V2 is here.
V2 WORK ON BOTH TURBO AND BASE.
ALL SAMPLE IMAGES WAS MADE WITH SINGLE PASS ON TURBO!
This version is now a slider, meaning it preserves facial identity and overall image quality.
V2 is trained on the Z-Image base, making it a major upgrade from V1.
It supports a wide range from -10 to 15, with best results typically below 10.
Because a slider only amplifies what the base model already knows, it’s less extreme than V1—but delivers significantly higher quality.
Description
This was originaly just a test, but it turned out quite good imo. So i released it.
This (V1) was trained on a bad dataset so it messes with faces and the general quality of the output.
But it has some usecases where other sollutions dont work.