Keanggotaan PixAI
PixAI
PixAI
Generate
Sign in
Beranda
Buat
Model
Studio
Kontes
Mio.2

Conversational creation

Toolbox
Dokumen PixAI

LoRA Pengguna

XL
Karakter

[Experimental] She Venom SDXL 0.9 LoRA

#Mature Female#Girl#She-Venom

Alat AI

  • OC Maker
  • AI Anime Generator
  • VTuber Maker
  • Sonic OC Maker
  • Hazbin Hotel OC Maker
  • Anime Character Creator
  • AI Figure Generator
  • Genshin OC Maker
  • All AI Tools

Temukan

  • Tag Populer
  • Peringkat
  • Model Market
  • Kontes
  • Berita

Tentang

  • Dokumen PixAI
  • Cara Menggunakan PixAI
  • Tsubaki.2
  • Kenalan dengan Mio
  • Aturan Konten

Harga & Bantuan

  • Keanggotaan
  • Paket Kredit
  • Kontak

Aplikasi Seluler

  • Dapatkan aplikasi PixAI
  • App Store
  • Google Play
© 2026 PixAI
  • Ketentuan Layanan
  • Kebijakan Privasi
  • Kebijakan Hak Cipta
  • Atribusi
  • Undang-Undang Transaksi Komersial Tertentu
[Experimental] She Venom SDXL 0.9 LoRA - AI Model cover image
Diunggah pada
21 Sep 2024, 00.55
Penggunaan
2.4k
Ulasan
Luar Biasa  (2)
Kata Pemicu

she venom

Izin
  • Izinkan pembuatan & berbagi gambar
  • Izinkan pengguna mengunduh model Anda
  • Penggunaan komersial

Deskripsi

She Venom SDXL 0.9 LoRANote: This LoRA was made on SDXL 0.9, so it will not work for SD 1.5 or any other version of SD!I made this kinda just to see what happens when I throw the dataset I used for my 1.5 she venom lycoris into SDXL, so don't expect anything incredible. The tags were booru styled, so the triggerword might not even be correct. I am just posting this to see what other people can make with it. It is not very flexible and has some errors (like random hair appearing when trying to just get the mask) and the chest pattern is also not consistent. What I really like tho is the patterning on the black bodysuit thingy itself. The teeth and claws are also better than on 1.5, which makes me really look forward to 1.0 finetunes. If you prompt a face you can get some creepy results. It also likes a higher step count.The triggerword should be she venom, but it requires some additional prompting. Check my images to get some ideas.Images were generated on SDXL 0.9 at full resolution (no hires fix or other upscalers used), at either 30 or 50 steps.

Komentar