Feature Requests

Toll wäre es nach dem Einfügen mit generativen Füllen per Tastendruck sich nochmal das Orignial anschauen zu können, anstatt die Entwürfe durch abbrechen zu löschen.

Die Vorschaubilder für Effekte müsste man sich zusätzlich in groß anschauen können, z.B. nach druck auf ein Info-icon. 

Here is the prompt: super hero who knits socks as his super power with white hair, 50 years old, no beard. Remove the beard. NO BEARD, no facial hair! All I get is a santa figure with a white beard.   Even if I remove the white hair, I get a beard.  As though all 50 year old men have beards.  Even when I say NO BEARD!!!!!  You could teach Firefly to read. Better yet, you could allow us to click on a photo and then request for alterations to that photo. As it is, Firefly is lightyears behind Chat GPT for creating images.  At leaste ChatGPT allows you to alter the current image.  With Firefly, you have to change the prompt to try and get a new result and it may or may not use some of the things you like from the older version.   I did try to use the remove tool to select the beard and put in the prompt to "remove beard" but Firefly just replaced the beard with another beard.  So apparently shaving is aga

It is pretty unclear when an image is saved what the file type will be. At some point it is png and another time it is jpg, depending on wether an image is editted or not. This also effects the file name. Some clarity and consistency would be helpful.

Przetworz zdjęcie na video - obracający się produkt (3D)

It would be useful if Firefly video can understand how visualise a character talking beyond randon mouth movements. I have tried something like:<character> saying "hello" Firefly kindof understands it with a human character, showing the character waving a hand, no mouth movement. With an animal, there is no indication of it greeting the viewer.When I use "taking" instead of "saying <something>", I get mixed results, sometimes mouth moving, mostly nothing to indicate speech.

To implement AI in Adobe Bridge for sorting and managing images, consider the following approach: AI Integration: Embed AI into Adobe Bridge to automate sorting, tagging, and analyzing images. This AI could analyze both vector and raster images, including files from Illustrator, Photoshop, and possibly InDesign. Credit System: Implement a credit system where each credit allows for the analysis of a certain number of images, e.g., one credit for every five images. Adjust the credit allocation as needed to balance user needs and resource usage. Automatic Tagging: The AI would automatically tag images based on content. For instance, it could identify elements within Illustrator or Photoshop files and assign relevant keywords. Adobe Firefly Desktop Version: Create a desktop version of Adobe Firefly that integrates with Adobe Bridge. Images tagged in Bridge with an AI reference tag could be used in the Firefly application. Current work arround is Utilize existing tools like GPT4a

give 10 free credits images for month... this is my idea....this is firefly free promotion

Hi. I can't find the images I created with AI(text to image).

I've just been working into a Firefly image from text using the remove button, and happy with where i've got to but I want 1) Upscale my image from here, and 2) save it for future reference. If I exit at this point it seems I loose everything. Please can you add these 2 thing as features

Very good ai

Hello,"I had an idea while editing my photos. I used an AI-generated background for one picture and loved it. To maintain consistency, I wish there was a feature to apply the same AI-generated background to multiple photos, making them look cohesive and natural. Would be awesome if you could consider this feature!"

I love some of the autofill images especially after a few itereations. However, I have no way to go back to the image I am referencing or even a way to save that new image into favorites folders 

Firefly image and video doesn't communicate how it is dealing with contradictions in what is specified. Example 1: In Firefly video in the 'shot size' setting, I choose 'Extreme long shot' but in the prompt text I include 'Extreme close up'.  The result after multiple attempts was that the prompt 'Extreme close up' took priority in the output.  Example 2:In Firefly video, my prompt had "red and orange koala, grayscale" (abbreviated version). Results with multiple attempts included simply a grayscale koala, a mostly grayscale koala with some hint of red/orange in its face and ears, a face that starts as mostly grayscale that animates into a more orange face, a face that is orange but ears, eyes, nose, body are grayscale.The above are clear contradictions. There may be more subtle ones that a user does not realise. A way Firefly could deal with things like the above, both for images and video),is to show the user the actual prompt that was used - so a new Firefly version o

I lost my perfect image i've been editing in firefly, just because my couse navigated one page back. that is just incredibly frustrating. id rather use offline tools in the future, which is stupid, because everything you do is in the cloud. so why not my firefly edits??

I would like Firefly video to allow subsequent output of content to be consistent in look and feel with, so new content with clearly specified (by the user) variations. This is possible to a degree but has limitations as I'll cover. Examples of what I've tried to do with limited success.* Create a powerful looking character by the camera angle and the expression in the character. Then have the same character looking vulnerable. * Create character in video doing one thing for a few seconds, then the same character doing something different for a few seconds.   In the current beta version, changing the prompt slightly can give significantly different looking results.You can use a reference image but it is restrictive. As mentioned in my post Firefly Video 'Shot size' and 'Camera angle' with reference image, if you use a reference image, you can't change the camera angle by the settings or in the prompt.   Firefly Video has a seed number setting. My understanding of a

Olá, bom dia! Gostaria de relatar que a ferramenta necessita de aprimoramento quando se trata de criar imagens de Curtumes (indústria que faz processamento de couro). Atualmente quando solicitamos imagens de curtumes a ela, ela mostra apenas imagens de uma visão muito ultrapassada de curtume que são os buracos no chão em marrocos. Porém, curtume está longe de ser isso. Gostaria muito de uma revisão.  

I've been trying to generate a US-EN image of an extension cord being wrapped up by a worker. Sadly the algorithm is set up to only show EU and APAC plugs (male and female) not US plugs. I also upload images of professional cords as an example for reference. And yep hmmm same results.  Very dissatisfied given I've specified in Firefly US cordage connections :-(. Anyway to help out on this? Many thanks. 

to not have users switch tabs while generation is happening, we can engage them with suggestions based off their prompt, and these suggestions can be visual by leveraging any adobe product so that they are more ready with their next prompt to be exact, than trying out multiple prompts and waiting.

The interface requires significant improvements. Currently, there is a lack of transparency regarding the number of credits used, and no functionality allows users to define how they want to allocate credits for each generation. This absence of control is a major issue. Additionally, the interface is confusing when it comes to demonstrating the expected results based on user-configured parameters, making predictability and usability challenging.Another critical point is the lack of consistency in the tools maintaining standards. Sometimes they work one way, and other times, entirely differently. This inconsistency renders the tool unsuitable for professional use and undermines trust in its reliability. Without consistent results, it’s impossible to depend on the tool for professional applications.In its current state, the experience resembles a "slot machine," where every attempt produces unpredictable results. Imagine if Photoshop behaved similarly, delivering different outcomes every

As a fortunate participant in the Firefly Generate Video (beta),  I have noticed the 'Shot size' and 'Camera angle' settings become disabled if you upload a reference image. This may be an initial limitation as the text-video generation is in its early stages. I see the use of these settings as extremely valuable in terms of what this tool can offer. In my case, I have been experimenting with creating videos based on static images created with Firefly. While I can make the static images come alive through the conversion to video, it would be useful to change the camera angle or shot type. For example, I may want a long shot or a midshot with a low angle. This would allow a user to influence the story, which is very much linked to camera angles and shot types.Screenshots without reference image   Screenshot with reference image:        

Hallo zusammen, durch das benutzen ist mir aufgefallen das die Funktion "Bildformat" manchmal bis garnicht geht. Da man soviele verschiedenen Formate hat und diese auch unterschiedlich braucht, wuerde eine funktion fuer die Formatvorlage echt super sein.  Warum, da man immer nur ein Format bekommt und die Hochskalierung nicht immer bei mir Funktioniert, was vielleicht auch bei anderen vorkommen kann. Mfg Simon.

Posso não estar achando, mas poderia ter um local onde ficasse salvo as imagens mais recentes criadas. Pois todas vez que fecho o FireFly, aquilo que eu já criei, imagens e o prompt, todos eles somem. Se caso eu quiser continuar depois usando os mesmo prompt eu não posso, pois tudo foi apagado. Então, uma biblioteca onde fique salvo pelo menos as cirações mais recentes, por exemplo dos ultimos 3 dias, já ajudaria nesse ponto.Repito, pode ser que já tenha isso lá, mas eu não estou achando, então nesse caso se já tiver, seria legal ficar de uma forma mais fácil de encontrar essa biblioteca.

Firefly could easily address a direct PNG downloads:Offering PNG downloads directly, particularly for images requiring transparency or high detail.Providing better resolution options for export, so users don’t have to rely on external upscaling.

Hi, I can't find the button upscale, is this a bug?