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

LoRA Pengguna

XL

Flintlock Pistols

#Gun

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
Flintlock Pistols - AI Model cover image
Diunggah pada
4 Des 2024, 21.35
Penggunaan
2.3k
Ulasan
Luar Biasa  (1)
Kata Pemicu

flintlock

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

LoRA yang Direkomendasikan

Sampo (hsr) - AI Model cover image

LoRA Pengguna

Sampo (hsr)
11
ifn - AI Model cover image

LoRA Pengguna

ifn
0
Shadowverse Tidal Gunner / 潮流の砲手 (シャドウバース) ( Pony ) - AI Model cover image

LoRA Pengguna

Shadowverse Tidal Gunner / 潮流の砲手 (シャドウバース) ( Pony )
0
igl - AI Model cover image

LoRA Pengguna

igl
0

Deskripsi

Stable Diffusion is really bad at drawing guns in general. Sometimes, it makes horrible monstrosities, sometimes it draws the barrel facing the wielder, sometimes it draws the grip in the wrong place. Sometimes it is quite humorous.However, if you try enough, it will get it right... for modern guns. If you want something old, then you are just out of luck. I have never ever gotten SD to draw a flintlock or even a deformed mess that had a flintlock like mechanism.This LoRA is meant to change that. It is trained on images of flintlock pistols, and people holding flintlock pistols, and flintlock pistols firing.This is probably not the final solution, I have plans to improve this in the future.This is step one.This works much better now than other models, however, there is a bit of a quirk to be aware of - this tends to produce images that are very close up and cropped. It helps if you add something to your prompt indicating that it should not be zoomed in or cropped, or if you generate wider images.

Komentar