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

Creazione via chat

AI Tools
Guide

User LoRA

XL
Character

Fan No Hitori, Tentacles - Illustrious

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
Fan No Hitori, Tentacles - Illustrious - AI Model cover image
Caricato su
30 giu 2025, 05:16
Utilizzi
304
Reviews
Insoddisfatto
Parole d'ordine

shirikodama, folded, tentacle, tentacle sex, all the way through, colored skin

Permessi
  • Allow image generation & sharing
  • Permettete agli utenti di scaricare il vostro modello
  • Usi commerciali

Recommended LoRAs

Belinda (ill) - AI Model cover image

User LoRA

Belinda (ill)
4
tomboy circle-glasses - AI Model cover image

User LoRA

tomboy circle-glasses
24
Loak from Avatar: The Way of Water [IllustriousXL] - AI Model cover image

User LoRA

Loak from Avatar: The Way of Water [IllustriousXL]
4
(illustrious) Maria Akizuki (秋月 真理亜 ) - Shin Sekai Yori (新世界より) - AI Model cover image

User LoRA

(illustrious) Maria Akizuki (秋月 真理亜 ) - Shin Sekai Yori (新世界より)
4

Descrizione

New Version 3.0.I'll give a brief summary of the differences between the various versions.Version 1 was created with a larger image dataset (about 40-50 images), but without cleaning or resizing the images. It creates more "fantasy-like" environments, but it's also easy to encounter horrors and quite disappointing results...In version 2, I reduced the dataset to a few images (about ten), but all were cleaned. The results are more limited, but clearer.With version 3, I slightly expanded the dataset (about 20 images), but each image was generated using img2img combined with LORA, similar to this, to train the LORA with more defined images.I'm not sure if this can be done for previous versions of this LORA, but to drastically improve the results, I generated the images posted here using img2img by uploading monochromatic images (white, pink, green, blue) depending on the background + Denoising strength set to 0.75. For example, with a pink background, a tentacle pit will automatically be generated!!

Commenti