Any chance of doing the same for TEXT-detail-improved?
#1
by
dsent-zen
- opened
Citing from the readme of the zer0int's model:
👉 The "TEXT" model has superior prompt following, especially for text, but also for other details. DOWNLOAD
👉 The "SMOOTH" model can sometimes** have better details (when there's no text in the image). DOWNLOAD
The "GmP" initial fine-tune is deprecated / inferior to the above models. Still, you can DOWNLOAD it.
In my tests, TEXT is the best one, but there seems to be no way of using it with Invoke.