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

User LoRA

XL
Karakter

Eternal Return - Marlene (Swimsuit)

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

  • App Store
  • Google Play
© 2026 PixAI
  • Syarat Perkhidmatan
  • Dasar Privasi
  • Dasar Hak Cipta
  • Undang-undang Transaksi Komersial Tertentu
Eternal Return - Marlene (Swimsuit) - AI Model cover image
Dimuat naik pada
30 Mei 2025, 5:23 PTG
Kegunaan
5.1k
Ulasan
Bagus  (2)
Kata Pencetus

1girl, white hair, pink hair, two-tone_hair, low_twintails, twintails, red eyes, visor_cap, pink sunglasses, pink-tinted_eyewear

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

Recommended LoRAs

[Artist]  Nanao (Mahaya ななお (真早)-il - AI Model cover image

User LoRA

[Artist] Nanao (Mahaya ななお (真早)-il
0
Baby One More Time - AI Model cover image

User LoRA

Baby One More Time
8
(illustrious) Takamachi Nanoha Aggressor Mode - AI Model cover image

User LoRA

(illustrious) Takamachi Nanoha Aggressor Mode
5
Milim Nava ( Tensei Shitara Slime Datta Ken ) (5 Outfits) - AI Model cover image

User LoRA

Milim Nava ( Tensei Shitara Slime Datta Ken ) (5 Outfits)
12

Keterangan

This is a LoRA of the character Marlene (Swimsuit) from Eternal Return.Since I use ComfyUI and call the LoRA through node connections, there are no specific trigger words required.If you're using a different tool instead of ComfyUI, you can call the LoRA using the lora:~ syntax.The base model used for training is ILXL, and the recommended LoRA weight is around 0.7 to 0.8.Based on personal usage, I recommend using it at 0.8.If you go above 1.0, there's a risk of overfitting, which may distort the face, so using face detailer is highly recommended.As for the checkpoint used for the sample images, I used the WaiNSFW model.Recommended prompt:1girl, white hair, pink hair, two-tone_hair, low_twintails, twintails, red eyes, visor_cap, pink sunglasses, pink-tinted_eyewearFor outfit details, try using:white bikini, rash_guard, black hood, gas mask, mask_around_neck, see-through_sleeves, white shoulder'Eternal Return'의 캐릭터 'Marlene(Swim suit)'의 Lora입니다. 저는 comfyUI에서 노드로 연결하여 Lora를 호출하여 사용하기에 트리거워드는 따로 없습니다. 만약 comfyUI가 아닌 다른 툴에서 사용 시에는 lora:~ 하는 문법으로 호출하시면 사용 가능할 겁니다! 학습은 ILXL 베이스모델을 사용하였으며 추천하는 설정 값은 Lora weight 0.7~0.8 정도입니다.개인적으로 사용 후기로 0.8으로 사용을 권장합니다. 1.0이상을 사용시 과적합 이슈로 인해 얼굴이 무너지기 때문에 페이스디테일러 사용을 권장합니다. 그림을 뽑는 체크포인트의 경우 저의 경우엔 WaiNSFW 모델을 사용하였습니다. 추천하는 프롬프트는 다음과 같습니다. 1girl,white hair,pink hair,two-tone_hair,low_twintails,twintails,red eyes,visor_cap,pink sunglasses,pink-tinted_eyewear복장의 경우엔 white bikini,rash_guard,black hood,gas mask,mask_around_neck,see-through_sleeves,white shoulder 정도를 사용하면 됩니다.

Komen