Feature Requests

The UI/dashboard is extremely convoluted to use and in no way harmonises with other Adobe products. You’re left randomly clicking back and forth with no definitive journey or structure. It’s a smorgasbord of  buttons and drop downs. Not very well thought out at all. It took 4 attempts to actually find a way to delete the projects I was trialling.

The number of greatest should be increased for free users, along with this the quality of a video and image generation should be improve and also known person in places should be generated with safe limits[Title edited by mod]

I want to use same style header for different photo’s

Why is Sora 2 not inside Firefly boards? Can it moved back there? also including the duration options? 

Sometimes I begin a project with model selection. I run the same prompt in multiple models to see what they do with it and then choose which one to continue with for the rest of the project. I wish I could easily select multiple models to do this with.

Hier je savais que mes credits allaient etre reinitialisés .. j’avais 4000 /8000 . je ne savais plus quels credit avaient ete achetés et quel credits sont réinitialisés . et j’ai donc tout epuisé . sans vraiment le faire avec parcimonie comme je le fais habituellemnt .. si vous separez les deux cela m’aidera à le savoir .. pour le moment je ne sais pas quand me seront remis les 4000 qui me manque ? merci 

The results are not always great. It can be due to bad input, or bad AI. But I still have to burn my credits to generate the video.I would like to to see a button “Video Preview”. It would allow me to see the results before I commit the credits. For video, it can be like just a few frames, maybe 1 frame/sec to see the effect. It can be low resolution. It should use far fewer credits to generate these previews. I suppose for images, something could be worked out as well. Perhaps a very low resolution?

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

Bring the Flux.2 [max] model into Firefly and Photoshop!!! It is crazy that ElevenLabs has it there and not my flagship graphics programs :(

Hello Adobe Firefly Team,I’m Juan Diaz, Course Director for Compositing & Scene Finishing at Full Sail University. As part of our AI-integrated production curriculum, we actively test Firefly alongside platforms such as ComfyUI, Weavy, Runway, and Pika to evaluate real-world workflow integration.While Firefly’s generation quality and Creative Cloud integration are excellent, I would like to formally request consideration for a node-based modular workflow system within Firefly for advanced users and enterprise pipelines.A node-based architecture would enable:• Procedural prompt stacking• Mask and region-based routing• Multi-pass generation control• Style and motion layer branching• Depth and normal pass injection• Controlled iteration comparisons• Export-ready compositing structures• Seamless After Effects / Premiere / Photoshop pipeline flowCurrently, tools like ComfyUI allow modular control but lack Adobe ecosystem integration. Firefly is uniquely positioned to bring professional,

How many credits did I use and the video wasn't created?

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

Is the integration of Firefly with InCopy and InDesign planned for the textual part? For example: given a news agency text, create an alternative text; or, given multiple texts, create a single summary text. Also, given a text, create an alternative version of the same text. More generally, integrate a generative LLM?  Best Regards

I am finding the limitation of the characters very difficult to get to the Image I desire. In fact it's Miles away.

There is no reason why the prompt character limit should be so low on image generation on nano banana pro/2. It is literally the one model where it makes sense to give users the ability to have longer prompts. Its barely usable for me on firefly. I have to force myself to use firefly. At this rate I cannot see myself renewing. yes its that big of a deal.

I want to highlight an area say KEEP or REDO and put in another prompt to make refinement edits 

Currently when generating a soundtrack we are limited to choosing different options to create a song, I would like to be able to input a custom prompt instead of the current multiple choice system!

Why can't I create detailed prompts in NanoBanana Pro on the Firefly website? The number of words I can enter is ridiculously limited!So, it's a silly situation. In the Photoshop interface, the generated description is unlimited, but the maximum resolution is 1k. On the Firefly website, you can generate at 2k, but you can't create detailed prompts. This is completely nonsensical. Please fix it.

Videoları resim ve konuşmalar dahil düzeltebilme

I primarily use this tool for virtual staging work, where I need to write highly detailed prompts describing specific furniture, materials, color palettes, layouts, décor styles, lighting conditions, and spatial arrangements for each image.Because of the level of detail required (for example: furniture material combinations, edge styles, color restrictions, flooring types, wall finishes, lighting direction, décor placement, etc.), I often exceed the current prompt character limit.Having a higher character allowance would significantly improve my workflow and output quality, as it would allow me to provide clearer and more precise instructions without needing to shorten or remove important details.Thank you very much for considering this request.

Please add a recap with the list of everyone of our generations on how much credits it has cost us for us to see how we used our credits and be able to predict how much a project is going cost us and correctly bid it

many users use ChatGPT for a creative prompt, when you past it in Firefly and pick Nano, there is a LIMIT...so you cannot use Firefly...you need to do it in Nano directly. 

generate 5-10 second AI video clips from already make images or generated 

There are only 1024 text characters in the text field, which is not enough. To create better content, it is necessary to be able to write more voluminous scripts.

Intento generar vídeos con Veo 3.1 fast a partir de varias imágenes, que no infringen ninguna regla, son animaciones simples y no puedo porque sale que ha ocurrido un error. Cuando intento animar las mismas imágenes con gemini o flow, pongo la misma indicación que puse en adobe firefly, se genera el vídeo sin ningún problema. el problema es de adobe firefly