Feature Requests

Within text effects can you add an adjustment box to view your word/words and letters in style you are creating with the ability to block out individual letters within the word e.g only one letter gets the treatment with ability to scale individual letters as well within the app.

It would be great to have a project type feature, like a collection or set which you can group your generated imagery into in order to organise and return to it

Having been throug at least a half dozen attempts to reword the text prompt, including the use of scientific names, it becomes VERY apparant that the fault in fact IS the images the AI is trying to use are quite simply put "Only REMOTELY "close to" matching"! Various wordings for the basic idea "American skunks sat at a table eating waffles" has resulted in variations of minks, ferrets and badgers, bur NOTHING "like" skunks, striped skunk (Mephitis mephitis), eastern spotted skunk (Spilogale putorius) or American hog-nosed skunk (Conepatus leuconotus).So the idea would be the ability to be able to upload whatever the ACTUAL image of the desired object is that the AI is SO DOGGEDLY GETTING WRONG so that it could be added to either some personal image database ot the greater image database 

Gostaria que a escrita (texto) nas imagens saissem em Portugues.

when in generative fill mode, collage pieces together to formulate a better picture.for example  I like a certain image but not all of it, so I take what I like, and mesh those together with other pieces I like to form a unifying piece.can I please be the one to help implement these? I have an unlimited supply of these.

Enable users to stitch their products onto a model for e-commerce websites. Using this feature multiple images of different styles can be created.

I think one of the biggest improvements would be to be able to use adobe fonts in the text effects. The existing fonts now are very sparse and leave very little creativity.

Hello, I'd like to propose an idea, if it hasn't been implemented already: could we link the original contributor of a prompt idea who has shared their content in the library, while also offering them the choice to remain anonymous? This could pave the way for us to connect with them, and perhaps even collaborate with creative minds of similar inclinations. While I've come across numerous captivating images, I recognize that they're AI-generated. Nevertheless, there's often an artist's vision that precedes the tool's output. I'm keen to understand the inspiration behind such prompts and seek permission before using them, especially if they're original. Unfortunately, I haven't found a way to do this yet, and I'm hesitant about using someone's unique concept without proper acknowledgment. Thank you.

Add social media Tab for social media preset in New document Window for Photoshop and Illustrator

Good morning,a simple nice improvement i'd like to see, would be a way (after the 4 different pictures are created) to select one and let the program to keep on developing new pictures with the same subjetct.

An enhancement for the "in exploration" Text to Pattern commands: allow the user to define the layout beyond block layout, to also allow half-drop and brick layouts at the very minimum. That would be a tremendous enhancement for patterns in repeat, tiled, surface design, textures, etc. Also, either during or after generation, if the user could also define how to mirror/flip/rotate the graphic then that would be off-the-charts amazing.

I was stuffing around with the font-style generator and found that you can't really get the text to be 'one large X', e.g. one large cloud or one large snake, it always just fills the letter in with other large snakes or clouds.Oh and while I'm on the topic I would also think it cool if the font-style generator could have more parameters, like the other ones, like maybe how much of the letter it has to conform to (like, can it remove parts of the letter to make the font look better?) or other things like similar things like that to make it more easy to make fonts that match my expectations.Im just saying this because I went into it expecting something and it gave me more of what I expected and less of it at the same time.And could you make the thing not generate until I finished changing all the parameters I need to change? Thanks.

Dear Adobe Firefly team, I am writing to suggest that you add Arabic context to your platform. I believe that this would be a valuable addition for Arab and Middle Eastern users, who are some of your most active consumers. According to a recent study, the Middle East is one of the fastest growing regions for digital consumption. In fact, the region is expected to reach a value of $100 billion by 2025. This growth is being driven by a number of factors, including the increasing adoption of smartphones and tablets, as well as the growing affluence of the middle class. Adobe Firefly is a powerful platform that can help Arab and Middle Eastern users to create and share content. However, the current lack of Arabic context can make it difficult for users to fully engage with the platform. For example, users may have difficulty understanding the terminology used in the platform, or they may not be able to find the content that they are looking for. By adding Arabic context to Adobe Firefly, y

Can change the skin color of the person from white American to Black American. Without changing the face of the model. 

It would be great if when generating a room to "hang" my art in, if the ai could understand what dimensions my art is that I am going to want to put in. Right now the system wants to just create giant squares or 4:3 sizes.

it would be nice, if the AI could learn, like: Generate a composition of two objects "A" and "B". "A" is the letter V made of black feather, "B" is  the letter S made of white feathers. Place "A" behind "B". The more prompts i use, i get coplete diffrent results. the prompts will only be partially implemented if there are too many (or if it is not too general / or if the description is more detailed). I cant get a V from black and an S from white feathers, but get a VS from mixed black and white feathers e.g.

I want to give you a suggestion, if you want to work on this, then you must pay attention to this, we faced this problem while I was editing my background photo, at that time you should not save the photo of different location. While the location where photo editing is being done according to the skin machine of a person, if you want to paste some photo of that country only, then you can put it on that location, while I have seen that photo background using At the time of doing this, foreign country's Hindi company's other country is attached to another country, so you should take maximum care and the number has also increased to choose

To draw and fill with colour 

Add structures like trees, pepole, houses, cars etc.(as stickers, so that they can easily show the AI where they really want the thing.) as special objects and let the users make their imagination images roughly on a blank page. After that, let the AI show them the enhanced version of the image they made. Show them multiple options for the same image. With this type feature, the people like us who don't know the English language well, will also be able to do the image generation easily. And also the other people don't have to give prompt again and again to make the AI understand. I am facing the same problem. That's how the idea came into my mind.

Hi Adobe,I am veerendra nadh. Thankyou for wonderful features provide though app and online services. I am graphic designer and this is more help to me.My suggestion is can build up small gif in text effects.Like snakes move in and out text. 

Hi, please design a part in website for Creating Loop Animated Video From a Still Static Image.

Poderia melhorar a qualidade das imagens geradas no Preenchimento Generativo para serem baixadas. A qualidade fica um pouco ruim da imagem original. A ferramenta (Adobe Firefly) é muito boa!

There REALLY needs to be some tool to adjust the depth like a camera focus, so you can zoom in or out with a picture. ESPECIALLY out! 

Using firefly, a tool that can change the color of one element of the picture without changing the shape of the element.IE : now, if we select a green T-shirt on a model and ask for a red one, firefly create a totaly new T-shirt. The idea is to juste change the color of the existing one. 

Would be great if you could rotate images.