Feature Requests

A dark background would help.

You should also add the feature of adding the person who is generating the image

The process of generating images curating to favorite the best options becomes laborious and boring, even more risky that you lose everything if someone deletes cookies from your browser by accident. We urgently need a simple button to download all images from favorites at once or in batch. I would not like to use the save option in the CC library this is a little useless in the usability of the user who always sees 4 result options.PS: I can like images from the community but it doesn't make sense if these likes don't go somewhere and I can consult later, as well as the basics on all the sites that you like images (freepik envato...)

The AI seem not to understand "no background" or "plain white background". Try to teach it this.

Je me sert régulièrement des mes créations en arts plastique tels que peintures, dessins et autres créations prises en photos mais aussi de mes créations numériques notament réalisées avec photoshop et d'autres logiciel. Très régulièrement le logiciel Adobe Firefly ne m'autorise pas à me servir de mes crétions sous prétexte que cela n'est pas autorisé par les standards de la communauté. De plus certains mots dans les prompts me sont bloqués régulièrement pour les mêmes motifs. Si ce logiciel doit être un outil libre de créations ne peut-on pas avoir un bouton ou une case à cocher qui permet d'indiquer, comme une déclaration sur l'honneur numérique, que l'on assume juridiquement la paternité des créations utilisées ainsi que les recherches graphiques associées à nos idées ? Je fais souvent des créations mystiques sur fonds de poésies noires et de spiritualités qui inclus des questionnement sur la vie et sur la mort que je cherche à mettre en images et cela m'est interdit pour le moment

First of all, I am very happy using Firefly so far. Thank you very much. I wish there is a function where user can type addictional prompt when using a function [Edit - Create Similar Image]. For example, user can designate one object to change the location or resize it.ex1) Make tree 130% bigger and shift it to 10% to the left. For adding additional prompt, there could be prompt textarea for user or combo box(select box) for certain object which program can change property of the object. Thank you for reading this:) 

Derzeit ist es, meines Wissens nach, kaum möglich, einmal aus Prompts und Effekten erstellte Grafiken später im gleichen Stil  zu reproduzieren.Ein Beispiel: einer erstellten Grafik soll später eine weitere Grafik folgen. Natürlich im gleichen Stil, so dass sie zueinander passen.Zwar werden die genutzten Prompts als Dateiname genutzt, die Effekte die zur Erstellung genutzt wurden, muss man sich mühsam wieder zusammen reimen...Man kann doch die Bezeichnung der Effekte in den Bildinformationen hinterlegen oder ganz einfach einen Verlauf anlegen, in den man sieht mit was man wie erstellt hat...

Make a feature to change clothes perfectly 

Output imagery at 300dpi 

No puedo hacer juegos de recortables. Ya que me dice que incumple las directrices , es absurdo

I think adobe firefly really needs to know more about anime Characters such as "Sosuke Aizen" From Bleach and "Satoru Gojo" From JJK, when I tried to make their wallpaper for my phone, it created simple anime faces, which didn't resemble reference image I fed it, the AI doesn't know anything about Anime Characters and their appearance particularly famous names I mentioned above, it would be great if he knows face of Gojo And Aizen! 

hi, how come whe have write first and get the first generate image and then all the setting menu show up? why not just make the setting show up from the beginning before prompting? or is there a way?

Why has Adobe created a bunch of artwork in the style of Abigail Larson without compensating the artist? Why can Ian McQue, @Loishh, and several other artists all find their names in the Adobe Library when they never put any of their artwork up into Adobe stock for sale? I thought Adobe was supposed to be "ethically training" just on the images that Adobe owned in its own stock library. It appears now Adobe is being trained just as unethically as all the other unscrupulous Ai text-to-image generators. Very disappointing. Adobe you are now directly stealing and laundering the art of your own users. Please fix this.

After editing an image in generative fill, I can't seem to get back and edit the original image. I get sent back to the landing page and have to start all over again. This seems a pretty basic oversight but maybe I'm missing something?

Adobe Firefly is Awesome in concept.  The Adobe Corp needs to focus on UI and UE though.   The fact that this isn't a standalone app is MAL. I would also say that Adobe needs to unlock allowing for Print res and also why not make this engine a built in feature witth Illustrator or Photoshop?  I just think Adobe is great and the suits in the hightower are stunting growth...  Just my opinion.

It's a problem that the advanced features of Firefly, especially custom styles, are not available to individual users. This creates an unfair advantage for large companies seeking growth, while limiting the creative potential of individuals. We believe in equal opportunities for creativity, and many talented individuals could create remarkable work if given access to these tools. Therefore, we urge Adobe to reconsider its policies and offer the same creative resources to individuals and corporations alike. This would foster a more equitable creative landscape and benefit the entire community. Thank you.

E.g. it would be good to make and save presets (with an example image). At the moment I have to do screenshots...The icons could be larger.Also, a search field for all the Promts would be nice (e.g. search "Hyperrealistic").The Structure Slider could be more sensitive. At the moment one can only adjust it to 3 steps. More (1-10) would be better for refinement.

Firefly 3 is a definitive huge step back from Firefly 2 Just look at these two images! What would you rather eat??? Common Adobe!!!

adobe firefly ne semble pas connaitre l'univers de warhammer 40K et c'est vraiment dommage

Please add the idea of ​​isolating the main element from the background as layers and download file as psd file

How about saving the favoiurites in the cloud and not locally on only that particular browser... Cloud this cloud that and then the app that operates entirely in the cloud saves the favourites locally in the browser.... I haven't even found out how the heck I transfer favourites to my cloud at all. It only saves a severy compressed Jpeg in the cloud... What the heck... That is the most stupid thing I've seen in ages. 

Tarayıcım sıfırlanmış ve firefly yardımıyla oluşturduğum bütün görseller kaybolmuş. Nasıl geri getiririm ya da geri getirmem mümkün mü?

In addition to a freeform text field to prompt Firefly we NEED a "prompt builder" that breaks down key prompt elements to ensure that users understand how Firefly will interpret their elements. For example, a series of text boxes for; camera angle, subject, subject angle, background, lighting, etc. can help users write more precise prompts with better results.

So, I had to re-write this when I realized it was going to be a community post, versus sending in feedback.  I did not edit much, but want to get my point accros.  I tested out the Gen AI with Firefly today using both the Image 3 (preview) and Image 2 ...whooosaaa...and I am really sad.   When you think of how the big players in the ai image gen space are doing it by using an Art Style to first define the image and that encompasses so much.  There are HUNDREDS, But for some really strange reason  Adobe has it in under "Effects?"    This is confusing and very frustrusting. And to be honest, that  jumbled "Content Type, Structure & Styles?"  More difficult than necessary.  Maybe others have found a way to perfect this, but for me it really made a difference as the Firefly results were...Whoosaaaa (just look at those I compared below), and after generating a few images, I am good.   I d

It would be great if after creating an image we would be able to download it in different file types, dimensions or even higher quality for print. Printing usually requires 300 dpi and currently the files download in 72 dpi.