Feature Requests

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 

Please add the option to choose the resolution of generated images. Currently, when I generate images using this application, I receive images with a fixed resolution. However, different use cases may require different image resolutions. For example, if I want to generate thumbnails or print-quality images, I may need different resolutions depending on my specific needs.

I lose too many credits doing trial and error. The monthly cost should be based on downloads

A cancel option to stop a generation before it completes, especially for those that use credits. Sometimes the button is hit too early by accident, or the wrong model is chosen, or some thing is incorrect in the prompt but its not caught until the generation starts. Would be nice to not have to waste credits on an useless generation.

Let's say I wanted to storyboard a script and produce different angles of the same thing. It would be nice to have something that holds on to the core look and objects within the frame so we can get a wide, medium , and close shot of the same scene.

When I try to generate a movie and I’m adding first and last frame the movie doesn’t see this frames and makes movie by own idea, not on my pictures. 

In the text to image part, I didn't find a place to cancel prompts like in stable diffusion. Often we have artifacts with double faces or eyes in the wrong places. It depends on the channels I think but it could be efficient and necessary to add this function. Or maybe add a basic lexicon for prompts if we have to use No in front of cancels or others basic operations.   Thank you for your job, im a teacher and i think you are the best to create an democratic useful app for commons users   Eric

Allow for feedback so parameters can be modified or at least HIJT can make changes. Allow for the interruption/termination of a generation.

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

Estou tentando gerar imagens usando referência e prompt, porém fica dando erro atras de erro no sistema.   

Occasionally Firefly will generate a video that isn’t remotely close to what I want or need. It would be nice to delete those from my history, but I go around and around trying to figure out how to delete the generated image/video. It should be MUCH easier. 

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

It would be great if we could upload a brand book / branding guidelines to help guide firefly in the parameters of the design style we are looking for 

Não estou conseguindo gerar nada no app, fica pensando e não dá o retorno de imagem, nem mensagem de erro. O que hhouve?

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]

Hi gang;   I've been using Adobe Firefly for about two weeks now and I'm quite excited about the prospect of it.   Prior to this I was fairly involved with MidJourney, especially from its initial release. You can see my AI work (predominantly created with MidJourney) here:   [Weblink removed as per forum guidelines]   I will be adding my Firefly work to it day by day.   I thought I would offer some of my insight to the Adobe team regarding my initial experiences so far. I want to preface this by saying I am not partial to any particular software. As someone who has been working in the computer graphics and animation industry for close to 30 years with all types of apps, I love see these wonderful technological advances and how they can be creatively combined, regardless of who makes what. The only reason I mention MidJourney is because there isn't much else to compare to, aside from Dall-E.   - I'll start by saying that I find Firefly's beta commercial wor

Alors que mon abonnement semble le permetre, je me trouve bloqué sur firefly avec ce type de message : Vous n’avez pas accès à cette fonctionnalitéVous pouvez contacter votre administrateur pour demander l’accès.Que faire ? 

when I try to use adobe firefly it tells me WE HAVE ENCOUNTERED AN ISSUE

❤Hi Adobe Firefly team,My name is Andro, and I’m a huge fan and regular user of Firefly. Your work has become an essential part of my creative process, and I’m truly grateful for everything you’ve built.I recently saw the new Seedance 2.0 video generation model appearing on other platforms, and I can’t think of a better place for it than Firefly. It would be amazing to see this model integrated into the Firefly ecosystem so I can keep all my creative work in one place and not move elsewhere.Firefly already feels like home to me, so I’m writing this as a sincere request and a big hope: please consider adding Seedance 2.0 to Firefly.Thank you so much for listening, and I’ll be eagerly waiting for any updates or feedback from you.Best regards,  Andro

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.

Search bar when searching inspiration images for prompt. it would be great than scrolling and finding. 

Firefly generation should show estimated credits per prompt. I just spent 2,000+ credits on three 5 second long videos!? EEK

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.