Firefly returns a slop image. Text is garbled (was simplest text in the world). Gives an awkward, unusable image, poor ratio, perspective. Failure to feature the subject.

Hi imvp,
Thank you for reaching out about this.

Text generation within AI models is a known limitation, and Firefly is no exception. Adding text or symbols directly during the generation step can sometimes be unreliable, even when quoted.

One good option is to generate the image without the text/symbol and then add it afterward in Adobe Express.

Another workaround you might find helpful is using Edit in Boards. Load your generated image with the misspelled text, choose Edit, then Edit text in image, and you’ll be able to correct the spelling.

I hope these steps help you achieve the result you’re looking for. Please let us know how it goes.

Hajar
[Moved to question]