Questions

You want me to pay, even thpough you do not follow my prompts? That is insane. Images generated do not respond to details written into the prompts. Requests for specific changes are ignored, with pretty much the same image being regenerated, or, worse–the prompt is igmmored entirely. A waste of time. 

The interface requires significant improvements. Currently, there is a lack of transparency regarding the number of credits used, and no functionality allows users to define how they want to allocate credits for each generation. This absence of control is a major issue. Additionally, the interface is confusing when it comes to demonstrating the expected results based on user-configured parameters, making predictability and usability challenging.Another critical point is the lack of consistency in the tools maintaining standards. Sometimes they work one way, and other times, entirely differently. This inconsistency renders the tool unsuitable for professional use and undermines trust in its reliability. Without consistent results, it’s impossible to depend on the tool for professional applications.In its current state, the experience of every attempt produces unpredictable results. Imagine if Photoshop behaved similarly, delivering different outcomes every time the same feature was used

I’ve been spending a lot of time experimenting with Adobe Firefly recently, and while I’m getting some great results, I’m still trying to understand the best way to consistently improve image quality, realism, and fine details in the outputs. I thought I’d share what I’ve noticed so far and also ask for suggestions from others who have more experience.One thing I’ve observed is that Firefly responds very strongly to specific adjectives. Simple prompts give decent results, but when I add more descriptive details like lighting style, mood, texture, composition, or camera angle, the images become noticeably better. However, there are times when the model still softens small elements like hair, text, reflections, or background structures.I’ve also tried guiding the output by using different styles such as “photo-realistic,” “cinematic lighting,” and “high detail,” but sometimes the results shift too far into an artistic look instead of natural realism. I’m curious whether there’s a reliabl

I am trying to get used to firefly after not having used it for about a year and a half and it is honestly astounding how bad it is considering how far generative AI has come elsewhere. Firefly has infact gone backwards it seems, as now, constantly and arbitrarily it refuses to generate something for breaking its completely nonsensical guidelines, for example, trying to generate something of a fantasy image - it will constantly block generation of anything deemed 'menacing' or 'threatening', then randomly allow it, if someone is paying this much a for image creation software, you would assume it would be less restrictive than the countless free alternatives out there that can even run without connection to the internet. Secondly I could've sworn it was far more intelligent when it comes to using generative fill to normalise an element of larger compositon, i.e created a background and foreground then selecting forground elements and either typing nothing into the generative fill prompt

HolaI noticed that in the Adobe Firefly they have a "new" section where you can buy tokens to use Ffireffly.I'm a suscriber to the whole Adobe Suite.Do I have to pay to use it?Thanks

Dear Adobe Firefly Team,I’ve experienced low success rates with the generative fill feature, using 89 of my 125 credits without achieving desired results. This process can be frustrating and costly. I suggest charging credits only for generations that users decide to keep, which could also aid in improving your model based on successful generations.Thank you for considering this feedback.

Firefly is absolutely awful. It should be renamed 'Mutation' as that's what I get with every image it generates.

Being able to compare all the major models to Firefly ie image and Video generation one sees just how behind and primitive Adobe Firefly is. Same or roughly the same prompts on Firefly and Veo for example yield ridiculous and useless results on Firefly. At least this promo has showed that there are much better options on other apps. To use generative AI as anything other than a novelty item takes a lot of learning and discipline. Adobe Firefly is useless and maddening producing so much unusable garbage. Also as an aside the guidlines have flagged and refused to generate the most ridiculous things. How did the largest image and video software in the world make such a useless product? Do better. Also if you want to make your product ultimately useful you need to make an unlimited flat rate option or at least a "relaxed rate" like Runway and others have. Maybe it's my prompts but they seem to work on the other models.

Not really a bug, but I dont know what else to put it under. Firefly ignores most of my prompt and gives me simple low quality images that dont even make sense. I describe what I want with great detail and its frustrating that it ignores what I want and gives me random stuff. I heard great things about Firefly but so far it has beyond disappointing.

I looked at my Firefly generation history today and it seems that some of my past generations have dropped off my page. Looking at the Firefly help page (below), there isn’t anything about when this functionality began (so how far in the past you can expect to see) and if there are any limitations (maximum amount of content available).https://helpx.adobe.com/au/firefly/web/access-your-files/view-generation-history.htmlWith my history page, I am wondering if there is a problem on my side or if it is a Firefly history limitation.On a side but related thing, in the early days of Firefly, you could create a shareable link to your generated images. I did this and saved those URLs, Now if I go to those URLs, the pages are no longer available with a ‘Page does not exist, Check the URL and try again’ message. An example is:https://firefly.adobe.com/shared/texttoimage?id=urn%3Aaaid%3Asc%3AAP%3Ada0cb0b0-0ef2-4d89-a6a7-ddb606ff96c4So to confirm my questions:Is the generation history supposed to b

So I bought a month, I expect / need to be able to tell what I'm being charged for and how many credits are remaining. Where is it, I must be missing it???   Thanks

Hi, newbie here and I did what I always so, jump in with both feet first into the generate image space. I am having a hard time maintaining background continuity. I thought I was getting the hang of it until I got to my last image. I couldn’t get the exact match for the background as I did with the other ones. I tossed the file because that’s what I do. 🤷 Is there a prompt that I can use to make sure that the background for this last image to match the background of this one? Am I in the wrong section. I will go back and look over the tutorials. Promise.  

https://firefly.adobe.com/generate/images?id=0a11c3ae-bf45-4e9d-b2aa-24cbc843a81eEstou usando o modelo de geração de imagem através de text e ele não permite que eu utilize na minha conta mesmo possuindo 4000 créditos. [PII redacted by Mod]

Vocês podem verificar esse problema na geração de imagens ou infelizmente precisarei cancelar o serviço e pedir estorno, pois foi cobrado ontem, 17.07.2026, e se for para não ser utilizado, eu cancelo. O problema de geração de imagem é tecnico do site de vocês!!!Já testei em outros navegadores.Agora é com vocês, resolvam. Preciso trabalhar!!!

I asked to create a video but the one I received contained many grammatical error. why should I be charged 500 credit to correct them 

"I am unable to cancel my Firefly plan because my account shows a billing issue and the Cancel Plan option is locked. Please cancel my subscription without charging any further amount."

Я згенерував одне відео і після цього виникає помилка "недоступно у вашому регіоні"

i am simply trying to get text to flow from one set of text to the next in a video and it’s jumbling up all the words together making it unreadable

I asked it to make a VERTICAL video 3 times and it used my credits to make it horizontal. How do I get my credits back. 

I can normally add up to 6 images to create an image.  that feature is miising

Quand je clique sur generer une vido, la page ne prend plus aucune commande et reste bloquée

I tried to use the bulk option to remove the background from images. Instead of getting a transparent background, I got the exact same pics and the background was exactly the same.

I am trying to generate voice on firefly… it charges me credits (I have 7000+) but does not generate and says contact support. I am not generating video.

I'm an same issue using Kling 3.0. I've tried multiple times across multiple days and no luck. I don’t want to be forced to use my credits differently. Is there a fix? 

firefly failed to create an image, but still uses the credits