Feature Requests

Upload subject or scene images, for the AI to reference in a text prompt. Example:Uploaded Image Marked subject (shows a guy in a blue shirt with a pattern and grey kakis waving hi) Uploaded Image Marked scene (shows a beach scene)Text prompt (Show the "subject" walking in the "scene" with an ice cream cone)The visual provided would reference the images uploaded for a more direct result.

Bonjour,pourquoi ne pas rajouter la possibilité a l'ai de conceptualiser des logos, et autres illustration graphiques comme des etiquettes ?

Not able to genrate image of particular company products or showroom or place, say for example u tell it change background like sitting in a indgo plane or standing at a apple showroom it fails to understand the background 

After removing the background, there is no option to export the image with the transparent background

Seria incrivel criar uma imagem com uma imagem de referencia que possamos fazer upload, seja uma imagem ou uma foto como por exemplo um desenho.dd

This AI is an amazing tool, thanks for making it!Maybe add an option to directly export it to Ps or Ai?

I think it would both be consumer friendly and an attractive service for people to pay a set price(not subscription which is anti-consumer) to remove watermarks at a price or at least a set number of images fora set price.  To say that Artiificial Intelligence has improved within the past few years would be an understatement but much like any other market, there's potential to have a quick cash grab.  I think it would be in the interest of Adobe to offer services that are not only competitive in the AI image generating market but that also stand out.  With that, I'd also like to suggest upscaling, downscaling, smoothing reduction and choices of resolution as features as well.   

Ai to have knowledge of pop culture, for an example it should know about spiderman. or what disney or marvel is.

The AI could take people from 3 different photos and connect into one.

We are also having some questions on superscript and subscript. We are trying to implment the superscript and subscript for the dynamic text in a text area. We have tried even with antialaising and still the super script is not visible properly. Can we have some source code on how we can implement this.

Auto select an object,,like sky, dresses, person, sea, tree etc.

I am kindly request you to please add famous celebrity faces places just like Robert junior Ven Diesel Shahrukh khan Salman Khan ...    This will be help to people to take a photos With their favorite celebrities   Thanks    ["places" changed to "faces" as per later post from OP]    

Bonjour, bravo pour ce que vous faites.  J'aimerais bien que un jour on puisse obtenir les api de Adobe Firefly car J'aimerais développer un bot télégram pour mes différents groupes et chaînes télégram.  Merci 

Ao digitar o código raltivo a cor desejada, que a ferrameta preencha com a cor relativa ao código.Tive sucesso em uma tentativa de troca de fundo, contudo, o mesmo processo não se repete.Ex. Solicitei a remoção do fundo da imagem. brush-settings-background-button solicitei a código #F5661Bum dos botãoes gerados mostrou o fundo da foto na cor laranja mas com tonalidade diferente #AE5C2A e variações. Indicar exatamente a cor para preenchimento seria interessante. 

Hi there,Wondered if we can add our own product, eg sunglasses by uploading so the AI can use the actual product with text? Love this feature. What if we can add brand logos?  [Name removed]

Minha sugestão seria:Não repetir o mesmo gráfico nas letras que forem repetidas em uma palavra.

When I apply background removing with a group photo of 4,5 people. It doesn't properly cut the human subject. Precise cutting is required.then after when I apply background with ai generated scene. It changes the shape of face of human subject with different background.which looks not real. Need to improvement 

Add superhero characters, and superstars, movie actors

Sarebbe bello avere un tools per rigenerare e restaurare vecchie foto.Anche rendere le foto binaco e nero a colori.

Adobe firefly needs a stop button to be able to stop the process of generating an image during the first seconds in case some of the input had mistakes

Add a cancel button for users to stop an AI generation if they realize a setting is wrong, like using the wrong engine (defaulting to VEO, when I wanted to use Firefly) or setting the wrong frame size (540p instead of 1080p). Currently, I feel like I'm wasting cycles and time when I notice the settings just after clicking Generate.

Adobe Firefly is amazing for image and video generation, but I believe it will be even more powerful if Adobe adds AI voice generation. Many creators want to produce full content — not only visuals — and realistic AI voice would complete the creative workflow. This would help: • Filmmakers and video editors create narration fast• International users who can’t speak English fluently• Faceless YouTube and TikTok creators• Content creators who need voice-overs but don’t want to record themselves• Businesses that need fast professional narration Firefly could become a full A.I. creation environment:Image + Video + Voice = Complete Production Tool. Thank you for considering this feature — I think it will bring massive value to creators and push Adobe Firefly forward.

The text prompt and how the video actually turns out is very hit and miss and requires quite a few tweaks on the text and even then its not always perfect or in some cases gets worse.It does listen to some key parts of promps either and seems to just do what it wants to do.It seems very unfair to be charged credits for unused creations. I feel it would be fair to only use credits for creations downloaded. 

How can we actually generate 4K, 2K images on nano banana pro model in firefly, others like freepik,envato, higgsfield already have it 

1. first we have to draw a basic image and they by that image IA should create best photos2. by users have to create videos