for the demographs (general public? VIP event?) and how dense the scene should be filled, and intuitively know to put a few people in the front of the scene, a few in the back, to understand how to generate crowds to interact with the elements of the image, like seated guests on couch furniture, or ordering a drink at a bar element.

It would be great, and possibly would allow for more accurate "reading of text" if there was an option button to choose fonts from an adobe typeface. I know this is a tall ask requiring a deep look at the underlying code, but it would also likely solve the general AI issue of being poor at generating text. Basically, if the option button for text is checked, a subroutine would be inacted that ran text recognition and then replaced the recognized text with real text from a font database.....Having it run only when a user selects a radio button would prevent other elements from being recognized as text and help it to learn. just a thought. 🙂 

Introducing new dimensions for the aspect ratio feature in Adobe Firefly would be a great improvement. Another suggestion would be addressing the issue where previous designs become inaccessible after a certain period in the history section

Perhaps could you add a Slider? For us to to see it the whole history of the pictures

可以加入比較不同種類的動漫風格,例如二次元風,或是像美少女戰士或柯南風,不用太立體

When creating AI graphics in 672x384 resolution nothing is visible at least 1000x500. No details and we lose valuable tokens.

Hi,Recently, we wanted to use advanced Adobe Firefly Services, like Custom Models, Adobe Firefly API services, etc.  However, they are not available for VIPMP customers, only available for ETLA customers.It will be good to have also for VIPMP customers. References:https://developer.adobe.com/firefly-services/docs/guides/get-started/https://helpx.adobe.com/enterprise/using/assign-users-to-firefly-custom-models.html Best,Olaf 

I do not like the popups of any kind that covers over content. there is plenty of space on top for notifications and options. screen realestate is critical for all developers. so i hit fav and now cant click share! because the popup is in the way.

I'm not sure if someone else already wrote something like this but I had some weird stuff happening with the prompts I wrote. Like for example I would write "cheetah and bunny running together" and I would get a hybrid cheetah bunny or only a cheetah. I know Google uses punctuation marks so maybe it also can be used here?Like write: "cheetah" and "bunny" running together. So the 2 animals won't be merged in 1 weird animal?

Using AI recognition to be able to align certain elements to the canvas or to eachother would be beneficial for my workflow. If I have for example 100 images of people in different poses, and need to align their faces to the center of the canvas, that is a lot of eyeballing and manual work. However, with AI recognition I believe we should be able to do this now.Faces would be the obvious use case, but if it would be possible to customize this even further that would be spectacular. For example, typing in what to search a batch of images for, such as "XYZ Logo".