Feature Requests

Please allow neutral identity-related words, such as “gay”, to be used in prompts without automatically blocking or stopping image generation.The moderation system should consider the full context of a prompt rather than treating certain identity-related words as inherently sexual, explicit, or unsafe. For example, prompts describing a gay couple, gay characters, LGBTQ+ history, Pride events, or inclusive branding should be allowed when the requested content complies with the platform’s policies.I experienced this problem while using the Boards feature to create a logo for my project, The Gayest Tarot Ever. I attempted to use the available logo presets to generate and explore different logo iterations, but the generation was stopped because the project name contained the word “Gayest”.The request was solely for graphic design and branding. It did not contain sexual, explicit, harmful, or otherwise restricted content. However, I was unable to use the logo iteration presets as intended b

$$.  I’d like to make month to month bill tracker for people who’s memory or need to have it written down to help them understand and keep track of there bills and where there money is going 

Criador de falas não tem disponibilizado a versão em português do Brasil.

Provide a variety of Aspect Ration selections for the generation of GPT 2.0 images

No nosso plano empresarial, não vem com o modelo Adobe Graph em português. Eu gostaria de saber o porquê não estar incluso.

Hi Adobe Team, I wanted to take a moment to share some honest feedback regarding Adobe Firefly’s image generation tool. Unfortunately, my recent experience has been quite disappointing. The overall quality, realism, and accuracy of the generated images fall far short of what I’ve come to expect from Adobe’s usually excellent creative tools. The results are often inconsistent, distorted, or poorly composed, even when prompts are clear and detailed. Compared to other platforms, Firefly’s current outputs feel unpolished and not suitable for professional or client-facing work. I’m a long-time Adobe user and genuinely want Firefly to succeed — it has so much potential. However, at this stage, it’s difficult to justify using it in a professional workflow. I’d love to see improvements in image quality, realism, lighting control, and prompt interpretation in future updates.Thank you for taking this feedback seriously — I know Adobe values user input, and I hope these concerns he

I would like to provide some constructive feedback regarding the current workflow for generating AI videos in Adobe Firefly. I am a regular user of Adobe products and have always appreciated the quality and innovation you bring to creative tools. However, the way Firefly handles credit usage for video generation is causing significant frustration—not just for me, but for many users raising similar concerns.At the moment, Firefly requires users to spend credits before they can see what the generated AI video looks like. This means we are asked to pay in advance without knowing whether the end result will be usable, relevant, or even close to what we requested.To put it simply, this feels like being asked to buy a car without knowing what model, colour, or condition it will arrive in. The outcome can vary widely, and there is no opportunity to judge quality before credits are consumed.While I understand that AI generation has inherent costs, this approach creates a very real risk:Adobe m

ao tentar gerar imagens no firefly da erro tente novamente mais tarde.. as ias tambem não funcionam no photoshop, aparece mensagem: o serviço está indisponivel no momento, tente mais tarde 

Sehr geehrte Damen und Herren,ich habe gerade ein Bild mit dem Prompt “Ein Schwarzspecht mit wunderbar freigestelltem Hintergrund, der etwas Besonderes macht bzw. sich in einer besonderen Pose befindet, z.B. beim Füttern des Nachwuchs” generiert, das ich gerne weiter verwenden würde. Bitte bestätigen Sie mir, dass das generierte Bild frei von rechten Dritter ist und weisen Sie mir die Quellen nach, auf deren Basis dieses Bild generiert wurde. Vielen Dank!

Dear Adobe, My general idea would be something very simple, that would make the generative fill even more fun and helpful, is to have an option of "Something like this" Where we can upload some picture, how we would "Imagine" our photo to look like, then of course the AI and the Adobe Firefly could generate something like that.  That would save a lot of time, also would help a lot for creators.  Thank youAttila Nagy

With this designers don't have to go to a new place to use the A.I functionalities 

I'd like to save an image that i edited using the Generative Fill tool to my Favorites since i don't always want to download them. That way, I can continue editing the image at a later point

Please have favorites somewhere we can access while generating image or changing backgrounds. Having to go out to the top level menu to get to them is inconvenient. This is important as we try and get similar images of the same style. 

Make it. Better because not able edith and not able smoot face editing should also done by aiMake ai like this that I can edit video of US

Basically a img2img feature would be nice, to get paintings of photographs etc

streamline tasks and improve the outcome of my work

My idea is that Generative Fill is provided with Text to Image style options to get the ideal background.

Hi there, Great addition would be to have an option to remove a background and specify to remove a spill of color or how hard should cutout be. Many Thanks

Viewing and evaluating files in the history window in Firefly is a nightmare. I've only been working on the project for two weeks, and I'm already having trouble evaluating the content of the generated files. See how it's organized on leonardo.ai.

I recently encountered the generic “Something went wrong. Please try again later.” error in Adobe Firefly. I noticed that several users have reported the same message in the community, but the interface does not provide any useful information about what actually caused the error.In my case, the problem was that the prompt exceeded the 1,000-character limit. I only discovered this by opening the browser’s Developer Tools, checking the Network tab, and inspecting the response from the generate-async request. The API returned the following validation message: “Validation error for field ‘prompt’: String should have at most 1000 characters.”After reducing the prompt length, the request worked. Adobe Firefly should display a clear validation message or a character counter before submitting the request, instead of showing a generic error. This would save users a lot of time and make the issue much easier to diagnose. For anyone experiencing the same generic error, checking whether the prompt

Seedence 2.0 keeps showing "I don't have permission to access" when I add video and image references, even though I have 4000 points.

There isn't enough characters available in Firefly prompts using nano banana. Please increase to at least 5000 characters.I run out of characters to accurately describe the image I’m trying to generate. 

Para este modelo que es muy creativo, 1800 caracteres es limitar la creatividad del modelo, es lo suficientemente inteligente para leer y realizar escenas complejas, mínimo pondría 2200 caracteres. Gracias!Lourdes @iapulse

A song creator that makes custom backing tracks from audio and text prompts. You can choose style, tempo, genre. You can choose a voice to sing it, or just use your own. Add a recording and it makes a track for that song. Add lyrics and it makes a song from it. You can even give an idea and let it do the rest. There’s also a stem splitter and vocal remover. You can even use third-party models like Suno.

I would need a presentation mode in Boards to show my work to my boss without having to show my browser tabs or anything. Simple presentation. Maybe also a Zoom-Tool, to circle certain areas to quickly zoom into specific topics. Like a Mindmap i’d like to have clusters of information, to which i can quickly refer via zoom areas within a presentation mode.