Feature Requests

I'd love to be able to save my settings in Firefly as a preset so I can generate consistent images.

It would be nice if Firefly on the web had an option in the general settings to ‘Create in Illustrator extension SVG’.

Text to image is great, but slightly limiting. What if you added art-direction tools in order to help the AI and user sync better in the creation process?-You could have an add lighting tool (Where you can set the desired direction, intensity, number of lights, etc.)- A 3D "wood figure" to pose how you'd like the subjects pose to be- A pen tool with various modes to "sketch out" roughly what the AI can fill in after (like structure, figures, horizon line, pose, expressions - something to allow the artist and AI to synergize)- A textbox with bounding edges to further provided instruction into specific parts of the paintingAlso, the initial text to image could be a starting place - it would be fantastic if you could select the direction you're liking and then launch into the detail editor as described above. 

Creating a set of multiple images that differ only by specified features would be extremely valuable and efficient for myself and others working in the field of autism and early learning.  When teaching a learner to discriminate and identify a specific item or adjective, it can be a barrier if the stimuli differ too much. For example, 5 nearly identical images of a raccoon that differ only in the facial expression of the raccoon can better help the learner to identify adjectives (happy, sad, angry, tired, scared, surprised, etc.). 

Make it so you can upload a photo of someone and the ai can recreate the face onto other images the ai creates!

I was creating an image of a tiger in the ink setting and realized a fun idea. It would be interesting if a function could be selected to take the generated "liked" image and create associated animation panes. For example: I generated a pen drawing of a tiger standing by water, I liked the image and when I did, I was able to select "generate animation images". This would allow me to download all the related images and create a flipbook-type of animation. Thought it would be a cool idea 🙂  Thanks!  - kris

There could be a "frozen" effect. We already have "Fluffy" "Metal" "Underwater", but I belive a FROZEN one could be really used by creators.Greetings João Monteiro 

In Firefly it would be really cool if I could incorporate my business logo into Firefly. For example, if my coffeeshop was named Bob's Coffee Stop, my prompt could be: Man holding white disposable coffee cup, Bob's Coffee Stop logo on coffee sleeve, winter, sidewalk, happy, etc...

Adobe firefly is an awesome tool but we need more than generative AI.  for example, today I wanted to recolor the original windows 11 "bloom" wallpaper to purple. since it is blue but there wasn't such tool.  it would be a great tool to have. having such option to recolor images based on AI and its accuracy.  please consider adding such option.  

I like to design and sell device wallpapers. I'm interested in Adobe Firefly adding some more sizes and aspect ratios; like 9:16 ratio for phones and an Ultra-wide aspect ratio that's the size of two 16:9 screens side by side. Thoughts?

Some times it become difficult to achieve your goals with text to image what you really want. Why not directly suggesting the system by uploading your image, ang get similiar results with changing in ambience, colors, art type, it would be a combination of getting AI generated images with the help of "text and image to image", For example i have a really good photo art of boy studying on study table, and i want a little modification in its dress or want a girl instead, or changing in ambience of same photo,  but text to image is giving me really different things which i dont want. Another example may be auto generation of similiar images of uploaded image of class room with same teacher and class ambience.

Howdy, When using Text to Image, it would be nice to save your effect and image settings and pick up exactly where you left off in a later session. I'm working on a large fictional project with lots of AI generated images to help tell a story. I've found a combination of settings that deliver very good results and it's difficult recreating this if the web browser gets closed or computer restarted. I've now written all of my settings down so that I can recreate them. I've learned that the order in which they're applied also makes a difference. It'd be convienent to save settings for various projects. Thanks, Sean

Quero uma função de criar não só imagem, como vídeos também! 

Being able to generate AI capabilities to a uploaded photo or portrait through Lightroom and even more in-depth through photoshop while we brain storm adding techniques to video 

Enhance picture quality to 4k or help to make portraits of low quality images 

Enhance Creation an interactive tool where users can select elements like subjects, styles, colors, and emotions from drop-down menus. The tool then constructs a prompt based on these selections, which can be further customized.

Ce serait bien si on pouvait inclure un texte dans une image générée par l'AI. Pour l'instant, si on essaie d'inclure un texte, ou même un mot, celui-ci ne s'affiche jamais correctement.

My idea is to make a feature or option that will generate a logo from our prompt because now if we give a prompt to make a logo it makes a picture, not a logo 

In Firefly, it would be useful to have a feature that allows users to add or modify details using the same generative fill prompt or a modified version. This feature should also allow users to save their prompts and recall them for similar types of images. In other words, the prompt is the user's attempt to make a change and it should be saved within the program as a source for generating new AI generations and alterations. Additionally, the thumbnail showing the adjustment prompt used should be attached to the prompt. This thumbnail should be made available anytime in order to correct other images to similar results without requiring a search. It might be helpful to have a button that finds the appropriate prompt from the selected image. This way, users can recreate the image and fill in another, potentially different image.

Seems to me that the prompt would be a good thing to save as a separate file in order to reuse it ito create a different  but similar image generation. To me, it is the prompt is the brainwork that needs to be saved along with the image generated. This would allow the user to call it up again without having to save it to another outside application. An example might be saving it to a recall button.  Perhaps this could be useful as a resource for other Adobe applications. Not all images are saved as favorites. Therefore many propts are lost. Hope this makes sense.

自分の写真を使い、AIの画像にそのまま合成できるようにしてほしいです。

Es wäre nützlich wenn man Effekt Presets erstellen könnte. Am besten alle Einstellungen wie Modell, Seitenverhältnis, Struktur und Effekte, wenn möglich auch Referenzbilder mit inbegriffen, die man beim generieren natürlich dann anpassen kann.

Dear Adobe Team, I am a regular and satisfied user of your products, particularly Adobe Firefly, which offers excellent functionality for image generation. However, as a frequent user of this tool, I would like to suggest an enhancement that I believe could greatly improve its usefulness for a variety of users. My suggestion is straightforward: add the 2:3 aspect ratio format to the list of image generation options in Adobe Firefly. Currently, this option is available in Photoshop's resize formats, making it a common choice for users working on photo projects. The 2:3 format is widely used in photography, especially for standard print sizes such as 4x6 inches or 8x12 inches. Its addition to Adobe Firefly would enable users to easily create images in this format without having to go through additional resizing steps in other software. As an active user of Adobe Firefly, I firmly believe that this modification would bring significant added value to the tool and make u

creat an option to use maybe command + b to emphesis exacly what that you want to add or change 

i'd been trying to create images from historic figures of my country, but the IA doesn't recognize them, it would be cool if there might be an option to create an image based on the photo of a person, like midjourney.