V.4-PonyXL & V.4-Illustrious

Fixed:

• Reduce File size

• More Flexible for apply style

• More accurate prompt

prompt: mnkRo, black capri pants, white coat, clothing cutout, strapless, bead bracelet, hooded coat, shoes

---

V3.0-Illustrious

I use a same dataset as PonyXL. I didn't test it much. Feel free to try.

Please request a LoRa you want to create to Illustrious.

My base for training ----> /model/795765/illustrious-xl?modelVersionId=889818

Recommended checkpoint ----> /model/827184?modelVersionId=1025184

prompt: mnkRo, pants, cleavage cutout, bead bracelet, jewelry

additional: hood

---

V.3-PonyXL

Almost images in a dataset created by generative AI. I'm not sure this is a cause of copy style from a dataset or not. I tried to decrease LR but not help.

Feel free to try.

prompt: mnkRo, pants, shoes, cleavage cutout, bead bracelet, jewelry

additional: hood

---

V.2

prompt: mnkRo, pants, shoes, cleavage cutout, bead bracelet, jewelry

additional : hood

---

Feel Free To Use.

Note that

• - Hood up + Long hair = No

• - Hood down + Long hair = Maybe

• - Hood up + Low twintails = Worked

Prompt - mnkRo, pants, bracelet,necklace, shoes, cleavage cutout, bead bracelet, jewelry

for Hood - hood, hood up, hoodie