Feature Requests

add icon to compare with original image

Add a button to enable or disable the change, so you can see the before and after.

Please add a "favorite" button on the prompt page for image creation.

Brush not good

YOU CAN ADD OPTION FOR A SELECTED PHOTO TO IMPROVE RATHER THAN GENERATE AGAIN AND AGAINORYOU CAN MAKE A BOX TO COLLECT GENERATED PHOTOS AND THEN COMBINE THEM TO GENERATE EXACT RESULT

start with my own reference photo

Hey,would love to scroll more to see different works, now its lacking. Flow should be constant of new art on the MAIN page ;D

Adding 2 separate photos and the merging the photos into 1 

When I tried to change the shirt colour of my photo, it changes but the shape of the shirt and body did't match.Please fix it... 

Ce serait bien de pouvoir quelque part retrouver l'ensemble des visuels qu'on a imaginé, sans avoir à les télécharger.

Upload one more picture for use edit in background or character add in working picture 

Please add a feature where we can resize the canvas and add generative fill so that we can have an image size based on our requirements.

It should extended dimensions and then that could be great 🙂

Please don't add ai tag because after editing the photo ai tag is automatically added then people can know this is edited so there is no benefit of editing photo 

text to image isn't showing "similar images" in search results anymore in the top left hand corner and it is not intuitive at all to click on edit to get to similar images, I would suggest reverting back to user seeing all functions on top of image results

1- If the AI allows the selection of objects in the image area before the design, it can produce objects that are closer (similar) to the subject.2- When it offers three different options, it would be more useful to choose one of them and redesign it close to that. Otherwise, it will produce very different designs again.

Make the AI smarter. I asked for a cartoon version of Vincent Van Gogh painting in a field and I got a lot of grassy fields and only 1 had a person in it and it definitely didn't look like Van Gogh. I asked for Alma Thomas in an art studio teaching students about art and none of the teachers looked like Alma and there were even some that were men.  I tried name art, where each letter of a name was represented by an object shaped like that letter. Did not work at all. Even with me spelling the name out and put into quotations, "Adam" was Adn when the image generated. All of the letters were plain letters, no objects. Instead objects were in the background surrounding the misspelled name.  This would work for plain, simple backgrounds but it doesn't seem to work for anything more than that. This needs to be way smarter. 

It would be great to slect your favourite image and then add a second layer of commands to progress the image further

An ability to move single components around the picture space and have the picture behind fill in automatically. or even manipulation of specific item without comprimising the resto of the picture.  Like to centre the person or move the person into more of a sprint form.  I mean it might already work that way I don't have a lot of experience with text to image yet. 

It would be awesome if we can move objects in the picture. To be able to select with a tool what we want to move and drag it across the image.For example to be able to raise a building higher or lower from it's original lication or even to drag it into the other side of the image. Also, Changing sizes and expanding upon orignial image at any given time would be cool to!

I wanted to add my and my son's pic to my brother and his sons pic

remove adobe logo from the image after download.

i.e. : like i will upload my pic on your generator then your generator will generate my pic into A.I. realistics generated pic

We cannot add elements like rose petals shower over the images. Please work on tht.

As a productivity and creativity enhancement to Adobe's overall platform, Firefly could offer users the ability to provide a text description of data they need visualized. A sample prompt might be "Vertical bar chart decpicted as stacks of newspapers where values = 20, 4, 33, 12, 31"