Feature Requests

Dear Firefly, Can you please make option of smaller chest size on your creative output Firefly.No matter what I try to tell you and in my politest manner... "flatter chest please", "more like a Parisienne", "not so American"..... asking for smaller breasts is out of the question since I am not allowed to write that word. (I do understand this of course, though I find it annoying when that monkey appears shrugging it´s shoulders saying there seems to be a problem with your prompt and making them even bigger for my next proposal). Is Firefly built by a male source who fed it with images of what is supposed to be beautiful? This is a little strange I think when it seems ultra important with a variety of different skintones for each prompt for nonbias reasons.. meanwhile you are not allowed to ask for less sexy output, we are all beautiful big chested according to Firefly... I am hereby concerned and worried that the word beautiful is misunderstood and we will be fooled generations to

I wouild like a button to exchange the roles of Styles and Composition

In Text to Avatar when the video is generated there should be a couple of seconds at the end to conclude the statement. In my generated video the avatar ends paused with thier mouth open and it seems awkward. 

I love the capability that this gives. I've been using RAY3 and it's great (HDR version is terrible though). The UI isn't very useable though, clicking the video thumbnails replace the settings and prompt which means I've accidentally overwritten recent changes. The prompt box is way too small and should be resizable as prompts can very very long. Overall, it feels half-baked and cramped. It would be much better if each itteration was a separate entity rather than them all in one filmstrip.

"Generate SImilar" is a great feature in theory but it doesnt work well. Please add a feature to upvote (more like this) and downvote (less like this) so that the next image regeneration continues to be more refined in the direction needed.

It would be great to have a way to view in a presentation mode, removing tools and generate.  I am presenting to a customer, using it as a working brand mood board.  I will have one employee in the board too, working through the concepts and design elements with the customer.  As they like something while I am presenting, I am going to have my employee move everything to a new group.  So we're basically helping them build a mood board in real time.

I kindly request you to add Telugu language support to your application/website/service Telugu is one of the widely spoken languages in India, with millions of speakers. Adding Telugu language support will help users understand and use your service more effectively.I hope you will consider this request and implement Telugu language support at the earliest.Thank you,rajesh

Hi, I have recently introduced Adobe Boards to my team as a way to gather ideas for campaigns. One feature we would love to see is the ability to copy/paste linkable URLs w/in Boards. This would be helpful in instances where it makes more sense to to look at multiple assets on a website or in a linked folder, for example.

When itwill possible to merge two different image or photoes ? 

I really like this and will start using it... I'm trying to figure out what is the best way forward ai deck generation where I feed it a Title and a few bullet points for about 10 slides and it creates a really nice stylized flow and dynamic layout similar to when I license Adobe Stock and place the text as needed. So I am thinking Image Gen + Page Weight + UI Experience in one from text prompts... 

We’re an enterprise user integrating Adobe Firefly Services into an automated asset generation pipeline (NestJS backend + async job orchestration). Current Firefly APIs (v3 image generation & related endpoints) produce only raster outputs, while the Firefly web experience already supports “Text to vector” with downloadable SVG. We request official API support for native vector (SVG) generation to achieve parity and unlock scalable programmatic creative automation.

I had this idea for photshop but it would may be helpful in firefly as well. Something that could leverage the power of AI that would be game changing and useful ,would be the ability to take A photo and automatically composite all the elements into layers, even to go as far as filling in the areas you dont see.So for example imagine a picture of a woman walking in front of a city with cars and buildings. AI could seperate the woman into the top layer, and the city/cars/ect into another layer and fill in the area where the woman was so if you move the woman layer there are no building gaps anymore. Maybe you could select how many composite layers you want to generate or maybe hand select a single element you wish seperate and composite for you to fill in the layers below.This is also useful for editing elements easier and work more freely.AI Video already sort of does this, and you could do this manually which is time consuming but instead we are just taking the same technology an

Hola.Quisiera pedir que los videos tutoriales que se encuentran en Recursos, puedan verse en español y otros idiomas. Ante esta imposibilidad, yo traté de traducir uno con la misma función de traduccion de Firefly, y me negó la autorizacion por derechos de autor. O sea, los videos están solo en inglés, sin subtitulos a español, si traducción al español y tampoco se pueden traducir utilizando la misma herramienta de Firefly.

na parte de traduzir videos com IA, deveria ter como dizer o texto final, tipo, definir o texto final para a IA pegar esse texto e considera-lo para fazer a tradução do vídeo ficar bem parecido com o texto solicitado!

I would like to suggest to add Adobe Color to Firely. This would allow creators to instantly create  color palettes from colors from a generated photo or the entire moodboard. For example, when creating from images: the user would click the •••more tab > Adobe Color > Create palette from image. The palette would then generate and appear on the moodboard as rectangular shapes. 

Needs to allow editing of copy, after generation.Dont remove from cloud area after 7 daysAllow phonetic guidance for words that it struggles to pronounce correctly.Allow for hand gestures via prompts within the copy, head gestures, eyebrow gestureHow about a 2 way 'coffee table' template 🙂

Having an option to copy a previous prompt from the Files window would be a handy feature.

Please put the translation ARABIC language for videos and text  from german to arabic and arabic to german and also otherwise with english and other languages ! thanks

Slow Motion itself is a great visual story telling element, i have lost more the 10000 creidts but not be able to generate even, one slow-motion output, if we have dedicated selection for the speed of motion then it will be great, Half of the content itself look great output, Even Timelapse will also work in same way.

It would be great to be able to have a model or illustration style be recycle-able for different poses or scenes. For example, to be able to use the same male figure, but be able to submit prompts to generate various poses or expressions, such as happy, angry, or sad.

Hey Adobe Firefly team, loving the creative potential of Firefly, but there's a small yet frustrating issue: we can't right-click to copy or save generated images directly. Having to navigate through menus or buttons to download feels like an extra step that slows down the workflow. Adding right-click options for "Save Image As" or "Copy Image" would make the experience so much smoother and more intuitive, especially for users accustomed to those shortcuts in other creative tools.

Hi - you should be able to delete all the non-favorites in your generation history as a batch by maybe selecting "favorities" and then having an option to inverse that selection and then "deleting all". Most times I have to generate a lot of images before the AI understands what to produce that I have in my mind. It's very labor intensive to delete them one by one, but they crowd up my screen if I don't.

With project a voice is chosen for video production. I will like to see the capacity to be able to use an mp3 file to create a talking avatar. I tried  to synch the mp3 file with the voice of choice in Prime, to no avail. I think it will be a great feature to be able to use your own mp3 file to create a video.

1- Increase the time lenght.  Other AI companys are offing 8 sec, 10 sec, few are 12 sec now. 2- Referance images,  Allowing people to add ref images such as object on a white background. (example..  blue folding chair on white background. Its the exact style artist wants chair to be but wants AI to fill in the rest,  I need this because my walleyes looks like a bass or trout *fish speices* all the time, unless I use first frame based of image i create or find) 3- I know working on it but audio.  voice match is getting better and better each day.  US TV editors would love that abilty cuz filiming show out in the feild people miss words or say wrong product name or number. 

Identify favorites in Generation History with a star so non-favorites can be selected and deleted more easily.