Feature Requests

Ter opção de editar a tradução em texto.

remove the prompt limit.

just having a comic thing in the options and a free like very free option for kids who jut wanna have fun making their imagination a reality

voglio interagire con firefly come chat gpt. dialogo con IA 

I would like to propose a powerful enhancement to Adobe’s AI image generation tools: the ability to attach and reference multiple images directly within the prompt using structured tags such as @image1, @image2, @image3, etc.Currently, when working with reference images, the connection between the prompt and the visual inputs can feel implicit and less controllable. By introducing a tagging system, users could explicitly map different parts of their prompt to specific reference images. For example:"Use the lighting style from @image1, the character pose from @image2, and the color palette from @image3."This approach would significantly improve clarity, control, and output quality. It allows the AI to better understand user intent by associating each visual reference with a precise instruction, rather than treating all uploaded images as a blended or ambiguous input.Platforms like Freepik and emerging AI tools have demonstrated that structured referencing enhances both usability and cre

Can we have the Firefly Board feature available on the mobile app version? Wondering if that will be a good mobile experience.

As a video editor/creative director, I am requesting the ability to upload a reference video (driving video) to control the motion of the generated AI output in the Kling model. The Goal: I want to upload a static character image (or image-to-video) and a separate video file that dictates the motion (e.g., a person walking, dancing, or gesturing).   The Feature Needed: A dedicated "Motion Reference" upload slot that extracts body dynamics, hand gestures, and facial expressions from the reference video and applies them to the generated character, similar to a "motion transfer" or simplified motion capture workflow.   Why this matters: Currently, text-to-video prompting is too imprecise for complex choreography or specific performance acting. A motion reference option would enable: Precise, believable physical movement. Consistent performance across multiple clips. A significant reduction in prompt editing time.  Workflow Example:Upload Character Image A. Upload Reference Video B (pers

新しい画像生成の際に前の履歴の続きから始まるようになってしまったので、使いにくい。前の履歴は引き続き履歴から再開できるので、新規作成の際はまっさらなルームを用意してほしい。毎回クリアして新しい生成物を作るのは面倒。[Adobe Fireflyへ移動しました：モデレーター]

Here’s an example:I want to see images that other users have created of line drawings for tattoo designs so that I can use the same settings and prompts that they used to create my own version with different subject matter so that I can hand my artist a line drawing and have him use his own creativity to color it.With no search feature in the gallery, I am forced to endlessly scroll through user created images hoping to find something that comes close to what I was thinking.A gallery search based on keywords used in the creator’s prompt would help tremendously!! Thank you for your consideration.

Ich erstelle einen digitalen Reisebericht über die Bretagne. Dabei sollen Videos vertont werden. Jetzt habe ich das Problem, dass französische Namen nicht korrekt ausgesprochen werden. Eine Möglichkeit wäre, wenn Firefly “Sprache zu Text” die internationale Lautschrift “IPA” unterstützen würde. Tut sie scheinbar nicht. Habe ich da eine Möglichkeit von Firefly übersehen oder kann es das tatsächlich nicht? Wenn es nicht möglich ist, wäre interessant zu erfahren, ob es in naher Zukunft implementiert wird.

I often download multiple separate assets from my boards but they end up being name “project file name 1”“project file name 2” adding this extra step to rename files is unnecessary friction so a rename option at the point of export would be really helpful

Save as jpeg as a choice instead of just png - my clients want jpeg - would save me a conversion step

daha uzun promt yazabilme seçeneği nano banana veya diğer harici modeller için yetersiz oluyor

I swear you have no idea how to build controls for AI for video. You have to have multiple key frames, you need inbetweening of frames, for both video and images. You need to define locations/backgrounds, props, actors, camera, and lighting on a stage. Then manipulate the props, actors, and camera to hit the beats. I made amazing videos for free, but once we started paying, less than 1% is even close to usable. Backgrounds are grainy, they fade in and out, people disappear, walk through furniture or morph into objects. 0 consistency. You build APPs and UIs as if you have never created an image, animation, or video before.  Everything works like an off-brand videogame, not a real tool.  It needs to be simple to make what you want with repeatable consistency.  I have been building in 3d cad, creating keyframes for products, and it works great on the first try, but the next 1000 tries are crap. You need to throw everything out and start over. You are not thinking of users, you are not thi

Suppose I type out a prompt and attach a reference image and hit “Generate”. But I realize I used the wrong image for the reference, It would be really useful to have a stop/cancel generation button so I don’t lose precious credits over a mistake. This stop/cancel can be a “X” icon button when the image is still generating. 

Though Adobe Firefly has a long way to go, it’s “Firefly Image 4” model actually yields pretty decent results (if prompted correctly), so I use it often. Unlike the other models, it outputs four pics instead of just one. I would click on any of the four pics, and it would take me to the “Edit” page, where I could quickly navigate through those pics, using the navigational arrows that USED to be there.. However, at some point in Firefly’s update history, they decided that we didn’t need these navigational arrows.🤦🏽WTF, ADOBE - PUT THE NAVIGATIONAL ARROWS BACK. What tf is wrong with your UX team?? Which one of y’all decided that we no longer needed navigational arrows???? I am truly baffled. I honestly don’t understand how ANYBODY thought this was a good idea.  This might not seem like a big deal, but for me, it absolutely is, because “workflow” is important when I’m creating, and there is nothing more aggravating than software that INTERRUPTS my workflow, rather than aiding or enhanci

Can search for the type of images you want to generate, and then use the prompts of these images as templates to generate your own images. This makes Firefly a more efficient tool for generating AI-generated images, essentially an AI version of Stock.

I would love to be able to use the film impact transitions as effects, example would be glitch or kaleidoscope. I know of a few tricks to kind of make that work by using adjustment layers and splitting them in half and pulling the handles past the clip beneath, but please tell the devs we would all love to use those transition effects as actual effects.  If you guys can make this happen I promise to be your best friend. Thanks.

Thank you for your continued support. I would like to have a chat history feature for Firefly and an image export function. Also, I would like a feature that allows me to select and use multiple models with a single prompt submission, making it easy to compare the generation results from each model.

please add 4K resolution to Nano banana pro model

I would love to see an integration between Adobe Firefly and OpenClaw to allow creators to send prompts, generated images, or assets directly between the two platforms. This would make it easier to incorporate Firefly-generated visuals into automated workflows and AI-driven creative tools. For example, creators could generate images in Firefly and automatically send them to OpenClaw for further processing, automation, or integration into other creative pipelines. This would help creators build more advanced AI-assisted workflows while keeping Adobe Firefly at the center of the creative process.

Here is my idea….Feature Request: Allow Uploading a PDF/DOCX as Structured Instructions for FireflySummaryToday, Firefly prompts are constrained to a relatively short text length (community and staff discussions have historically referenced ~1,000 characters, with users sometimes encountering lower effective limits depending on the model or surface). This makes it hard to use Firefly’s recommended, structured instructions without aggressive pruning—reducing clarity and, ultimately, output quality. What I’m asking forPlease add a capability to attach a reference document (PDF or DOCX) to a generation request so Firefly can read and follow a structured instruction sheet in addition to a short prompt. This mirrors the research-and-attach flow I use elsewhere (e.g., Copilot scenarios where I attach a brief or template), and would let the short prompt act as a high‑level instruction while the document carries the detailed guidance.Why this mattersStructured prompts drive better results. Ado

Dear Adobe team,If you have truly decided to focus on the AI segment and are no longer giving the same level of attention to Illustrator, XD, and other products, then please make Firefly’s interface genuinely convenient and professional.In my view, what you need most right now is a proper canvas-based editor with a node system. That would be a far more powerful and logical format for working with generative tools. As a reference, Weavy is a very good example of this kind of approach.In your case, however, this should not be just another web service — it should be a full desktop application deeply integrated into the Adobe ecosystem. Most importantly, it should allow generated results to be passed easily into After Effects, Photoshop, and Illustrator, creating the kind of seamless workflow that users expect from Adobe products.If you build it this way, you could end up with a truly outstanding product for professionals. And for users, it would mean being able to stay within a single eco

I'd wish you could upload existing video clips to Firefly so you could add camera motion to shots. For example, adding a dolly zoom or a camera spin to a locked off shot.I’d like to be able to add difficult to execute camera motion to the footage I shot. So if I have a locked off shot of someone standing in a kitchen holding the snack product I am creating a video for, I would like to be able to use AI to add dramatic camera motion to the otherwise boring shot. I’d like to be able to add camera movements like a dolly zoom as the person takes a bite, or add a camera spin around the person as they enjoy the snack.

need to be able to cancel a generate.