Copy link to clipboard
Copied
Hello people!
Did you have questions about Firefly or Generative AI for which you needed a trusted expert to weigh in?
Whether you’re a beginner trying to understand the basics or an advanced user looking to delve deeper into the functionality, our Ask the Experts session is the perfect opportunity to get your questions answered!
How to Ask Your Questions
Participating is easy! Just reply to this post with any questions about Firefly and its use in generative AI. Here are some ideas to get you started:
Session Timeline
Drop your questions below, and let’s get this conversation started!
Looking forward to seeing what you all come up with.
Cheers,
Preran
Copy link to clipboard
Copied
Copy link to clipboard
Copied
Thank you @droopydog500
I have been experimenting more since then, and it has dawned upon me, that in order to get something usable, one has to work around. Using the word "mexican" is no good. It will provoke some abuse filter somewhere. Using the word "bandit" is no good. Filter again. Guns, are no good. Filter again. So basically you have to write along the lines of "a person with a moustachne and a sombrere with something resembling a gun...." etc. Otherwise the AI will generate silly stuff. It's like working with gigantic mittens on both hands and one, extra big, mitten pulled down over your head. 🙂
Copy link to clipboard
Copied
The clue here is where you say "With a pencil I can draw anything." Use the pencil, draw a sketch of what you need, then use the sketch as a structure reference. The combination of structure and style reference is quite powerful, and worth expermenting with.
Copy link to clipboard
Copied
Hi, Preran!
My question is about the possibility to generate a human character or a cartoon character and create a scene, and then the possibility to create other scenes with the same generated character in other poses and in other environments.
Thanks in advance
Copy link to clipboard
Copied
To my understanding there is no offical way to do this.
However a combination of reference image and structure reference may get you close.
https://www.youtube.com/watch?v=vkZIsP3srU4
Copy link to clipboard
Copied
This is absolutely something we've been exploring and hope to have this feature in the future.
Thanks
Tracy
Copy link to clipboard
Copied
Thanks a lot!
Copy link to clipboard
Copied
Preran,
Will Firefly soon enough be able to take a prompt that creates videos or video slideshows out of a prompt that you can update after?
Copy link to clipboard
Copied
As far as I know, there isn't anything in the roadmap to this effect. I suggest sharing your idea with the team by posting in the Ideas section. Easier still, see if you can find a similar request to. upvote.
Copy link to clipboard
Copied
Can the design templates in firefly be used commercially?
Copy link to clipboard
Copied
I am not quite sure what you mean by templates in Firefly. This is most relevant info I have on this topic: https://helpx.adobe.com/ca/firefly/faq.html#using-firefly
Can I use Firefly generated outputs commercially?
For features without the beta label, you can use Firefly-generated outputs in your commercial projects. For features that are in beta, you can use the Firefly-generated outputs for your commercial projects unless explicitly stated otherwise in the product.
Copy link to clipboard
Copied
Did you mean perhaps Adobe Express?
Copy link to clipboard
Copied
Hi @Preran .
Thanks for this thread.
I have skimmed through various questions here and what I have may overlap a bit. From what I've seen discussed in the forums and also what I'd like, there are 2 big areas in demand:
1. Negative prompt update.
2. Better saving of history - images and prompts.
Are you able to give an indication on what we can expect in the future relating to the above?
Copy link to clipboard
Copied
I would certainly add an item 3 here.
Another huge item in demand is increased resolution of generation
Copy link to clipboard
Copied
Agreed Euan.
Copy link to clipboard
Copied
Curious when or if a field for NEGATIVE PROMPTS will be added?
I was surprised how other platforms are using this... and the results get even better when you are able to include things you do not want to appear.
Copy link to clipboard
Copied
Absolutely, however I smiled at "include things you do not want to appear"
Very much: "If you can't hear me at the back let me know" 😉
Copy link to clipboard
Copied
What are the plans for generating video content? And will that be a Pr only feature or will After Effects also have it implemented?
Copy link to clipboard
Copied
@Joost van der Hoeven have you seen the latest posts on this? https://blog.adobe.com/en/publish/2024/04/15/bringing-gen-ai-to-video-editing-workflows-adobe-premie...
Copy link to clipboard
Copied
I have noticed that when giving some prompts, they are deemed not allowed but no reason is given. This is rather confusing and it would be helpful if the prompt is highlighted and some reasoning given. I have turned to other AI apps when this has happened and received not similar warnings for the same exact prompts.
Copy link to clipboard
Copied
Hey @michelew83603738,
Please upvote: Show words omitted from prompt or violates content guidelines
Thanks,
droopy
Copy link to clipboard
Copied
When this has happened to me, I have sometimes referred to the Urban Dictionary page and, on a couple of occasions, came across words that had some "interesting" double meanings.
Copy link to clipboard
Copied
That might be helpful, but I am using common words that should be interpreted that way, not in an unusual manner by any means.
Copy link to clipboard
Copied
Hi Preran,
Wondering if Firefly offers image to image prompting?
Thanks,
Tim
Copy link to clipboard
Copied