P: Maintaining a scene or character across different prompts

[James2808541164de]

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.

[The Scott Valentine]

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.

[mckinney3]

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.

We are hungry for more.  😃

[CSI Productions]

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.

[dorar68035820]

I see that there is a lot of interest in generating different scenes with a consistent character. Has this been achieved yet?

[billsantry]

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!

[billsantry]

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?

[mckinney3]

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.

[Yannick33227625ajl8]

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

[msvp84]

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.

[defaultxamq4dghdkxp]

Yes to consistent characters!

[Michael25931279ehyw]

I think such a feature would be very strong. There is already the possibility to upload reference images. That already works pretty well. If I now imagine that I upload a character as a reference, which is then incorporated into all images, this would be a powerful tool.

[33322510bu6b]

I'm trying to create a storyboard quickly. I'd like to be able to use the same character (same shirt, same hairstyle, same age / look) but I can't figure it out. Would love to do that. Or sometimes I like the image, but I don't like the style (I need it to look like a sketch). I want to be able to use the same image but ask the engine to change the style of it. Or change one part of it.

[CSI Productions]

Welcome to club of people trying to do exactly the same thing. We're all hoping Adobe is working on this. I've see other apps that people are using with this capability so I know it can be done. If you discover a way to do it with the available tools, please PLEASE let us know. I'm trying to do some children's book illustrations and this would be mandatory for the character to carry over between images in various scenarios.

[mckinney3]

@ CSI Productions.
Until Firefly has this capabilty I create a character I like and download. Then I can mask all but the charater in Photoshop and then place in different Firefly produced scenes.  I can change the size of character  and colors of the clothes amd placement and can flip  but of course not the 'tween orientations.  Even with creative use of layers I can selectively place behind a prop.  Not a big payoff but a tiny work-a-round.  I did this to create 3 solo charaters from a trio and once isloated can place individual characters in different parts of a scene. Etc.

I am exploring the use of poser software that is mainly used for artists to create a particular pose to draw from.  Similar to the old school wooden posers.  The online vesrions work great and can be imported into 3D modeling programs like Blender.  The needed piece would be to have a set of clothes that are also 3D renderble that then could be used to wrap around  the body model.  I do that already with say upholstery and chairs.  Basically 3D paper doll sets.

Add to the wish list.

[CSI Productions]

I could also draw them by hand. I'm well aware of the options available with compositing and I've been aware of poser, blender, Cinema etc etc. The point is to streamline this with Firefly. Another reason this is desperately needed is for storyboarding. I'll just do thumbnails by hand rather than go through the gymnastics you suggest.

I appreciate your willingness to suggest workarounds but isn't the whole idea of AI to streamline the production process, not find other ways to do things the way they're done now?

[mckinney3]

I am not blessed with the artist skills of creating characters and scenes.  I am a manipulator or mechanic. I like Firefly and I think it adds a needed tool for me to turn my thoughts and ideas into unique and well crafted images albiet there is a certain "slot machine" aspect to the process.  That is the "new" for  me and a wonderful tool that I can add to my tool-kit.  

I need to produce finsished products and not sketches or story boards.  I love Firefly and other forms of AI beacuse it creates new paths for me to follow that I would have never thought about.  So I guess I am a hybrid of AI and natural abilities.  The blend of old tools (blender, photoshop, poser) and new tools (Firefly)  is working for me.

A corollary thought is around text.  Wow,  I get great new story lines from a bullet point list as input but more than often the text, though creative and "new", is stilted or versbose or etc. and I have to turn to old writing skills to hone a new better product.  AI makes me better and expands my work but I'm kinda' glad that I still stay in the process and am part of the creativity.

[CSI Productions]

Well to that I say, you are doing the best you can with what you have to work with and I compliment you on that. I suck at carpentry but I still have tools and use YT video tuts to do projects I wouldn't normally try. Like you I enjoy the craftmanship and I find it to be very rewarding. To me, I'm a carpenter, to a carpenter - ha ha ha they'd laugh but, that's ok, it brings me pleasure. Keep going, over time we all improve and Firefly may be just the thing to get people who wouldn't normally build their own media to dip their toes in the water. Fascinating times.

[Laura33388722n4j0]

Did you find an asnwer to this? I'm sorry but the answer given by the adobe employee doesn't work. I too want to make illustrations for my book with the same looking character throughout. Clicking "Use as a reference image" does NOT work. It gives you images that are somewhat similar but not the same. I finally found a character I liked, clicked that, changed one word in the description and suddenly he looked like he was drawn by a different artist and had different color hair. So far I'm finding this useless for my books and my presentations as a teacher. You can't make anything look cohesive. 😞

[CMass]

Please add your vote to this idea: https://community.adobe.com/t5/adobe-firefly-ideas/p-maintaining-a-scene-or-character-across-differe...

[VincentD22]

Is there a way to have a AI reference image of characters be replicated exactly in other scenes? Using beta 2 firefly

[WapoFranck]

Vous pouvez travailler sur la suggestion en permettant à l'utilisateur d'importer achaque etape de sa modification l'element similaire qu'ils voudrais editer. Cela donnera encore plus de facilité de une correspondance encore plus avancé de ce que desirs le createur

[IESEGEM]

Bonjour,

ce serait pertinent d'avoir la possiblité de pouvoir travailler à partir de la même image afin de la faire évoluer dans différentes pauses ou actions. 

Ex : un homme qui sourit, face caméra.

le même homme qui fronce les sourcils et s'interroge, les yeux levés en l'air

le même homme qui salue quelqu'un (hors champs)

etc

je vous remercie par avance de votre écoute. 

Bonne journée,

[Removed by Mod]

[Stepan30239091ajsv]

In Adobe photoshop it will be very useful to generate same thing on different photos. For examle in one photo I replace some background stuff and I have almost the same photo but I can generate the same background as on previous picture. PLEASE it is very important button generate as on privious image =)))

[Matt Matt]

The real answer is that in ANY AI tool (at the current moment) it's not failproof, given the very nature of generative content, which means "random", but the short answer is yes, ROUGHLY speaking. It's never going to be spot on perfect until the engines start refining their learning models. 

Observe: (Currently working on this project)

Generated source used a a "Style Reference"
In my explorations I've discovered it's better to have a human character without clothes (Adobe has an obvious limitation here) to that the learning model doesn't try to "force" the clothing in any subsequent generations/scenes. 

Now, we generate specific scenes being VERY descriptive. If you're lazy with your prompts your results will be more "guesswork". It's important to note I included the prompt I used in the source image in every new scene/generation, followed by my specific scene descriptors. 

      
As you can see, the results are close, but not spot on. Again, even in Midjourney using the “/prefer option set” you're NOT going to get 100% likeness in each generation. This is the nature of the AI beast. That being said, Firefly's interface is money.

Overall, I find that as it stands at the current moment, multi-scene application using the same character is not refined enough by the current toolset. It's been a somewhat contentious and frustrating journey trying to force a square peg in the proverbial round hole. This method starts to break down whenever you start adding more varired characters into one scene. Firefly can do it, but the other characters look VERY related to your main character.

I have a deadline, so I'm going to have to soldier through it, but I can't wait to tell my Art Director in post mortem that, "this ain't it".

Right, time to brew more coffee. 

[VincentD22]

Hi Can you share the prompts that you used?
Vince