Feature Requests

Sarebbe bello avere un tools per rigenerare e restaurare vecchie foto.Anche rendere le foto binaco e nero a colori.

The text is always too dim and cant barely use it in dark backgrounds. I would like to be able to generate text with bright colors.

It will be great if we can submit an image from our own collection to be used in the graphic generation process.

It would be interesting to animate a PNG or Jpeg logo with FireFly. Imagine a one colored or Duo colored logo that would "melt", "bounce", "crystalize", or "explode into frame" by uploading this PNG or JPEG and the generative AI would handle the keyframes allowing the user to export a 1 ~ 2 second animation of their logo. Nice idea 😉

As we are scrolling through the photo settings, hovering of over the drag handles shows a sample photo. What i noticed was that the photo changes based on where the drag handle is along the slider.An animated GIF showing the effects based on drag handle position in lieu of static photos might be better.

It's great to be able to match an AI-gen image to a particular style using an example that has been uploaded.  What would really be helpful is to be able to upload my own image/design/illustration as the base, and then have that match the style of another image, so that I could basically reskin the work I've done for a different look. For example, if I design a character that is vector-based line art, I would upload it to Firefly. Then I could upload an image of an oil painting, and Firefly would reskin the vector drawing I did to match the look of the oil painting. Or I could upload an inked graphic novel illustration and my art would match that style. This would be extremely valuable in quickly exploring and determining the right style for a series or a campaign. Is this possible now or in the works? Thanks!

Ótimo programa muito bom, só poderia arrumar uma coisa, quando salvamos a imagem editada ela perde a qualidade.

Most of the time the positioning of my main subject is not where i want it. Mostly it is to much zoomed in, it would be nice to keep the generated images with a simple option to zoom in and out, additionally move left, right up and down. That way we have more control over the image.

Being able to re-draw an image in a different style (specified in the prompt). This would enable users to see what their image looks like with a different aesthetic. For example, if I have created (or taken) a photograph of a fairground carousel, and wanted to see what it looked like at night, or as a woodblock print, or in a cyber-punk dystopia, that would be very useful.

Sehr geehrtes Adobe Team, ich würde mir sehr wünschen wenn man mit einem Text, sich mehrere Bilder erstellen lassen kann, dann die Bilder auswählen kann und sie zu einem kurzen Video erstellen lassen kann. Die KI soll dabei zwischen den Bilder einen sanften übergang erstellen das es so aussieht als würde das bild sich nur verändern und nicht mehr aussieht als wären es mehrer Bilder an einander gereiht.   Mfg   [Removed by Mod]

It would be helpful to have the option to generate one image instead of four, especially in the beginning while you are still finding your way. This way you can get directions on your idea quicker and it will put less strain on the servers.

Firefly focuses on generative content that has AI creating the design of the subject content or creating art. What would be most helpful to me is AI that structures a file layout I can open in AI and I can then proceed to artistically complete using my own ideas and style. What would save me time is layout and format designs, AI generated shapes, AI generated layout options predesigned. For example, "design a layout for a four page brochure in InDesign that reflects the layout of a 1920's newspaper". In this prompt example, I would fill the content, the colors, the images etc. It would save me much time for AI to create a bunch of layouts to pick from as a starting point. 

I would like to be able to see my previous creations and the prompts i used to make them. thank you

Could you add a suggested prompt for creating images in a toggle button.

when usuing text effects i would love to be able to keep one letter from one choice and a differnt one from a second choice becasue a lot of times the ai makes some letters better then othersit would help me get the vision i have much faster and sometimes one letter always looks off to me in all the variations 

Please improve the model so it can create realistic and accurate animals and plant images in different styles like Botanical Illustrations, Illustrative, Digital Art etc.So far its an amazing product, I really like the UI/UX and can't wait to see the new improved models, keep up the good work!

Maby a way that users can learn to be better in search so they can fill out mutch as posible to even get better images

Would love to be able to change the color of an item in a photo.  Is that possible? 

I have an Idea for the Adobe team to add photo unblur and quality enhancer into Adobe Firefly. 

image to image generation

We can Update the Heart Image Generated every time with Reload of the page  Change Required:-As this image of  Flowing liquid  from the heart & this texture would be uncomfortable for hemophobic  as it resembles Flowing blood from Organ  

2 photos editing where they are named as fire pic and fly pic.... Both has different colour brush and can be command to AI to exchange cloths or swipe face or exchange things or merge together... Many possibilities 

make it an app

it would be cool if there was a way to tell firefly to make a graphic with a specific background color like "navy background"

Hello Guys.  While using Firefly I found it quite limiting that the AI is not generating images corresponding to brand items. For instance, when I ask Midjourney to generate a  "Jordan 4 Shoe, floating in the air, 3D style, hyperrealistic " Midjourney will generate a Jordan 4 shoe taking the same model and applying the details. When we ask Firefly to do the same the results are yes shoe floating in the air but nothing related to Jordan 4. I thought it would be good to get to that level of detail as it is a need. Many thanks for considering this idea.