Feature Requests

If Adobe Firefly could do this, it would be revolutionary and amazing: generating an image but from two camera angles and rendering it as SBS or top-bottom so it can be viewed in magnificent stereoscopic 3D.Currently, using LeiaPix converter, a fake 3D (depth-map based) image can be created, but it will never compete with a true geometric 3D.See some Adobe Firefly imagery in fake 3D here:Adobe Firefly AI in 3D VR 

Sometimes the text to image generates some pictures that deliveres exactly something that I visualized in my mind - but in seperate pictures. It would be really awesome if I  for example could select "Background" from picture A and figure from picture B and combine them.

a girl in a forest 

We need more features:-zoom-text on 2 or more lines-possibility to enter more text-options to move/rotate/resize/bend text (each letter separately)-load your own background-working on layers-increased number of available languages (now national characters are inserted, but fonts are in a different style)

I how u guys can create a image to vector conversorsomeplace where i symple upload a image and transform it into a vector

Hi there, hope you're doing great!One idea as a suggestion could be the possibility to add custom color since now only we have the option to use a pallet predefined.This could be a good implementation since if someone wants to create something and use their branding color is not possible. I love the tool, I'll keep testing it.Best regards, 

Add Image to ai art for more options so the ai can learn from it

mixing two images for examplea computer 3d model of a buildingand a particular style of a architect or architecture movement like brutalismwhich can produce blended result

I hope you take a look to some apps that give you examples to click on it to add prompts like imi prompt that would be a great idea 

could we have freedom with artificial intelligence use a selection of photos to create a realistic person as we want and as it is moving more is my opinion more is very good so far

It would be a useful feature have an option to be able to start with simple prompts and add to them, and build on top of the same image, so if we find parts we like, we can keep them, instead of generating an entirely new image each time.   For example, the following images had good results for each individual element added to the prompt, but each time completely changed the composition.  The final image is the key elements arranged how I originally wanted them to appear. 

Hello!  I am a Director of film and commercial video. I am excited about Firefly's ability to create backgrounds for greenscreen shoots. Although, it would be great if it had a Zoom Out or Zoom in feature. I have gotten quite a few interesting photots but I'd want to Zoom Out more so as to show a wider shot. Or Zoom In more as to show less. I tried the Wide Angle selection but it didn't do much. It would be better to have something that was more like a slider where as you could just slide it to the desired size and then it would fill in. It would also be HUGE to have a way to change the angle of the shot. When doing greenscreen I'll need to match the angle of the picture with the talent or else it won't look correct and makes the whole thing look off. I tried typing camera looking down at 45 degrees but that didn't work. Againg if there was a way to have a slider to turn the "camera" up or down or side to side it would be amazing! So far this is really interested to play

It would be wonderful to have the ability to choose one primary image from a group of four and then have the flexibility to make modifications to that particular image. These modifications could include adjustments to color, focus, blur, changing the person or object, or altering background elements, etc. This process would generate a new set of results and include the original image selected. For instance, in the image provided, the first dog is perfect, but it would be great to change only the color of its fur or the background.

A Real Nut Job is the title of a business but has been restricted (seems a bit extreme)No baklava image referencesWould like negative promptingWould like to understand how styles work (order of operation)Would like to control seed 

Would it be possible to erase the horns from the Viking helmets, because the only horns vikings used was to drink from.    

When the generator comes up with an image I really like it would be nice to be able to change the aspect ratio without it regenerating all new images.What's really needed is to be able to select an image that's working and then isolate it and then continue to refine and work the image with the AI to refine the details to achieve what I truly want.Further more it would be nice to select multiple results and save them to a "selects" group then, hightlighting with marching ants or something, the prefered results in one image and move that over to another image. Effectivly combining all the preferd aspects of a variety of AI generated images.On the topic of refining results: We need the ability to add adendum or refining text to a result. For instance if the hero of the image is to close to the edge of the crop and needs to be centered to give it adiquite bleed area around the hero. Simply adding center hero add negative space around hero and center would all change this from being a novel

It would be amazing if you guys could have an option to convert the image (if it's graphic) to a vector format. I know there are programs to convert from jpeg or whatever format to a vector format but if it was included here, it would be incredible.

It would be really handy to be able to add a picture in the text to image Ai. This would help narrowing down the search

As a download format, I think it should be downloaded as ai format and the user should be allowed to rearrange

I would love to see an efffect that simulated embroidery patches on hats. I've tried the word prompts with the yarn and denim options and but can't quite get it to come out right. If there was a way to simulate the 3D puff embroidery that we would see on like basball or nfl tema logo hat.

Would love to have these options in text to image: Image rendering 4k/8k Cinematic lighting Volumetric lighting  And in text effects: Full colour wheel to choose from for background colour More font options And similar options as the text to image options.    

One of the most frustrating things about where a LOT of companies are going is to subscription based applications. I have a Mac Studio Ultra, M2 Ultra CPU, 128 GB Ram, Screaming fast SSDs...Yet, everyone wants to run their software in the 'cloud' (Clouds are not fuffy wonderful places, they are Sub-Zero, freezing miserable places, that it is very hard to get to, hard to stay there, expensive to get to.. and you don't own them... and they can blow away on a whim.  Which is why cloud computing is so well named...) I don't currently 'rent' software, so I stopped using Photoshop, and now use Pixamator and other applications that I can purchase, and run on my kicking fast hardware.  Something that *I* have control of, and if it stops working it would be because I upgraded the software/os and I can always go back to a backup using Time machine. I also have 4 TB of space to store the software, so no problems there.  Paying $50/month to use would price this out of

Right now the generations seems to all be follow the same overall look. Maybe adding a chaos parameter that allow the user to increase the level of variations is a good idea.