Ahli PixAI
PixAI
PixAI
Generate
Sign in
Laman Utama
Jana
Model
Studio
NEW
Kontes
Cipta dengan Mio.2
Kotak Alat
NEW
Guide

User LoRA

SD

Kobeni (Chainsaw Man) LoRA

Cipta

  • Penjana Imej AI
  • Penjana Animasi AI
  • Kotak Alat
  • Penjana Tematik
  • Latih LoRA
  • Ejen Mio.2
  • Studio

Temui

  • Tag Popular
  • Ranking
  • Pasaran Model
  • Kontes
  • Berita

Tentang

  • Guide
  • Cara Menggunakan PixAI
  • Tsubaki.2
  • Kenali Mio
  • Peraturan Kandungan

Harga & Bantuan

  • Keanggotaan
  • Pek Kredit
  • Kontak

Aplikasi Mudah Alih

  • Dapatkan aplikasi PixAI
  • App Store
  • Google Play
© 2026 PixAI
  • Syarat Perkhidmatan
  • Dasar Privasi
  • Dasar Hak Cipta
  • Attributions
  • Undang-undang Transaksi Komersial Tertentu
Kobeni (Chainsaw Man) LoRA - AI Model cover image
Dimuat naik pada
31 Mac 2023, 11:17 PG
Kegunaan
44.6k
Ulasan
Cemerlang  (2)
Kata Pencetus

Kobeni_Chainsawman

Kebenaran
  • Allow image generation & sharing
  • Benarkan pengguna memuat turun model anda
  • Kegunaan komersial

Recommended LoRAs

Himeno - AI Model cover image

User LoRA

Himeno
56
Joy Blessed Assassin Mobile Legends - AI Model cover image

User LoRA

Joy Blessed Assassin Mobile Legends
94
Zhu yuan(Zenless_Zone_Zero) v2 - AI Model cover image

User LoRA

Zhu yuan(Zenless_Zone_Zero) v2
80
Manhwa Artstyle | Webtoon | LoRA - AI Model cover image

User LoRA

Manhwa Artstyle | Webtoon | LoRA
36

Keterangan

Personal Note: dont try to mix other loras with it, doesnt do very well.

Authors Notes: Update 02/10/2023: Just thought I'd mention that I now have a somewhat better understanding of LoRA training. This LoRA in particular suffers from being overfitted hence why just activating it cause Kobeni to show up. Although you can still get quality generations of Kobeni it may struggle when changing up her style with whatever prompts you may use. I plan to fix it eventually.

Training of Kobeni from Chainsaw Man. I'm just getting into LoRA's so I still lack a ton of knowledge on the different parameters to set when training but I think this LoRA functions decent enough that you can produce quality images of her. This LoRA was generated before I knew how to set up a trigger word for it, so it doesn't have one. Will fix it eventually.

Just use generic prompts like: 1girl, white shirt, black necktie. etc. when you have the LoRA enabled. I've found that a weight of "0.9 or 1.0" works best.

Komen2