There is also a new tool that can edit text in speech bubbles directly. I haven't been able to get it to work yet, but it looks promising.

Brilliant! I'm glad to see a fellow creator publishing narrative content. I do have a few suggestions. Don't publish directly from AI generator. The chances of having a blurred image or a post-publishing admin takedown are much less likely if you add your images to assets and publish from the new virtual try-on tool. You don't even have to change any of the clothing. Just use the manual selection and change the big circle to the smallest dot possible, then place the dot somewhere in the background where it won't be noticed.

4 hours and a 6 pack later