Feature Requests

What I miss the most in in Adobe Firefly is the option to use image to image.Now I am using Playground.com that makes that possible.That way you can for example create a modern painting of your own (whole) image.

Hi, I think it would be great if there was an option to only buy generative credits if you use up your number, some other programs have that as an option and it's a shame it's not here because I really like Firefly

Hello , quick Suggestion for the Text /AI  Generator , it would be cool for the Future to safe my own Text Promt Styles. So i have Custom Presets like in Photoshop ,when i use Text  or Shape Styles.

Jo, es wäre sehr nice, wenn man unterschiedliche fotos oder auch zeichnungen eingeben könnte, aus denen man einen eigenen bildstiel generieren kann um so fotos in Zeichnungen im selben stiel umwandeln könnte. Vielen Dank für all die bisherigen funktionen und einen guten Tag euch!

Hi,Recently, we wanted to use advanced Adobe Firefly Services, like Custom Models, Adobe Firefly API services, etc.  However, they are not available for VIPMP customers, only available for ETLA customers.It will be good to have also for VIPMP customers. References:https://developer.adobe.com/firefly-services/docs/guides/get-started/https://helpx.adobe.com/enterprise/using/assign-users-to-firefly-custom-models.html Best,Olaf 

SEARCH A PERTICULAR TYPE OF A BACKGROUND VIA IMAGE INPUT. THERE ARE SOO MANY CATAGARIES OF BACKGROUNDS AND EVERY USER DONT UNDERSTANDS HOW GENERATE FILL WORKS THATS WHY I SUJEST YOU.

I want to generate moodboards with this. Im actually trying to build that. Moodboards.ai

menus does not have background. is transparent tex, and  opens up to instea dto the side..been able to chose the seed of the render will be great

I do not like the popups of any kind that covers over content. there is plenty of space on top for notifications and options. screen realestate is critical for all developers. so i hit fav and now cant click share! because the popup is in the way.

visually pleasing but need to work on the details, not all elements are well organized and somehow it doesn't good well with complexities

i'm peeking and trying to understand how it works, but i already know right away its not very realistic, better try to make an AI for photoshop where i help photographers with good tools, i would make specific AI for portrait photographers, macro photographers and all kind of photography, that's not the right way people like to edit and use photoshop, because it's an institution in the world of photography, and you're in charge of saving it from these logarithms, you have to work with modern photographers and create a security system that check that the photo is taken by a person, who certifies it in the world of work and social networks

Hi Adobe Firefly team, I would like to share some feedback with you regarding the text to image generation feature in the photo generator. I have used many high-quality prompts for image creation, but I have noticed some issues with the characters generated by the system. Specifically, the textures of the face, eyes, hands, and other details are not well-defined. Additionally, I have noticed that some images are repeated.I would appreciate it if you could address these issues in future versions of the software. On a positive note, the colors are very natural and realistic, and the lighting is better than the mid-journey natural lighting.Thank you for your hard work on this feature. I believe that resolving these issues will make Adobe Firefly even more effective and successful after the beta version.I LOVE YOU.....

I'm not sure if someone else already wrote something like this but I had some weird stuff happening with the prompts I wrote. Like for example I would write "cheetah and bunny running together" and I would get a hybrid cheetah bunny or only a cheetah. I know Google uses punctuation marks so maybe it also can be used here?Like write: "cheetah" and "bunny" running together. So the 2 animals won't be merged in 1 weird animal?

It would be nice to have Firely have some sort of animal, fish, bird and insect image repository. Everytime I type in a specific ocean dwelling fish. It wants to put a tun a body on it. The animal and fish response is about 15% accurate in most cases. 

Bring more of the firefly features to photoshop. That's it 🙂

 

If you can allow to edit our image with out own idea looks great 

Create a new kind of file extension for AI-generated images to reduce the likelihood of facial images in the Internet.

would be great to be able to automatically apply a generated image as background or sky in a picture from lightroom

Replace the garbled text on generated images with proper word art and allow us to generate it separately like in the word art generator

Using AI recognition to be able to align certain elements to the canvas or to eachother would be beneficial for my workflow. If I have for example 100 images of people in different poses, and need to align their faces to the center of the canvas, that is a lot of eyeballing and manual work. However, with AI recognition I believe we should be able to do this now.Faces would be the obvious use case, but if it would be possible to customize this even further that would be spectacular. For example, typing in what to search a batch of images for, such as "XYZ Logo". 

Seria interessante ter uma opção para gerar um certificado ou comprovante que comprove que a imagem foi criada por I.A. Trabalho em uma empresa e produzo algumas imagens com figuras humanas. No entanto, existe o receio de que alguém possa se sentir parecido com uma dessas imagens geradas e acione a empresa judicialmente.Um certificado de geração por I.A. seria uma medida importante para resguardar a empresa em situações como essa.

With the new credit system implimented I think it would be benificial for users to recieve free credits for rating pictures. MidJourney does it and it works great. This would also be a great PR move that would help combat the sour reputation Adobe has recieved over the past few months.As of now I have no motivation to give my time for nothing, not now that I can do that with other image generation software. 

Good morning everyone, with Firefly I have created some really beautiful images. Even if I realize that it cannot be done for free, there should be the possibility of training your "firefly" with the language and syntax of each user in correspondence with an image. for example: an image that represents a dog, which we call dog.jpg and a txt file that I call dog.txt with the description of the image inside, so my firefly learns how a certain user thinks and writes. I am trying to do something similar in "lora trainer" but I can't get the same quality as Firefly. I use several generative AI tools, including lesser-known tools like Tydiffusion, but the image quality and result/prompt correspondence that I have with firefly I have not obtained with any other tool, can I send you the images created? Thanks for the time you have dedicated to me. Filippo

Download button for all images generated in favorites Filter and organization of images by category in favorites A dedicated page (without CC libraries) for images generated without linking to browser bookmarks Download the images with the prompt used as file name or a page to better administer images and their prompts with a grid interface, image info and date