Feature Requests

Il n'est pas capable d'identifier les pays et province des pays correctement. J'ai demandé une carte du monde qui relierait la province de Québec au Canada au Royaume-Uni. Il a identifié des pays en Amérique du sud et quand j'ai enlevé l'accent à Québec, il a identifié des pays un peu partout dans le monde.  Il faudrait lui apprendre la géographie. 

Hi - you should be able to delete all the non-favorites in your generation history as a batch by maybe selecting "favorities" and then having an option to inverse that selection and then "deleting all". Most times I have to generate a lot of images before the AI understands what to produce that I have in my mind. It's very labor intensive to delete them one by one, but they crowd up my screen if I don't.

With project a voice is chosen for video production. I will like to see the capacity to be able to use an mp3 file to create a talking avatar. I tried  to synch the mp3 file with the voice of choice in Prime, to no avail. I think it will be a great feature to be able to use your own mp3 file to create a video.

Hallo zusammen,wir sind auf der Suche nach alternativem Layout. In Indesign funktioniert das nur maginal gut.Ein Beispiel: Ich gestalte eine Anzeige und möchte die für unterschiedlichen Medien und Formate schnellstmöglich ausspielen ohne großen zeitlichen Aufwand. Ist das mit Firefly möglich?Oder gibt es gar einen anderen Zugang?

können Sie mir eine klassische bialetti - Espressokanne also mockup auf diesem Plakat platzieren das auf dem heruntergeladene Bild steht?

Ich versuche ein Bild für ein Kinderbuch zu generieren. Drei Drachen, zwei Gespenster, drei kleine Jungen. Die KI kann nicht zählen, denn sie macht mal zwei Drachen 1 Gespenst, 4 Jungen. Dann drei Drachen, zwei Jungen, ein Gespenst usw. zudem gibt es Fehler in der Darstellung. Verschbene Gesichter, undefinierbare Muskelmassen an der Seite usw.

編集ボタンを押してないのに直前に作った画像がサンプルとして挿入される連続でいろんな画像を作る事を想定されていないバグ

Would be nice to include an option that would allow for various item images to be uploaded and used in the AI genereated image. Would love to add company logo to image / video creation images. Would love to add still prodouct photography which includes text on labels to used in AI generated images & video. Example: Upload an image of a makeup product and then describe the enviroment to put it into with AI generation. This would be very valuable in the creation of specific product or company (logo) advertisments. 

1- Increase the time lenght.  Other AI companys are offing 8 sec, 10 sec, few are 12 sec now. 2- Referance images,  Allowing people to add ref images such as object on a white background. (example..  blue folding chair on white background. Its the exact style artist wants chair to be but wants AI to fill in the rest,  I need this because my walleyes looks like a bass or trout *fish speices* all the time, unless I use first frame based of image i create or find) 3- I know working on it but audio.  voice match is getting better and better each day.  US TV editors would love that abilty cuz filiming show out in the feild people miss words or say wrong product name or number. 

Necesito que mi logotipo aparezca formándose en partes.Mi logotipo aparece sin movimiento. Necesito que lo haga formándose mediante una secuencia de puntos rojos

I wanted a quick update to my profile pic. So I asked for some modest updates. Instead Adobe (Firefly) decided not to listen to me or anticipate this most basic of requests from its user, and went ahead and showed me what I needed instead, a new gender, more bare chest and some ethnicity suggestions as well!Is this the best your smart AI can do?Do your developers routinely take simple requests and make them pointlessly complex? I think they do... Is that why Adobe has become a laughing stock? Helllo... QuarkXPress... remember them? Unless your products are immediately useful all the stuff you push at people is wasted Adobe. And newcomers are right around the corner ready to make you irrelevant, regardless of how big youve become.

Eu já pago muito caro pelo Adobe CC para não ter direito a criar 4 animações em 6 meses.

DEBERÍA CONTEMPLAR LA POSIBILIDAD DE QUE EL USUARIO SUBA UNA IMAGEN Y, SOBRE ESA IMAGEN SUBIDA ADOBE FIREFLY HAGA (DISEÑE / EDITE) LO QUE EL USUARIO LE SOLICITA!!! ESA OPCIÓN ACÁ... "NO LA TIENEN CONTEMPLADA"

Identify favorites in Generation History with a star so non-favorites can be selected and deleted more easily.

He estado utilizando Firefly para varios proyectos de diseño y, lamentablemente, me he encontrado con problemas significativos en cuanto a la calidad de los acabados. A pesar de proporcionar descripciones detalladas sobre lo que busco, Firefly no ha logrado cumplir con las expectativas. Los acabados en manos y pies son insatisfactorios y a menudo se presentan con deformidades notables. Esto se vuelve aún más frustrante cuando se trata de crear caras, ya que Firefly tiende a generar rostros deformes o inestéticos, a pesar de las instrucciones precisas.Es preocupante que, incluso con una dirección clara, el resultado final sea tan alejado de lo que se busca. Parece como si el sistema ignorara las especificaciones o no tuviera la capacidad de interpretar correctamente las descripciones, resultando en un trabajo que no solo es deficiente en calidad, sino que también carece de una presentación estética adecuada.En resumen, si tu objetivo es obtener acabados precisos y visualmente atractivos

What I'm suggesting: A "Technical Illustration" or "Schematic" content type, to expand Firefly's capabilities for design and product visualizationWhy it matters:Fills the gap between Photo and Art modesPerfect for product designers, engineers, architectsFaster ideation without jumping straight to CADThe problem it solves: Right now we go from rough sketches → straight to expensive CAD time. This would give us that middle ground for quick, dimensionally-aware concepts. Currently, the "Photo" and "Art" content type settings are excellent for their respective purposes. A third option focused on generating images with greater dimensional and structural integrity would be a valuable addition. This would allow users to create more precise drafts and conceptual illustrations, which would be highly beneficial for product designers, engineers, and architects in the early stages of a project. Even if it doesn't offer the precision of dedicated CAD software, this feature would significa

Would be great to have an option for AAF/OMF-export of audio created with firefly.  Example: I just finished creating about 20 sound effects for a short video clip. Some of them are stacked. Now I want to continue with the sound in my local DAW. To do this it seems like I need to download each sound and import them one by one manually in my DAW. It would be great if you enabled AAF/OMF-export so that I could get all audio files placed correctly with only one import. 

I'd like to start with my own design or picture. 

The AI should be smart enough to know that if I type in "exclude words" that it exclude words from its generated images/graphics.  Further, if it is going to have words, they should be actual words and not what appears to be devilspeak or uninvented foreign languages. For example, if I type "Announcements header image for church, but exclude words" the AI should create a graphic having to do with announcements and churches, without any words.  I mean, that's what I'm asking it to do.

Dear Adobe, It would be ideal to be able to search through the Firefly files by using words contained in the prompts. Presently one needs to scroll through a very long collection of thumbnails. It's very inefficient, sometimes it's impossible to find the file that one is after. Please incorporate a search feature into the Firefly file archives. ~ Thank you

It would be great to have a feature in the Adobe Firefly boards that lets us hyperlink and preview Adobe Stock videos directly. That would streamline our workflow significantly.

I have an idea for an AI-powered tool that automatically generates lighting and shadow effects on objects. The concept is simple yet powerful:There will be a movable sun icon that acts as a dynamic light source. Users can freely drag and position this icon anywhere on the canvas or workspace. Based on the position of the sun icon, the AI will automatically calculate and apply realistic light and shadow effects to the objects in the scene.This tool would simulate natural lighting behavior—adjusting the direction, intensity, and length of shadows depending on the sun's location. For example:Moving the sun icon to the top-right corner would cast shadows to the bottom-left.Placing it lower on the canvas would create longer, softer shadows as if it were sunset.Brightness and highlights on the objects would also adapt dynamically.This tool could greatly benefit for anyone who needs quick and realistic lighting in their design process. Instead of manually painting shadows or adjusting layers,

Quiero hacer un video 3D con mis pegatinas puestas en productos de belleza como champo , mascarillas goteros etc

Hello, Have two things to mentions here. First is an idea, second is more of error prevention.1. When generating a video, in composition reference, it only gives option to add a video. Even though we usually have a setting image, or have created a composition from where we want to start the video. In any case, most of the times, we don't have video reference while generating a video, and looking for one wastes a lot of time. Then there's the case where even the prompt is not picking the nearest thing. 2. Having the ability to add the exact text in the video saves many hours of editing, and reduced file size. The prompts are not picking the exact text.Thank you   [personal information removed by moderator]

Pourquoi y Y a pas le son