User LoRA

XL

Hecate PonyXL (Hades II) | LoCon

#Midriff

#Dark skin

#Witch Hat

#long hair

#muscular

#Robe

#Witch

#green eyes

#Armor

#Magic

#Glowing eyes

#Toned body

#Necklace

#Fire

#Muscular female

Hecate PonyXL (Hades II) | LoCon - AI Model cover image
Đã tải lên vào
22:26 19 thg 5, 2024
Lượt sử dụng
331
Đánh giá
Chưa có đánh giá
Từ khóa

hecate, dark skin, green eyes, glowing eyes, medium breasts, mask, covered mouth, toned, green hair, long hair, houtmain, witch hat, hood, crescent, necklace, cloak, crop top, midriff, belt, tassel, robe, armor, pauldrons, gauntlets, single vambrace

Quyền
  • Allow image generation & sharing
  • Cho phép người dùng tải xuống mô hình của bạn
  • Sử dụng thương mại

Mô tả

Hecate the Witch of the Crossroads from the game "Hades 2". Works best around 0.8-1.0 weight. Training done on Pony Diffusion V6 XL. Request form

Trigger: "hecate, dark skin, green eyes, glowing eyes, medium breasts, mask, covered mouth" always needed. Use of "toned" for accurate physique. Add/remove "Witch hat, hood" for her signature headwear. Use "green hair, long hair" if you remove the witch hat.

Suggestions/notes:

Main outfit: "houtmain, witch hat, hood, crescent, necklace, cloak, crop top, midriff, belt, jewelry, tassel, robe, armor, pauldrons, gauntlets, single vambrace" Its a bit RNG due to the limited data and will not work well from other angles as data was very lacking in variety.

Not super flexible due to limited data and will lose likeness of the characters if you remove the mask and/or the witch hat so beware. The hat stays on for best results :) Reduce weight for a bit more flexibility.

"belt, fire" in the negative can fix the odd flame that generates with her long hair.

The witch with abs from a banger of a game Hades 2, Hecate had such a great design so I wanted to make a lora for her with at least some flexibility. Sadly data was very lacking but hopefully there will be more later to make a better V2. I still hope you all enjoy.

Feedback and reviews are always appreciated.

Training data is in the Lora metadata on civitai.

Trained on 21 images.

Bình luận