Feature Requests

Also in Adobe Firefly: es werden bei jedem Durchlauf 5 Credits abgezogen, und auch nach 5 Minuten warten kein einziges Bild erstellt, die Fenster bleiben grau und die Erstellung läuft in Schleife. Drei Durchläufe getestet 15 Credits wurden abgezogen- kein Bild wurde erstellt.

how to remove favorite image in Text to Image from my favorite?

Hi, ich entschuldige mich im Voraus, falls diese Frage schonmal aufgetaucht ist. Per Direktsuche habe ich leider nichts gefunden. Ich habe vor eine Kindergeschichte zu bebildern und. Die Geschichte dreht sich um meinen Sohn. Das klappt mit Firefly sehr gut - ein Referenzbild meines Sohnes, ein bisschen Beschreibung und ein kleiner gezeichneter Junge sieht ihm ähnlich und tut was ich schrieb. Top! Aber jetzt habe ich EIN Bild davon. Wenn ich das nächste Bild formulieren möchte, kommt ein ähnlicher Junge mit einem ähnlichen Kostüm. Aber ich brauche ja GENAU DEN GLEICHEN Jungen. Es hilft leider auch nichts, das erste Bild als Referenz für Stil oder Komposition oder für alles einzustellen - die Bilder sind alle komplett unterschiedlich. Daher meine Frage: Wie kann ich eine Reihe von KI-generierten Bildern erreichen, die EXAKT das gleiche Motiv nur in unterschiedlichen Szenarien zeigt. Weiß das jemand? Ganz liebe Grüße!Adrian

和製英語や、日本固有の物の単語にもしっかり対応してもらいたい。あと、作画？がテイストがアメコミやアメリカンな感じが抜けきれない。

please add zoom to Adobe Firefly. it is really difficult to fix little items without zoom

Lack of history of all images generated is shame, now im searching in chaotic way by moving back with browser 'previous page' button... We should be able to see in nice way when what was generated. Cand find all my upscaled photos. Shame as f*... Or maybe im missing smthn

Generate SVGs

Die Bilder hängen voneinander ab. Somit ist es schwierig nach einem anfänglichen Fehler noch die Kurve zu kratzen. Zudem ist ein löschen des Verlaufes nicht möglich.

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.

Hello Adobe, Why isn't there a link to launch the Firefly app right on the "All Apps" home page when I log into my Adobe account?  This is frustrating not having an integrated way to launch Firefly when I log into my Adobe account.This seems like a missed opportunity for users, would be a great integration and doesn't make sense that it's not there. Thanks,Joe 

And i dont know how to upgrade 

I think it would be great to improve how letters and numbers are processed so they can better match detailed, custom designs created by the user. The goal isn’t to mimic licensed material but to allow people to bring their own unique ideas to life with better precision. This would make it easier to include finer details like custom curves, spacing, or alignment, giving users more flexibility to create something their own

When a violation of the guideline tail is detected, the ability to suggest alternative words that are less likely to violate the guideline would make it easier for users to handle.

FYI: I needed a realistic image of pre-historic paintings on a cave wall and the results were far from realistic which I imagine mean there needs to be more of this added to the data base.

I noticed that if the prompt is short when you generate an image, it will append a series of numbers at the end. However, this number gets cut off if the prompt is too long. Is there a way you guys could make it either put the full prompt and number without cutting it off, or a truncated filename with the number? File management gets combersome when you have files with (1), (2), etc at the end . Thanks!

Warum kann man die Stilstärke nur in 3 Stufen einstellen, warum nicht stufenlos, ebenso bei der Komposition?

Eine KI-gestützte Textunterstützung für Prompts, die es ermöglicht, Ideen detailreicher und ergänzend auszuschmücken. Diese Funktion sollte ein- und ausschaltbar sein. Der Nutzer gibt einen Text ein, und die KI bietet Vorschläge zur Erweiterung an, ergänzt Sätze oder fügt ganze Absätze hinzu, basierend auf inhaltlichen Vorschlägen, die aus Stichwörtern abgeleitet sind. Diese Funktion sollte individuell anpassbar sein. So meine grob umrissene Idee. Zusätzlich wäre es hilfreich, den Originalprompt bei Adobe Firefly zusammen mit den generierten Bildern in einer Datenbank zu speichern. Ich freue mich über weitere Vorschläge!

The upscale feature in Firefly has been critical since the initial images it creates are fairly low resolution.  However, the upscale feature only seems available to current work open on Firefly. I'm wondering if there is a way to use your upscale credits for images you created with Firefly in a past session? This is necessary for my work flow as a graphic designer. For example, I had a few Firefly-created images downloaded and had to run the different versions by my boss. Now, the final image has been approved, but it's too low res to use. The tab I was working on closed and I can't seem to access past creations. I am hoping to be able to drop my Firefly-creation back into the app and use my credits to upscale it. Is this possible? Thank you so much!

Sería genial que pudiéramos retroalimentar en el chat lo que queremos que la AI haga para nosotros, de modo que podamos enseñar a la AI la manera en que nosotros seguimos ciertas instrucciones, para conseguir el objetivo de diseño. Por ejemplo, poder explicarle conceptos sobre un tipo de dibujo y que esta logre comprender de forma básica los fundamentos especiales para completar nuestro diseño. Otro ejemplo es, si quisiera corregir un error que cometió la AI, quisiera poder señalárselo inmediatamente de forma que la retroalimentación sea tal cual. Poder enseñar a la AI a tener estrictamente los parametros que le quiero imponer, ayudaría bastante a optimizar las tareas de los jugadores y demás clientes. 

In real life, the number of times a pro is going to take a Firefly-generated image and use it as-is are vanishingly small. You can have happy surprises, something I refer to as "controlled serendipity," but of all the images I've ever generated in Firefly, only two were good enough to stand on their own. (Photography is the same way: You start with an idea, and you get as close as you can at the time of capture, but even in the studio there's almost always some adjustment in post-production, even if it's as simple as cropping or adding a vignette.)   Straight text-to-image is so limited that it's almost never fun. Either it takes fifteen tries before Firefly comes up with something cool, or there's an image that's this close but the exposure is off, or there are some of those weird artifacts we know so well, or the composition sucks. You're at the mercy of whatever mood Firefly is in today (and it does have moods, let's face it).   "Challenge" is a bit of a misnomer. The

Firefly is in need of a context buffer that will allow the continuation of a prompt without having to inject a modified full prompt every time. This is completely doable in LLM architectures, a routine in text generators like ChatGPT, Copilot, or Llama, and it ties in with the repeatability problem, whereby we can't generate multiple images of the same house/car/character, but are always presented with a random variation on the theme.   Firefly would become genuinely useful if it could retain an image and execute minor edits on it via text input.   As an example:"A cartoon mouse with black ears and nose wearing white gloves and red pants." [Firefly generates an image] "Make the ears rounder." {Firefly modifies the selected image.] "How about blue pants?" etc.

I am fat and hairy and want to generate an avatar that looks like me. In Firefly Image 3, I have been able to generate images with composition similar to what I want, but when I try to use those images as composition references and make the image fat and hairy instead of a muscly jock with a 6-pack, I get an error that my prompt goes against user guidelines. Being fat and hairy is not hateful or negative, it is descriptive.

It would be good to have the option to save as a JPG, if possible

I'm currently working on a customer journey for a presentation and would love to use Firefly to illustrate various product use cases. However, I'm finding it challenging because the AI's current capabilities are somewhat limited in terms of creativity. One issue I've noticed is that when I specify a prompt with the name of an object, the AI only generates it in a standard upright position. For example, even when I enter a prompt like "an overturned chair," it only produces a chair with all four legs neatly on the ground. To create more dynamic scenes, it's important for both people and objects to exhibit movement. It would be great if an update could enable the AI to understand not only the relationship between words and objects but also the posture and context in which these objects are placed. In the future, I hope to be able to input prompts like "a man who climbed onto a chair to reach a can on a high shelf and accidentally fell" and get images of a man sitting on th

Since your company is Adobe, I find it strange that in Firefly you don't allow image to image in generating an AI image. It is a very useful tool.