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.

[CSI Productions]

Tracy, at the risk of sounding rude, your thread entry is from last year.

I don't understand how a statement that you want to track the popularity of this request is even in question. Ever since Firefly was introduced to the world users have been requesting this feature. From children's book illustrations (my personal request) to storyboards to print ads or corporate how to's - this community has been asking for this since it's inception.

This whole time, through many upvotes to anyone who's requested this feature I think it's painfully clear we've been under the impression Adobe has heard us and was working on it.

Your response suggests you need to take a poll to determine if it's something worth Adobe's time suggesting developing this feature hasn't even been started yet. Has it? Is it even possible? I'm not a programmer so I won't even pretend to know what's involved and I respect those who can write code.

I understand with certain feature requests popularity dictates priority but it's been clear to anyone who's followed this thread that we've been asking/waiting for this feature for over a year.

I would submit the jury is in and the verdict is, there's a dire need for this feature. We'll keep waiting, unless another company figures it out first, in which case, problem solved.

Thank you.

[CSI Productions]

Welcome to the world of frustrated AI users. This has been one of the most popular requests since Ai Generated imagery has been released on the creative community. Maybe AIimage generation can't do everything. That being said, it sure is cool for the stuff it can do.

[CSI Productions]

That entry was misleading. You want to use the same character in for example a storyboard, where you can have an established character in various scenes and with various facial expressions, camera angles, clothing etc. What was written as a reference image "suggested" you could establish a character and then use it for a reference image and from there you can generate any other scenario with the character matching the reference - not so.

Reference image won't do that. In the example they are just asking for a cute dog sitting (no different than doing a stock photo search - in this case) and then selecting one of the photos and then changing the look to a different art style.

It won't let you pick one of the photos, use it as a reference and have the same dog chasing a stick, holding a ball in it's mouth or sleeping on a childs bed. This is what we all want but so far it's incapable.

The closest example I've seen is in this thread. It has images of a Latin looking woman with dark hair in various scenarios and that shows promie. Is it Adobe or proper prompt? I submit it's probably a combination of both.

We're all waiting for this feature to get nailed down. If Adobe pulls it off their stock will probably go up because every creative on the planet will be using it.

[CSI Productions]

No.

[droopydog500]

@CSI Productions, "Idea" posts are not threaded, so it is unclear which messages you are responding to.

    droopy

[Vivek12]

Hi, thank you for the valuable feedback. We have shared this feature request with our product team. They will review it for potential implementation in future updates.

^VS

[rujalmufti]

thank you for the AI ​​features that make my creative work easier. I have a suggestion, please add a feature such as: "Generate images with different poses, but still use the same face as the reference"

[tomg36159422]

I am using Firefly to create portraits of people in the early 1800s for a documentary film. Does anyone know of a method to duplicate the face Firefly creats in different backgrounds? I want the same person placed in various locations. 

[Monika Gause]

This is not possible. You can use Generative fill to replace areas of an existing image.

[tomg36159422]

Yes, that kinda works, but the face is looking in the same direction and expression. Thanks!

FYI I import the Firefly images into D-id an animate them. Very cool. 

[CSI Productions]

Wasn't an idea as much as helping others find a workaround. This was a Premiere Beta Discussion as noted in the subject - also where I posted it (or so I thought).

[Burljon]

To me, any AI that cannot replicate the same characters repeatedly in different settings has no commercial viability and is little more than a child's playtoy. However you do it, I need to be able to define a character, and then place that character in many different settings. Unless you can reproduce the character faithfully, the character has no commercial use. Customers respond to characters. For example, if Garfield looks like Garfield in one image, then looks like Snoopy in the next, then looks like Batman in the next, it is impossible to create branding. If you want a commercial tool, then Firefly MUST have this capability.

[CSI Productions]

We've all been asking for this from the beginning. It would be great if Adobe would be honest and let us know this is being worked on, it's difficult and may be awhile before we have a solution, it's impossible to do with AI. Whatever the reason, stringing this along when you might possibly know this isn't going to be doable would be welcome information so people aren't thinking the fix is right around the corner. We're all adults here, we can take the truth. It's not like we're asking you to prove the existence of extraterrestrial life - I think we all know there is and we handled it like adults (twighlight zone music).

This "has got to be" one of the most requested feature (if not "the" most) with FireFly yet very little is being said by Adobe on what the hold up is.

Admittedly I'm NOT a programmer which is exactly why I'd like someone who actually programs (for Adobe) to chime in as to what we can expect and when (if ever)? 

I'm now seeing regular online AI programs stating that they can in fact do consistency with characters between scenes so there seems to be a way to do it. This one feature request is really the only thing keeping me (and many others I suspect) from using FireFly almost as much as we do Photoshop - for me that's daily.

Thanks for hearing me out. 

[jane-e]

@CSI Productions wrote: It would be great if Adobe would be honest and let us know this is being worked on

If you read the replies from Adobe Staff in this thread (where you have posted close to twenty times), you will see that they are being honest with you and have said that they shared the idea with the product team to review for possible future implementation.

Anyone who knows if this is actually being worked on would be under NDA and could not say more. Adobe will announce in this thread and elsewhere if it happens.

Jane

[CSI Productions]

Jane-e, Thank you for replying and FYI I've read "every" thread relating to this issue because I have a special need for this feature to be implemented, hence, my desire to be treated as an adult with the information pertaining to the topic. I don't recall anyone from Adobe stating they're bound to a NDA and can't give us anymore information.

Your comment stated "if" they implement it feels like it's not going to be anytime soon and my suggestion to others who need this feature yesterday would be to search elswhere.

[jane-e]

@CSI Productions wrote: Your comment stated "if" they implement it feels like it's not going to be anytime soon

I didn't say that — please don't put words into my mouth. I do not work for Adobe and have no idea if they are working on it or what their timeline will be if they do. I only know what staff has said in this thread.

[CSI Productions]

My apology, I misunderstood what it meant to be a Community Expert. I guess I "assumed" you had more insight with Adobe and where they're going with all of this. It's very cool technology overall.

[jane-e]

Thank you for saying that @CSI Productions! For my part, I love the idea of maintaining a scene or character across different prompts. It would be a huge timesaver!

Jane

[CSI Productions]

NP. I admit when I'm wrong. I didn't mean to come across ungrateful. Yes agree with the time saving comment. I think that's what we all are looking for. It will change storyboarding, book illustration, marketing material - exciting times!

[Francesca5C3E]

It would be helpful to enter prompts in the forms of frames or a storyboard. I noticed that only part of what I typed was picked up in the videos, with other elements ignored. I think for both the backend and the user it would be helpful to have an optional choice for a prompt template like: 

Overall description:

What happens first:

What happens next:

(+ add another next)

What happens last:

This would be valuable as a guide, and the AI should also get a clearer picture of how to build the video.

[rudid44560136]

Hello? I like to create a specific caracter (pirate greenbeard) for a event. I would need this character in other settings and if possible in other poses. the first step is no problem, but how do I make the other settings?

[Monika Gause]

Firefly doesn't keep characters consistent. Please check out this: https://community.adobe.com/t5/adobe-firefly-ideas/p-maintaining-a-scene-or-character-across-differe... 

[BriCre95]

I really wish that I could keep the exact same AI generated person but put them in different positions - so when I am using pictures for a book, the person looks like the same person... instead of multiple pictures that are somewhat similar. 

[Vivek12]

Hi, Thank you for your valuable feedback. Our product team is aware of this feature request, and they will take appropriate action based on its feasibility. Meanwhile, please upvote this thread to get this request prioritized correctly. 

^VS

[Ramanakumar17844919axyr]

Hi,

I'm using the Firefly for last few months and was trying to create some consistent images of different scenarios for a slide show of a simple story. But everytime I submit a prompt, even it's the same, the image output varies with different appearnce, and I'm not able to create consistent image with same appreance for any sort of serious of images for a story telling purpose.

I'm looking for any suggesstions regarding.

Thanks