Iscrizione PixAI
PixAI
PixAI
Generate
Sign in
Home
Generazione
Modelli
Recipe
NEW
Studio
Contest
Mio.2

Creazione via chat

AI Tools
Guide

User LoRA

SD

Danni 2D

HomeModelliMio.2Profilo

Strumenti IA

  • 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

Scopri

  • Trending Tags
  • Classifica
  • Market dei modelli
  • Contest
  • Notizia

Informazioni

  • Informazioni su PixAI
  • Guide
  • Come utilizzare PixAI
  • Tsubaki.2
  • Scopri Mio
  • Regole sui contenuti

Prezzi e assistenza

  • Appartenenza
  • Pacchetti di crediti
  • Contatto

App mobile

  • Scarica l'app PixAI
  • App Store
  • Google Play
© 2026 PixAI
  • Termini di servizio
  • Informativa sulla privacy
  • Politica sul copyright
  • Attributions
  • Legge sulle transazioni commerciali specificate
Danni 2D - AI Model cover image
Caricato su
8 apr 2023, 16:52
Utilizzi
44.1k
Reviews
Excellent  (6)
Permessi
  • Allow image generation & sharing
  • Permettete agli utenti di scaricare il vostro modello
  • Usi commerciali

Recommended LoRAs

Overalls, Girl, - AI Model cover image

User LoRA

Overalls, Girl,
43
Hokuto Nagae - AI Model cover image

User LoRA

Hokuto Nagae
1
Celina (セリナ) - Good Bye, Dragon Life (Sayounara Ryuusei, Konnichiwa Jinsei) (さようなら竜生、こんにちは人生) - AI Model cover image

User LoRA

Celina (セリナ) - Good Bye, Dragon Life (Sayounara Ryuusei, Konnichiwa Jinsei) (さようなら竜生、こんにちは人生)
7
Shizuki/シズキ (Dvine[LUV]/ディヴァイン・ラヴ) - AI Model cover image

User LoRA

Shizuki/シズキ (Dvine[LUV]/ディヴァイン・ラヴ)
3

Descrizione

The LoRA was created to be used with NAI-Based "2D / Anime models" at 0.4-0.6 weight to create beautiful, curvy 2D/2.5D girls.

Trained on top of NAI (nai-animefull-final-pruned). Low weight is needed not because the lora is overcooked or overfitted, but because you'll get realistic results otherwise...(so dont dial up, unless it's your goal. This LoRA will make any 2D scene into 2.5/3D if turned high up enough)

2042 pics were used for the training

Dataset/Tags was manually curated

LoRA (ver. t001.00e05) was trained for a crazy 36075 steps ("36075 img x repeats" / "5 batch size" * "5 epochs") and then fine tuned to 60k+ steps (ver. t007.00e01) on DAdaptation. The whole thing was more an excessive experiment of mine where I tried different things in 4 different trainings.

This version is a resized 128dim/128alpha version of a 256dim/256alpha LoRa

Few of the manually tagged things: "precise tanlines" for signature tan, 80s haircut, 90s haircut, updo haircut, casual haircut, short messy hair, areolae slip,"shiny, shiny skin": for oily look, etc.

NOT INTENDED FOR REALISTIC MODELS OR BASE 1.4/1.5 models.

NOT FOR COMMERCIAL USE

DO NOT USE IT FOR ANYTHING ILLEGAL

Commenti2