Feature Requests

Bei Google Nano Banana ist es normalerweise möglich, mehrere Bilder einzusetzen und z.B. in einem Bild zusammen zu führen. Innerhalb von Firefly ist es leider nur möglich ein einziges Referenzbild hochzuladen.

Any chance we can get English UK for traditional storyteller style. 

I've been playing around with the video editor and noticed that it seems I am only able to change opacity on video layers, not set any kind of blending mode. I can see the video editor being a good on-the-go rudimentary solution, but the lack of blending modes really limits its professional use for me. 

Unser Vorschlag für die Generierung der Bilder: Einstellung Dateiname bzw. Dateibenennung fortlaufend. Dabei sollte sich der Dateiname anpassen lassen. Bsp: Firefly-ICONIC-7020-01.png und fortlaufend mit -02, -03 usw.

Me parece muy buena idea el generador de texto a locución. Los modelos en español son de España América. La versión español de España no están logrados. ¿podrían mejorarlos? Por ejemplo que no tenga el efecto de seseo. En españa la "C" se pronuncia como "C" no como "s".

I'm sure you do a lot of internal testing and beta testing. I have found when launching product, that the testing is more valuable when it is given to individuals not involved with the project (outside of the project) to really get a sense what is intuitive or not with the interface. The online firefly video app needs more user interaction feedback on screen to make workflow progress. If a buttn press doesn't start a process and just sits there, one may get the idea that it is generating, when it isn't. Alerts, warnings and built in feedback should show as an overlay rather than at the bottom of the screen which may be hidden by screen size use.

When creating moodboards the mosaic tool is great but it'd be great if you could set the artboard or shape you want the mosaic to fit to. i.e widescreen so the images all fall nealty into the space

For Firefly speech, there needs to be a better breakdown of phonetics for names. Its a lot of work to get it just right, and almost impossible to change the emphasis on different syllables. Perhaps it should be able to use the univeral diacritics (like ü, ǔ, ʌ, or ə).

would be great for firefly to better understand VFX and compositing context and be able to deliver generated passes from photo or video, i.e, depth, height, normal, bump, AO, roughness, etc. Kole Lugar - MAX25

Me gustaria tener subtitulos en el editorLourdes Molina @iaPulse

Adobe Firefly has a "Convert to GIF" feature which is a really great tool that I would like to use a lot. However, I think the export sizes need to be adjusted slightly. I tested the feature by converting a 15 second video to a GIF into all three download options.Current download sizes of a 15 second video at 16x9:small (180 x 102 pixels) - created a 1.4 mb file medium (360 x 202 pixels) - created a 6.3 mb filelarge (1920 x 1080 pixels) - created a 145.9 mb file The small download is WAY too small, not really seeing a use case for something this small, quality is terrible even on a small screen. The medium size is getting somewhere, and at a 6.3 mb file is still an extremely small file for a GIF. Highly recommend making the current medium size option to be the small size option. Then there is a HUGE jump between the medium and large options, where something inbetween these options would be very helpful. My recommendation would be to make the small option 360x202, the medium o

Adoraria que tivesse no idioma Portugues do Brasil no Gerar fala.

Hello, I'm new here and for fun I'm converting images and images to videos. I already have some experience from various free AI generation platforms. I understand that AI is still developing and that it sometimes doesn't understand my words completely. Therefore, I would suggest that there be an option to generate a rough preview before the main generation. Because even if I run the generation with the lowest computational power requirements and the result is acceptable, the next video will be generated again according to new algorithms and the result may differ. So either during generation, a number should be generated that will allow the video to generate consistently according to the same sequence. Or it should generate a preview of 1 frame per second.I understand that AI likes to make things up, but if a character is at the same distance in the original, it sticks to the concept, but as it gets closer, it invents interesting, even creepy things and creates characters that don't mat

What I would love to see within Firefly Productions: I’d like to provide a few ready-made example compositions in various sizes (e.g., square, skyscraper, panorama) for the same design.Additionally, I’d like to upload some iconic individual elements that make up the design.I’d like to select the desired output sizes.→ Either the most suitable example composition is cropped/rescaled,→ or the separate elements are used to create a new composition. (Also, I’d like to be able to use partner models within Firefly Productions, so I can explain what I want to achieve to, for example, NanoBanana.) Thanks!

It is really difficult and time-consuming to go through hundreds or thousands of files to find something that was created months or years ago. This app needs a search function to find existing files. Ideally, it'll use words from the prompt or a keyword that has been created for searching purposes. Either way this really would enhance the experience of using Firefly. Hope you can find your way to doing this. Thanks.!

Playing with Firefly boards and the export options are extremely limited.   I'd much rather export my noodlings (and video embeds) somewhere else - not just sharing the boards with others via Adobe, but export them as proper presentation decks a la powerpoint or keynote etc..  

Boards seems to re-compress files and thus when downloading them back off the server they are diminished a bit. So I tend to just use boards for organization rather than storage. Thus often I will have a lot of images on there and then will make selects based on my favorites. But then will have to source the original local file to ensure im continuing with highest quality version of the file. Currently the only way to do that is to compare image to image, can you enable the ability to turn on file name as a overlay/caption/comment/properties on the images. Would like to have some way to determine what is the file name of the image I am looking at.

Bonjour, Je trouverais bien que la galérie se renouvèle d'avantage afin de démultiplier les inspirations et les idées !

Really I have no idea why in Boards I get 16 images if I ask for a variation. I was happy with 4 already. Why is there no option to set this back to 4? 16 takes up more space on my board, I get more images that I don't use. Don't we have to consider the environment as well, when rendering images?

Right now a major hangup with my agency is having to manually add the Prompt to a sheet or tracker so we can stay organized with the images we create and use in designs. Is there a built in way to add the prompt to the Firefly image when its downloaded? 

Bonjour, lorsque l'on souhaite utiliser Adobe Firefly avec ses propres visuels, ce n'est pas évident. Par exemple j'ai un logo pour un club de tennis dont l'élément central “un joueur de tennis stylisé” doit être redessiné en matériau de terre battue. Ma procédure : dans “Type” de contenu, j'importe le logo du joueur de tennis en noir et blanc, sans texte, et dans “Style” j'importe le visuel référent de matériau de terre battue sur fond blanc, afin de donner ce rendu particulier au logo en lui donnant cette matière de terre de terrain de terre battue de court de tennis. Je veux un résultat photos que je sélectionne. Une fois le prompt réalisé : “ logo, terre battue, tennis, détails, hyperréalisme, fond studio blanc” on a besoin de faire pas mal de générations pour obtenir le résultat souhaité, et j'avoue assez approximatif. Certes, c'est l'IA. Mais y a-t-il une façon d'écrire le prompt, une méthodologie afin d'obtenir de meilleurs résultats, plus précis ? Merci à vous

I would think it a common request: since there are so many output options (Firefly, Imagen, ChatGPT), why not offer the option of producing one solution in all the formats so the user can pick the best to start with.

I have to redo the settings the same way every time I load up Firefly since they are the same for the given project. Remembering the last used settings seems to make more sense than reseting to default settings every time Firefly is loaded up.

I would like to be able to upload several style reference images and apply them to my prompt at a time. I also would like be able to customize/organize the composition and style reference panel, like adding folders AND keep or remove once uploaded images (so that I dont have to upload them every time). I also need the possibility to add Object references (like product images, maybe even in 3D) and use them unchanged (except for lightning/colors and perspective) to a certain degree in my new images.

I would love to have my work from previous session to be displayed at the start page of firefly.