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.

[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

[Franck335785421pgd]

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

[CSI Productions]

Did you say you did or did not use FireFly for this sequence of images. If you did, I think this is very close. If not, it gives me hope that at some point we'll have something like this in FF. The without clothes is clearly an issue but as you showed here, neck and shoulders isn't really naked but you probably need to use that in the prompt which would raise a red flag. Moving in the right direction.

[Matt Matt]

The main qualifying prompt is: 
"a 40-year-old woman with tan skin, medium-length black wavy hair parted to the left, with hazel eyes and a long slender nose, with medium-thin lips"... (This gets inserted in the front of every subesquent prompt)

Followed by an attire prompt: 
..."wearing collarless white pleated blouse with a saturated magenta blazer and dark grey business casual pants with purple flat shoes"....

Followed by an action prompt: 
..."sitting inside a blue car holding the steering wheel and driving on a busy city street, with her head pointed forward at the road"...

Followed by a camera prompt: 
..."Wide side view"...

Followed by an enviroment/lighting prompt: 
..."with back lighting."

The complete prompt looks like this:
a 40-year-old woman with tan skin, medium-length black wavy hair parted to the left, with hazel eyes and a long slender nose, with medium-thin lips, wearing collarless white pleated blouse with a saturated magenta blazer and dark grey business casual pants with purple flat shoes, sitting inside a blue car holding the steering wheel and driving on a busy city street, with her head pointed forward at the road. Wide side view with back lighting.

You can switch the order, and insert your own unique prompts. This has been working for me thus far, some scenes better than others. When I get to scenes that involve multiple characters (plus my lead character) Firefly reallys starts to shirt the bed. 

I'm still trying to figure out getting reliable/effective camera angles and NOT having the character look at the camera like a fool. Seems random at best. If anyone has any solid prompts for that I would greatly appreciate the share. Before anyone jumps in I've added "looking at camera" in the exclude list under the advanced field on the sidebar. Does not matter. 

[Matt Matt]

All Firefly, using the Style Reference feature, which is crucial to teaching the model that you want "x" character's likeness in each generation. 

[CSI Productions]

Matt,

Thank you so much. I (and I'm sure others) are so appreciative of you sharing this with us. We're all trying to get a grip on what prompts deliver what we want and this is one of the longer prompts I've seen. I wasn't even aware it would generate an image with this much info so I think we all just learned something.

I've mentioned a number of times that I'm trying to create a children's book my daughter wrote and until I can generate consistency of characters between scenes, I can't begin the process. To date this is the closest I've seen.

Again thank you for your kindness and willingness to share this important prompt.

[Matt Matt]

I appreciate your appreciation! 🙂 

Let's face it, generative AI is still relatively uncharted territory. It's been an "on the job" experience to say the least. 

In terms of prompts, I'm not exactly sure if having more or less information for the tool to bite onto is positive or negative. In my own expereience, and in also using other generative AI image tools outside of Firefly, the more detailed information you can feed it the better. This is why I've developed my own prompting convention to help keep this stuff approachable and manageable, otherwise it gets thick into the weeds really quickly. 

I have some possibly interesting takeaways to share after having just completed my last frame of the script, which was a hurclean feat and a half.  As follows: 

• Generative AI text-to-image (or video) is NOT ready for prime time in the context of multiframe narrative where you need the same character throughout the storyline. No jobs are getting replaced here. The toolset will get there within the next year or two, especially if there's a ton of demand for that out there, but as it stands today you'd better have a full body of hair on your head because half of it is getting pulled out and the other half is going grey. True story. 
  
  
• Firefly's "Style Reference" feature is a great bonus in terms of getting similar results, BUT it most definitely needs refinement, such as locking or resusing the same seed generation, which would go a long way to help ensuring you get the desired result. Again, if used, ALL characters in your scene get the same likeness. Everyone looks like a sibling. It's currently working in a pinch to varied results, but it feels rudimentry, or too "user-friendly" as it stands at the moment. Adobe, give us a little autonomy here. 
• Maybe this is a placebo due to starring at the screen for rash of uninterprupted consecutive hours, but as I went along in my generation journey of my character generation results seemed to get progressively worse. My results started to get progressively "muddier". I'm not sure how Firefly is working under the hood, and I doubt Adobe will let us take a peek, but resetting the UI seemed to bring it back to results I would expect. 

• Hands. Lord help us all with AI hands. Pick your poisonous generation tool, they all suffer from this and it will be the bane of my AI existence until it's reliably addressed. 

• Production time: Thought you were going to save time=money, did you? Ha! Sure, I didn't have to illustrate each frame which obviously DOES save time=money in the grand scheme of things, but there's plenty of time=money in having to sit there and massage the deep learning models to behave itself like an onry toddler. There's hope here; As the models data mine more information the equation will eventually be, "understanding=awesome sauce". 

Cheers, and happy holidays, you crazy creative cloud kids! 

[Sundip34223949uua1]

To build storyboard with same characters across images 

[형진박84186224]

Please create a feature that allows the character's image to maintain a consistent appearance based on the content written in the prompt. For example, if the prompt is "Create a side view of the character," it should be able to show the character's frontal view as a side view for the same character. The current situation of generating entirely new characters seems insufficient for utilizing the Firefly's capabilities to the fullest. From a designer's perspective, this feature is genuinely essential.

[Fabio310698141uoi]

Gostaria de sugerir a implementação de recursos aprimorados para a criação de personagens em sua plataforma. A proposta é que os usuários possam manter a identidade visual de seus personagens e, por meio de prompts ou comandos intuitivos, ajustar facilmente posições, cenários ao redor e interações com outros personagens criados pelo mesmo autor.

Imagino que essa funcionalidade simplificaria significativamente o processo de criação, permitindo que os usuários se concentrem na narrativa e na dinâmica entre os personagens, sem a necessidade de redesenhar cada cena. Essa abordagem inovadora não apenas agilizaria o fluxo de trabalho, mas também abriria portas para a criação de histórias visuais mais ricas e envolventes.

Acredito que essa adição não só beneficiaria os usuários ao proporcionar mais flexibilidade e eficiência, mas também enriqueceria a experiência geral na Adobe Firefly. Espero que essa sugestão contribua para o contínuo aprimoramento da plataforma, proporcionando aos criadores um ambiente mais intuitivo e inspirador para dar vida às suas histórias.

[jane-e]

@Fabio310698141uoi 

Firefly does not do that currently. If you want consistency between scenes and characters in your stories, you might want to explore traditional methods of working. Try Adobe Illustrator or Adobe Photoshop or a combination of both.

Jane

[Ttk88]

I've been looking for many AI tools to create a photo serie. I want to create a character and place him into different places and poses.. But every AI tool always creates a new picture and changes the look of the character.