Answered
Hi Sheryle,
Thank you for writing in.
Text generation within AI models is a known limitation, and Firefly is no exception. Adding text directly during the generation step can sometimes be unreliable, even when quoted.
A good approach is to generate the image or video first without text, then add it afterward in Adobe Express for more consistent results.
I hope this helps with your future generations.
Hajar
Sign up
Already have an account? Login
To post, reply, or follow discussions, please sign in with your Adobe ID.
Sign inSign in to Adobe Community
No account yet? Create an account
To post, reply, or follow discussions, please sign in with your Adobe ID.
Sign inEnter your E-mail address. We'll send you an e-mail with instructions to reset your password.
