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.
I see there is an upcoming FireflyAI feature that creates storyboards from text for video. I saw that and immediately realized how valuable that would be for publishing as well. I am working on a children's book, and have already produced the text and the corresponding visual descriptions to be given to an illustrator. If I could use this AI tool to swiftly generate a storyboard, it could simplify the illustrator's job significantly. Furthermore, it would offer me a chance to visualize the narrative flow and make any necessary adjustments to the visual descriptions.
Merging your thread here so we can track the demand for certain features. You can upvote the original post to let us know you want this feature.
First of all, I love Firefly and what you have done.
One suggestion I have is to somehow create a family of images that all have the same style as each other, even though the subject matter is different. Firefly is great for creating individual images, but if I want a suite of them to feel like they are the same, it's not currently possible, or at least I have not figured it out.
For example, I have written a short book for my son and I want him to enjoy it with some illustrations. It would be great if I could lock in a specific style so that I could create a book worth of illustrations that feel like they are done in the same style.
Hope that makes sense, it's kinda hard to explain.
As designers who may be designing for brands, personal brands, or projects requiring a specific brand style, we must achieve the same aesthetic for imagery as we need to. It's like a designer who is creating human-made designs in Illustrator and has mastered the look they need at each iteration through the use of palettes, forms, specific shapes, etc. It's almost as if our feature request could work as a short-term solution for †his. Though, it could lead to a more long-term solution through a project-based approach allowing us to have access to a specific design style of imagery already preprogrammed and learning continuously.
Thank you for providing more context. When you find an image that you like and what more of it, you can hover over the image, click Edit, and choose "Use as a reference image". That is the best solution I can think of to generate something similar to what was previously generated. You can also check out this post https://community.adobe.com/t5/adobe-firefly-discussions/tutorial-using-a-generated-image-as-a-refer... for a tutorial.
I have a suggestion for enhancing Adobe Firefly. To facilitate the creation of multiple images with consistent styles, I propose the implementation of a "Style Freeze" feature. This feature would allow users to lock or freeze specific style elements within the generated images. For example, if I'm working on a book project, I should be able to freeze the character style to maintain consistency throughout the illustrations. Additionally, it would be valuable to have the option to freeze backgrounds, ensuring that they remain uniform across multiple images, giving them a cohesive and family-like appearance. This "Style Freeze" functionality would greatly benefit users seeking consistency and coherence in their image generation projects.
Provide option to generate content as continuous based on common things. Like if we are creating a story, we can fix characters and continue to generate different story situations.
As for your idea, as you can see from this string it's a popular request. I haven't had a chance to try the "Correct Answer" but I'd be interested if anyone else has I'd be interested in your results - with samples?
R.Cates CSI Productions If you want peace, be peaceful.
I have the same query, AI Firefly has created an illustration of a character I like. I want to use that same exact character in different scenarios. Is it possible to create the exact same character? (Show similar function is not what I'm after) thanks
When creating a landscape and the result of a specific look and feel of a tree is one that we want to keep but the surroundings we want different. It would be welcome to be able to select a object (house, car, trees, etc) and protect their style while the rest regenerated into variations.
I really enjoy the Photo settings sliders, but I have a use case that is not currently met.
Changing the Photo settings also changes the image content as if with a new seed. I'd like to simulate shooting the exact same scene with different settings. This would simulate moving the camera when changing focal length or aperture. Retain the same subject composition, such as a bust or full length portrait so that the subject retains the same visual space in the frame.
------------------------------------------------------------ Never let your tools get in the way of your art!
Again, thank you! But the video "teaser" as well as comments in the thread do not get at solving the issue of "locking -in" a certain look as the story board progesses with different text prompts. Each re-generation or refresh just produces another "brand -new" rendering which may or not be compatible with the previous rendering.
I LOVE Firefly and have quickly outstripped , maybe, its intended purpose. But I am thirsty for more. Specifically , the ability to maintain continuity in creating a story board or an illustrated book.
I have tried the suggested technique of importing an image to provide a "seed" along with the text but that result was very different and therefore not a solution.
NOT THE CORRECT ANSWER. This is an issue I (and many others) have commented on (and requested as a feature). This video does not address the continuity of characters between scenes in a storyboard or storybook. Slapping "Correct Answer" on a post does not make it so.
If the community is missing something, I'd be interested in attending a FireFly webinar where the steps involved show this in practice - I'm sure many others would appreciate this as well.
I'm sure this isn't a simple "bug fix" so I can only imagine what's involved. Still, it's a very common use for FireFly and this would make it insanely popular for obvious reasons.
Thank you.
R.Cates CSI Productions If you want peace, be peaceful.
I think you can already see there's a huge demand signal for the capability of generating consistent characters across multiple frames and scenes to facilitate video storyboards and all aspects of production workflows. It looks like we can hack our way there but it's currently too time consuming. Please put your best team on this feature as soon as possible!
Lot of neat "coming soon" features in the video you sent, but I didn't see anything about maintaining a consistent character across multiple scenes and situations. Was I missing something or were you referring to a different video?
This technique is FAR, FAR away from what folks are asking for but in the meaantime, I have had some success with this approach.
I use the Firefly "slot machine" and arrive at a few characters in a scene that I am happy with. I use photoshop and a mask program to isolate the characters. Then I use just the character file to seed Firefly along with a description. I have even had some luck with asking for different views of the subject. After many generates, I usually come up with several viable views of my chaacter. I then pick a host scene from Firefly and use Photoshop to overlay a masked version . I can move the character around fairly convincingly.
For example the winged guide fairy in my story was created seperately from the scene. I guess I could use generative fill but I like to work in Photoshop as I can blend and place with better control.
pour une histoire, vous pourriez demander de décrire les différents personnage et de les nommer... ainsi lorsque l'on veut générer des illustrations, ses premières images créées par votre IA pourraient être utilisées comme base... on garderait plus de cohérence dans notre travail
From my point of view, one of the most important features that is currently still missing: people and characters must remain the same from image to image. So that you can, for example, tell a story with the same characters over several images.