Build better products with our product team
sarebbe utile stabilire il numero di soggetti nella scena, e definirne la caratteristiche
To whom this may concern, Thank you for the awesome and powerful features of Firefly. I have a suggestion for the 'generative fill' tool. It would be very helpful to be able to use an image as a reference. For example, I am editing a series of real estate photos and need the same accessories added to each photo so the room remains consistent. It would be of great help to be able to upload a sample of the accessory that should be added so each photo contains the same element. Thanks for taking the time to read this post and for considering the add-on.
Firefly no sigue las instrucciones de los prompt, necesito que me devuelvan los créditos porque el trabajo está mal hecho.
I think it could be fun to have a function that is like: you have a photo and you want to change thing without really losing things in the photo. like for example you have a photo of your dog and you want to cartoonify him
I've been using this website [link removed by moderator as per forum guidelines] but now I've hit the paywall. I already pay for Adobe so don't want another subscription. But this website works great for taking low-ish resolution images and upscaling the size and quality. I deal with a customer that sends me a lot of questionable quality images, and AI upscaling has worked wonders on them. Would be great to have it in Firefly. Thanks.
As a user, I would like to ensure consistent character portrayal in AI-generated images. If I define the features of a character 'A' in the first picture, I expect subsequent pictures to maintain the consistent facial and bodily resemblance of character 'A' throughout.
I'd love a clear and semi-prominent button that lets me go straight from the Text to Image page to the Favorites page. (If this button exists, I can't find it.)
My idea is that you can select the image you inserted and you have different types of settings, such as copy, cut, paste, etc... It would be great if you could change of shadowing, color, angle.. It would be great for many content creators that don't have the desired image, so they can adjust it as they like.
Upload own art that can be converted into the text
Hello there,I hope, team doing great, I was having a quick idea in my mind just after using the text-image prompt, i.e. you can create a section over for Logo and banner creation with practice of AI tool, as A.I. has a high scope and infinite scopes in creation and production of product.This idea will help business officials as well as big companies that invest hundreds and thousands of $$ in just creation of logos and banners, with help of Logo and banner creation section they will be able to generate there custom, self-satisfied logo on there own.Your' Truly,Utkarsh Kumar
It would be great if there was a way to put images that you use generative fill on into your favorites library so that you could continue to use the text to image feature on them. If there is already a way to do this, it would be much better if it were more clear. In many cases the image I am generative filling is something that has been generated via text to image, and I have already favorited it. However when I get done using generative fill, none of the changes I made are applied to the favorited image, and there is no way to favorite the new image. There is also no very clear way to take the new image and put it back into the text to image feature.
I'd love to see a tool to create infographics, graphs, and diagrams using prompts. For example, if we can generate a hierarchical diagram using a single prompt given that we provide necessary details to be added in each block. Sort of like creating a graph using MS Excel table, excet much advanced graphics and effects.
Dear Team,I propose that we should be able to create multiple poses of the uploaded image. This feature will greatly enhance the speed of our animation production process.Sincerely,Sonu
Suppose i got a picture of myself. I want to edit by text to image tool. It will be a very useful feature. Because users can modify their own pic as they want.
Creation of new content type for industrial design, logo design, fashion design, illustration based on the technical needs of these sectors. This could include full concept art, sketching, 3d modeling, moodboard. As well as ways to export in vector, 3d format, png
Once a user finds a particular image but would like to add to it or remove something. We should be able to edit that one particular image with generative AI
I raised this issue in a Roundtable Discussion but I thought I would include it here for posterity. (Also to see if we could get any upvotes.)It would be great if Firefly had tight(er) integration with Photoshop on the Web. I realize there are options to Copy and Save to library in the Share Menu. However, I think it would be ideal to have an "Open in Photoshop" option. When clicked it would open a new tab and push the Firefly image into the Ps Web GUI (creating an appropriately sized canvas). Please see attached mockup. I know there were some concerns about retaining the generative capabilities when moving the image to a new surface. However, I'm not sure that is as important. Just being able to move the image into Photoshop in one click would be useful. Then it could be conveniently generated, opened in Ps, edited, saved and shared for feedback with ease. Keeping this workflow within the Adobe Web ecosystem seems more convenient and retains Content Credentials along the entire path. Imagine workflows that begin in Firefly, images are moved to Photoshop Web for editing and then pushed to Adobe Express for layout and presentation design. I could see this being common (and popular).
- entourrer dans l'image de référence des zones pour indiquer a l'IA de quoi il s'agit, un peu à la facon photoshop.- avoir des zones dynamiques dans l'image générée (selection dynamique de photoshop) pour faire varier la sélection selon le prompt
I've been waiting for feedback for a long time and Adobe doesn't respond or give a position on a simple download button of all the generated images and in the browser's favorites. I have an Adobe CC subscription but I don't want to save one image at a time. Please listen to your payers and subscribers. The price is not cheap!!! Developers do not respond or give fair feedback on this. I'm tired!
• A search option for gallery.To sort required category based showcase.• A History of generated images.Come back and grab another one from the past. Thank you
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!
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.
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
Already have an account? Login
Enter your E-mail address. We'll send you an e-mail with instructions to reset your password.
Sorry, we're still checking this file's contents to make sure it's safe to download. Please try again in a few minutes.
OKSorry, our virus scanner detected that this file isn't safe to download.
OK