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.
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.
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"
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.
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).
R.Cates CSI Productions If you want peace, be peaceful.
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.
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.
R.Cates CSI Productions If you want peace, be peaceful.
@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-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.
R.Cates CSI Productions If you want peace, be peaceful.
@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.
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.
R.Cates CSI Productions If you want peace, be peaceful.
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!
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!
R.Cates CSI Productions If you want peace, be peaceful.
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.
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?
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.
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.