Keanggotaan PixAI
PixAI
PixAI
Generate
Sign in
Beranda
Buat
Model
Studio
NEW
Kontes
Buat dengan Mio.2
Toolbox
NEW
Dokumen PixAI

LoRA Pengguna

XL
Karakter

[Illustrious] Encore (Wuthering Waves)

#Wuthering Waves

Tidak ada versi yang tersedia

Buat

  • Generator Gambar AI
  • Generator Animasi AI
  • Toolbox
  • Generator Tematik
  • Latih LoRA
  • Agen Mio.2
  • Studio

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

  • App Store
  • Google Play
© 2026 PixAI
  • Ketentuan Layanan
  • Kebijakan Privasi
  • Kebijakan Hak Cipta
  • Undang-Undang Transaksi Komersial Tertentu
[Illustrious] Encore (Wuthering Waves) - AI Model cover image

Versi tidak tersedia. Harap gunakan versi lain.

Dilatih oleh
Avatar image of vjump#0

vjump#0

Diunggah pada
Penggunaan
1.2k
Ulasan
Luar Biasa  (1)
Izin
  • Izinkan pembuatan & berbagi gambar
  • Izinkan pengguna mengunduh model Anda
  • Penggunaan komersial

Deskripsi

Encore (Wuthering Waves)Version 1.1 descriptionLoRA+ with CLIP-L Only no more LoConVersion 1 descriptionFirst Lycoris LoConusing Lion SchedulerPink hair girl again.Trigger Worddefault costume (weight 0.9 - 1)encore (wuthering waves), cross-shaped-pupils, thick eyebrows, purple eyes, blush, hair ornament, pink hair, ahoge, hair bow, pink bow, low twintails, dress, bag, earrings, short, black sleeves, white sleeves, bowtie, black footwearany costume (weight 0.8-1) maybe some costume cant changeencore (wuthering waves), cross-shaped-pupils, thick eyebrows, purple eyes, blush, hair ornament, pink hair, ahoge, hair bow, pink bow, low twintailsLimitationsdefault costume still inaccurate sometimescheckpoints maybe know this character but extremely inaccurate.Training DetailsLoRA sizeDimension 16Dataset80 imagesparametersLoRA+resolution = 1024batch size = 2Network dim,alpha = 16,16mix/save precision = bf16/bf16optmizer = LionUNet LR = 1.75e-5TE LR = 1e-5scheduler = cosine_with_restartsl2 lossunet + clip-lstepstotal steps = 3050toolskohya-ss GUI v24.4.0 (custom version)torch 2.5.0 cu124Runpod RTX 4090 24 GB + xformers + gradient_checkpointingweightUNet average weights : 0.011061001399701292TE1 average weight : 0.009004636706473926*This LoRA is for studying LoRA training with new technique so do not use for damaging the character (also support Wuthering Waves too).*REPOST model is not allow if you found this model please report to me.

Komentar