i have two versions (lora (weak / strong) from -0.4 to 0.8
Sometimes it adds details, sometimes it doesn't, but it adds a background at a simple prompt even if you don't call it.
What i have found out that . . .
first the shedule-type is important (DDIM)
second the prompt order and some usefull trigger are important
eg:
"detailed, sharp outlines, contrast, wide angle lens captures the entire scen with a street (your words for details in background eg: car, people, building)",
and then the object of interest
"a woman in front posing on a street"
and on simple prompt eg: "portait of a woman" it adds at least a blurry background
avoid the word photo, portrait that makes more bokeh
lora (weak / strong) from -0.4 to 0.8
minus - is more cozy / natural / bit more bokeh plus - is more straight mostly more background, less bokeh, bit less face-details
play with it ... and tell me
Reprint with the author's permission
