Feature Requests

Would it be possible to include a next image button in Firefly.In Firefly, when you generate 4 images and you open one of the images in full could we have the next image button back please? At present you have to go back to the four images and click on the next one, it's quite time consuming when you could just add a button that opens the next image without having to go back to the four images.

Hello, Adobe Firefly team!I actively use your service, I use the NANO BANANA PRO model for operational work. Faced with a critical problem: The current token limit is sorely lacking for professional tasks.The main difficulty is the inability to insert a structured prompt in JSON format. When I try to set detailed parameters (composition, style for each object, color scheme), even a compact JSON file does not fit in the input field. The NANO BANANA PRO model, where accuracy and the ability to quickly repeat queries are often needed, this limitation completely blocks efficient operation.I either have to split one idea into a dozen simplified queries, or abandon fine-tuning, which greatly reduces the quality of the final image.Request: Please urgently consider increasing the character limit (tokens) in the prompt input field. This is necessary for:Using structured data (JSON).Improve the accuracy and reproducibility of the results for all users.Thanks for your attention! I hope for a spee

in The Generate video still in the sound of music so loud eventhough already notice no extra sound of music add to the video.please making sure no music added in Video generate.. it's hard for us to convert this video in to out mv music..so mess up sound

  Description（説明） Fireflyボードで、オブジェクトを複数選択すると整列が出来ますが 並べ方や大きさはそのままで、整頓だけしたいです。   ↓自分なりの整列をしている状態（服の色分けと優先度）の並び順と大きさは変えたくない。   現状、配置が「行」「列」「モザイク」の3択になっている ↓行で整頓   ↓列で整頓   ↓モザイクで整頓   すべて、大きさと位置が変化してしまいます。   ↓希望する挙動   ↓レイアウトや大きさは変わらず、グリッド状に整頓される   2. Why is this valuable to you?（なぜこれが価値があるか?） 整理整頓の手間を減らしたい。   ※現状のFireflyボードの場合、希望の整列をするためには まず上揃えをして 均等配置（水平方向に分布）をして   それから1列ずつ縦を合わせと均等配置をしていかないといけない   1クリックでグリッド配置できれば、何度も整列を繰り返さなくて済むので、かなりの手間が省けます。

Dear Adobe Team, We would love to see Turkish language support for dubbing added to Adobe’s AI dubbing and voice tools. There’s a huge and growing community of Turkish creators, editors, educators, and businesses who rely on Adobe products every day. Native Turkish dubbing would make content localization faster, more accessible, and far more impactful—without depending on third-party tools. Adding Turkish would help creators: Reach wider Turkish-speaking audiencesProduce multilingual content more efficientlyKeep their entire workflow inside Adobe  Thank you for continuously improving your tools and listening to the global creator community. Hoping Turkish dubbing makes it to Adobe soon! 🇹🇷🎙️️ #Adobe #FeatureRequest #TurkishLanguage #Dubbing #AIvoice #ContentCreators

Be great to have crossfade and fade in / fade out of the audio tracks. 

I would enjoy a way to reserve a portion of my generative credits. For example, it can be easy to accidently burn through them with video generating leaving me wishing I had some reserved or allocated for generative fill in Photoshop. This feature would not only help prevent running out of credits but also eliminate the concern of it happening at all.  

I use Adobe Firefly for my school projects, and it would be extremely helpful to be able to create citations for the generated images within Firefly itself. 

Currently, Adobe Firefly boards are not accessible or viewable on mobile devices. This represents a significant limitation for both content creators and platform ambassadors, as a large portion of digital content consumption now happens on smartphones. As an Adobe Firefly ambassador, when I share a board to showcase creative processes, results, or to inspire new users, the inability to view it on mobile creates friction and rejection. This directly impacts the user experience, limits content reach, and reduces opportunities for discovery and subscription to Adobe Firefly by potential new users. From a market perspective, this limitation means excluding a substantial segment of the potential audience, especially those who consume content through social media and mobile devices, which are currently one of the main acquisition channels. Proposal I propose an enhancement or expansion of the boards’ functionality so that they: Are visible and navigable on mobile devices. Allow at least

 User defined guides/grids for layout: the behavior of the pink smart guides is fairly quirky.Support for even more standard Adobe CC keyboard shortcuts–such as shortcut for add content, spacebar hand tool.Alignment tools.A way to get info (filenames, basic metadata) about the content so less labeling is required.Abilty to export an entire board as pages in a document format that supports media (PDF?).

I have two suggestions for features regarding Adobe Firefly Translate video. 1. Idea - Make the transcript editable. Sometimes the automatic transcribing makes mistakes or specific names are written wrong. 2. Idea - Add a "re-lipsync" feature. Sometimes I want UGC type videos in different languages.  Whitout any further work on this Translate Video Feature. I cant work properly with it. 

hey mir gefällt die app wirklich sehr ubd ich benutze sie für die Arbeit mir fehlt wie bei Higgsfield das man vorlagen von verschiedenen personen hat Zb. Arzt, Polizist Anwalt und so weiter das man die Bilder anders abarbeiten kann für ein Werbe Foto 

Create a ready-made AI library organized into categories such as construction, fashion, architecture, travel, vlogging, and safari. Have your team members build this library, then allow Adobe users to save it to their user libraries.

Should be awesome if we can select all the sources after import and have a option to group by file type, may could also select different dashboards and order by file name or modify date (ASC/DESC) 

I think that adding a feature that allows you to draw on the actual AI creation, to help promp changes. For example you have a flower at the top of an image and you want to move it to the bottom; being able to draw an arrow, with a mouse or an Apple Pencil, a promp box comes up, you write 'move this flower here', drawing another arrow to where you want it.    This would make changing things much more tangibility.   [Subject modified to reflect the suggestion. -droopydog500-moderator]

Hi, sometimes there are several similar  imaes that are in my scrolling history of generated images. I use one as a reference image; and then I want to double-check that I used the right one. I put my mouse on the small reference image but I can't enlarge it and confirm which of the generated images I am using.I think a way to see it bigger would be handy.  Thanks!

more generation AI credit tiers.  like maybe a 15,000 credits a month? 

adobe firefly를 이용하는 유저인데요내가 좋아하는 그림 스타일을 한번 실험해보니까 내가 원하는 스타일이 나와서 좋은데...뭔가 아쉬운점이 있는데요....크래딧이 소모되니까 월간이든,연년이든,정기적으로 구매는 나오는데.....1$,3$,5$ 같은 크래딧 구매가 없어서 약간 아쉬운데,,,,(다른데서는 1500원,3000원,5000원 같은 포인트를 구매할수 있는 시스템은 있는데....)  크래딧 충전 시스템 개정은 언제하나요?이런 형식으로?   

Bonjour, considérant l'énorme augmentation de 67 à 78 euros que vous imposez unilatéralement à vos utilisateurs Creative Cloud, j'espère que vous allez la justifier en nous offrant des services ia plus performants et sans surcoût. Firefly n'offre par exemple même pas la possibilité d'améliorer la netteté d'un rush flou. Merci beaucoup de satisfaire vos utilisateurs avec des services en rapport avec le prix auquel vous les vendez,Cordialement, Benjamin Waldbaum, abonné Creative Cloud depuis 2017.

Hello Adobe Team !Coll be nice to push back the "place on canvas" to the right location, on top of the image !thanx.... add push Gemini 3 to 2K & 4K !

Hi, I am using Nanobanana 3 to make superheroes.The first prompt creates too much lack of detail around the eye; so it is hard to see where the eye ends and where the skin begins - I hope that makes sense.I solve it by using the output as a reference image into prompt 2:"Good. Can the skin be more detailed. Can the lighting show less contrast on the skin?" I wonder if you could have a sort of CLIPBOARD APPEND so that any prompt I do in my work, Nanobanana will append that extra instruction or even know to do a follow up batch task of doing the seconf generation for me?  Thanks

Hi, last week, I only could use one reference image in Gemini 2.5 Nanobananana (now vn 3 also).This week, it seems that I can use more than one reference image; and that is great for some tasks but it increases my error rate for my current task:I have to remember to delete the orginal reference image and apply a second one;otherwise, there is the original redundant reference image beside the intended reference image.Could you have a mode to switch from single image reference to multi please?  Thanks!

When I generate a video, I usually start with a quick test using a fast model to fine-tune the prompt before switching to a pro model. For example, I may want a 4-second video and run the tests with Veo 3.1 Fast, but when I switch to the pro model, the duration automatically changes to 8 seconds. This has happened to me several times: I forget to adjust the duration and end up consuming twice the credits.Related to this, it has also happened to me on multiple occasions that, while waiting for the video to be generated, during that time for reflection, I realize that some setting is not quite right or that I have a new idea. During generation, it is indicated that if I close the tab, the generation will be interrupted and I will lose the video, but it is not clear whether the credits are also consumed in that case.If the credits are indeed consumed, it might be useful to have a button to cancel the video generation, consuming only half of the credits.

I’ve noticed that the speaking quality of Text-to-Voice-over is better than that of Text-to-Avatar. The pronunciation in Dutch sounds clearer, more natural, and aligns better with how the language is supposed to be spoken. Could this be because Text-to-Voice-over uses ElevenLabs, while Text-to-Avatar does not?If so, is it possible for Text-to-Avatar to also be powered by ElevenLabs?

I want the videos to be much longer at least 10 to 20 minutes