Feature Requests

Please add the feature to Generate 3D Scene from the video generated by Firefly for animation refinment or editing within Adobe suite of products. Generated characters should have bones and controll attached for fixing animation or apply new animation.

please implement zoom on adobe firefly generated image with caurosal right or left button click if generated is some image, because I like to make sure that image quality is good before I download it, specifically on number of fingers and other detail. thank you

Currently, Adobe Firefly (Web version) lacks an effective way to manage or delete "failed generation" records. While successful images can be managed in "Your Stuff," failed prompts and blank placeholders resulting from errors remain in the history with no option to remove them.Furthermore, there is no manual option to clear the prompt history/suggestions in the input field. I suggest adding: A way to "Delete failed attempts" from the generation history. A feature to clear or manage the prompt history in the input field. Please add a "Delete" function to the options menu on the right for these failed generations. 

Quand j’importe dans Firefly un visuel en jpeg avec des paramètres CMJN, il passe en png et les couleurs sont transformées. Il serait interessant de pouvoir conserver le format de fichier et les couleurs.

Many online video games and social platforms allow players to create unique profile names using invisible Unicode characters. These hidden characters help users create:blank display names stylish gamer tags cleaner profile bios creative clan identitiesAt the moment, creating these names often requires users to manually copy special Unicode spaces from third-party resources such as invisible character examples.You could insert your link on that phrase.Example anchor:invisible character examplesYour sentence would read naturally as:“...copy special Unicode spaces from third-party resources such as invisible character examples.”Then hyperlink that anchor to your site.Continue with:Adobe Firefly could improve creator tools by adding support for:invisible Unicode character detection profile preview simulation username formatting suggestions safe compatibility checks across gaming platformsThis would be useful for:streamers esports players gaming designers social media creatorsAdding this fe

3D scene and characters with bones.  Similar to iclone and DAZ 3D to control frame by frame video output. Poses will be sent as images for firefly to generate consistent video scenes.

Fotos de arquitetura normalmento preconiza uma boa composição onde temos a necessidade de retirar elementos que destoam. Gostaria que a IA pudesse fazer essa analise previa nas imagens. Além disso seria bem vindo a correção automática de perspectiva preconizando a paralelidade dos elemento retos quabdo acontecem

i can only type about 300 words in veo 3.0 video generation please upgrade it more so we can easily explain also Kling 3.0 is always saying error with big prompts also sometimes it doesn’t take 300 words prompt

When using an image or first frame/last frame image reference for image to video, it would be very useful to add an option to upload a subject reference.So in practice I have an environment image reference, and I want to add a specific effect to the space, or a specific character. or even a consistent effect/character for use in other generations. Currently its trial and error each time to try and find the correct prompt. Would additional references be possible? For instance a picture of the kind of character I want, or a video of the kind of effect?Specific example: I rendered a 3d start and end frame image of a room interior. I wanted to animate the trees outside the window blowing in the breeze, or the sunlight casting shadows on the floor, or a person walking through the room.It took a lot of trial and error to get the trees looking correct, but eventually managed it. I gave up on the sunlight effect since I was burning through credits, and I managed to get the character walking th

When I asked it to compare the images before and after, I get the following message. It will be really nice to see before and after once the modifications are complete. “Unfortunately I can't display two images side by side in this interface, but you can compare by scrolling up to the very first image in our conversation against the most recent one. The difference should be quite striking!”

■ タイトル / TitleBoardのズーム倍率によって動画配置サイズが変動する不具合（Kling生成動画）Bug: Video placement size varies depending on board zoom level (Kling-generated videos)■ 概要 / SummaryFireflyBoardにて、Klingで生成した動画をBoard上に配置する際、Boardの表示倍率（ズーム率）によって動画の配置サイズが変動してしまう。When placing Kling-generated videos on the FireflyBoard, the size of the video varies depending on the board's zoom level.■ 発生環境 / Environment FireflyBoard 動画生成：Kling / Video generation: Kling ブラウザ：Chrome / Browser: Chrome ■ 再現手順 / Steps to Reproduce FireflyBoardを開く / Open FireflyBoard 任意の画像を配置する / Place any reference image Boardをズームインした状態でKling動画を生成・配置 　→ 画像と比較して、やや大きいサイズで配置される 　Generate and place a Kling video while zoomed in 　→ The video is placed slightly larger than the image     Boardをズームアウト（例：表示倍率1%） 　→ Zoom out the board (e.g., 1% zoom level) 同様に動画を生成・配置 　→ 非常に大きなサイズで配置される 　Generate and place a video again 　→ The video is placed at an extremely large size   ■ 期待される動作 / Expected Behavior Boardの表示倍率に依存せず、動画は一定サイズで配置されること 画像と同様の挙動で配置され

I am writing to express my extreme frustration with the current state of Adobe’s generative AI content guidelines and filtering systems. As a professional creator and a long-term Adobe subscriber, I am increasingly finding the platform unusable due to over-zealous AI flagging that hinders legitimate, non-violating workflows.The current system is failing professional users in two primary ways:1. False Positives on Non-Violating Content I am frequently blocked from generating or editing content that does not violate Adobe’s stated Terms of Service. My work often involves professional documentation and educational content that requires specific technical imagery. The AI appears to be "playing it so safe" that it has become hyper-sensitive, flagging prompts that are entirely benign in a professional context.2. Lack of Actionable Feedback When a prompt is flagged or an image fails to generate, the error messages provided are vague and unhelpful. Simply stating that a prompt "may violate gui

I am writing to request improvements to the UI/UX regarding prompt management and credit consumption. Currently, the system's behavior leads to significant accidental loss of credits. 1. Auto-Clear Prompt and Prevention of Accidental Re-executionCurrently, when I press the generate button, the prompt remains in the input field. If I accidentally press Enter or refresh the page, the same prompt is re-executed, consuming credits for the exact same image. Furthermore, even after closing the window, returning to the site sometimes triggers an automatic re-execution of the previous prompt.I know this save time for executing the same prompt again, but as mentioned in No.2 below, 90% of the images are similar, and more of the time user wont be using same prompt again and again, compared to trying out other text-to-image. Everytime i have to delete all the words in the prompt bar and this’s kinda stressful. Request: Please implement a feature to clear the prompt field after execution, or add a

今天嘗試使用 Adobe Firefly 的音訊翻譯時，發現可以翻譯的語言沒有很多，特別是中文（華文）的翻譯上，很希望也能有繁體中文的音訊翻譯可以選擇，因為簡體中文與繁體中文使用的語境，在現實中有很大的不同，謝謝！ I tried using Adobe Firefly’s audio translation today and noticed that the range of supported languages is quite limited. In particular, for Chinese, I really hope Traditional Chinese can be included as an option.Simplified Chinese and Traditional Chinese are used in very different real-world contexts, so treating them as interchangeable doesn’t reflect actual usage. It would be greatly appreciated if Traditional Chinese audio translation could be supported as well. Thank you. 

To give an example, if you use a reference image for a while, even after removing the reference, it continues to use it. Or for simpler example, it remembers your old prompts and uses them even when you don’t need them anymore. Only way to fix this is clearing the cookies.

There's no posibility to edit the transcription, and there are several phrases that it misunderstood. So the translation is imposible due to those errors, hence, useless...   Also, it will consume my credits for generation, but it dont tell me how many. So I dont know if it will rip off all my credits or use just a few. I wont risk it and not be able to work later properly.

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.