Feature Requests

Specifically,it would be great when we could use firefly for ai based editing of Own's photo👍

what if someone upload a picture on text to image and it will help him to make according to available prompt or in his mind already means it will give more access as well as more ideas through one picture that he have and he want to edit it, so he can choose adobe firefly because it have easy and fast service.

Good morning,I tried to transform a picture into an old postcard in black and white and sepia, it is impossible, can be interesting to change the colors with more precise words?

There can be more focus on the uploaded image and how AI generate the background. most places there are scope of improvement in blending both the images. there is also good area of improvement needed in terms of selecting some background (for eg: temple, i am getting the same background even after searching with multiple keywords)

So how about a box that has a point that you can direct to any part within and a value slider that can adjust the save level or influence of the reference image. Also two other things to check off: inverse, white background. It would also be handy to have a save face check off too. I can start off with a white background but after so many iterations things get really weird and alien. It starts to add shadow and then the shadows separate. Then it turns it a spotlight. Then it took more of a banded hue and eventually into something that looks like an alien mouth. The AI wants to do something so this would be a very useful feature.

The AI interprets "make the background color pink" fine but can not yet interpret "make the background colour #F00BAA" That would be an awesomely powerful additrion! 

I suggest that on the right side of the image creation page, there will be an option to determine where the object will be placed in the image. For example: if I asked for a person standing in a field, sometimes it will only give me the image from the knees up, and I want to include the whole person.

The idea I've presented may seem intriguing and has the potential to empower individuals who may not have traditional drawing skills to express their creativity and storytelling abilities through comics.This application could incorporate various features to assist non-artists in expressing their ideas effectively.By creating an accessible and user-friendly comic-making application, Adobe could potentially democratize the art of storytelling through comics. It would allow people from diverse backgrounds and skill levels to share their unique perspectives, thoughts, and imaginations in a visually engaging and expressive medium. Such an initiative could contribute to the evolution of comic art by introducing fresh ideas, narratives, and styles from creators who may not have previously had the means or confidence to participate in the comic-making process.Overall, the idea of an Adobe drawing application tailored to empower non-artists to create comics has the potential to unlock a vast ra

I just saw a Verge article showing an emerging AI tech that is like Adobe's Puppet Warp + Content-Aware technologies on steroids.  It's awesome!  Adobe should acquire this tech and integrate it.  Here's a link to the Verge article: https://www.theverge.com/2023/5/19/23729633/ai-research-draggan-manipulate-images-click-and-drag

If posible to add the image and type what ever the customisation we want from the iamge. For Example:A person holing ( PNG image). It will be huge update.

Is there a way to delete "favorite" images from the Favorites page? Or a way to "un-favor" an image?Thanks in advance!M

how about you create an AI that create an image using another image(s) ?

A stereo pairs option.

Into the 'composition' choice bar, add the possibility to choose the angle view of the subject. Face, profile, 3/4 angle, left to right/right to left. Like shot from below, above.

As an artist, my goal is to bring my imagination to life through visual images. However, the text-to-image AI falls short in accurately translating my unique vision. While it generates stunning abstract and realistic images, they often follow a popular pattern. For example, let's consider a specific image I had in mind: a white sail floating in the midst of a stormy ocean, with a colossal wave rising towards the sky and gradually transforming into a mesmerizing galaxy. I wanted the wave and the galaxy to blend together seamlessly, as both possess circular structures. Unfortunately, the AI struggles to merge these distinct elements and fails to capture the essence of my vision. It kept producing images where the ocean and the sky had a clear boundary.  Its limitations prevent me from fully expressing my creativity. Although useful for quick ideas, the AI falls short in portraying my vision. It feels like the AI imagines for me, hindering exploration of my own artistic ideas. In sum

It would be raelly helpfull if text to templet feauture is available 

Make it better than midjourney and Leonardo.ai check the images these two image generators can out put. Your ai generates disgusting images. I am sad to say that truth hurts. 

It would be nice to be able to combine two or more images together by describing which part to keep on each image.The main interest would be to be able to upload your own image as a base for a generated image.

It would be interesting to be able to ask to describe a character or a scene from a specific book (so that the AI ​​keeps in mind that it is that character from that book) or a historical character based on an already known historical description

Would be great to know more about the optimal syntax. e.g. how to insert letters and numbers for a lettering or logo with keeping the exact phrase.

Firefly as an AI editor on mobile platforms like Android or IOS. Basic video and image editing, as a "plugin" and update by inserting the feature into existing applications such as Adobe Rush and LightRoom (not classic).Sample: "low saturation, soft green light, overlay with yellow light coming from the left side of the screen"

For example when I type "Griffin flying in the sky.", it gives me a regular eagle without the lion body.I'd love to do more monster/creature images, and not just dragons.Please add this, so we can be more creative with our images. ❤️If this wasn't already planned, that is.

In the furniture world it is extremely hard to get images of specific pieces of furniture covered with all the coverings of fabric and leather available. It would be awesome if ai could take our photo of a piece of furniture and recover it with our photo sample of available fabrics and leathers

Faceswap feature like insightfaceswap that you can use on midjourney, it's extremely accurate.

Hi everyone!I love Firefly beta but for me it would be nice, if I could load up videos or own pictures/photos and change them with firefly and then afterwards download it.Is that possible? I hope so! Thanks ❤️