Membresía PixAI
PixAI
PixAI
Generate
Sign in
Inicio
Generar
Modelos
Estudio
NEW
Concurso
Crear con Mio.2
Caja de herramientas
NEW
Guía de PixAI

LoRA de usuario

XL
Estilo

Fiz-Rot - LyCORIS LoCon - PonyDiffusionXLV6

Crear

  • Generador de imágenes IA
  • Generador de animación con IA
  • Caja de herramientas
  • Generadores temáticos
  • Entrenar LoRA
  • Agente Mio.2
  • Estudio

Descubrir

  • Etiquetas de tendencia
  • Clasificación
  • Mercado de modelos
  • Concurso
  • Noticias

Acerca de

  • Guía de PixAI
  • Cómo utilizar PixAI
  • Tsubaki.2
  • Conoce a Mio
  • Reglas de contenido

Precios y ayuda

  • Membresía
  • Paquetes de créditos
  • Contacto

Aplicación móvil

  • App Store
  • Google Play
© 2026 PixAI
  • Condiciones de uso
  • Política de privacidad
  • Política de derechos de autor
  • Ley de Transacciones Comerciales Especificadas
Fiz-Rot - LyCORIS LoCon - PonyDiffusionXLV6 - AI Model cover image
Subido en
21 abr 2025, 7:33
Utiliza
827
Reseñas
Sin reseñas
Permisos
  • Permitir la generación y el intercambio de imágenes
  • Permita que los usuarios descarguen su modelo
  • Usos comerciales

LoRAs recomendadas

NSWF my style01 - AI Model cover image

LoRA de usuario

NSWF my style01
2
Wotoha  ଳ  をとは - AI Model cover image

LoRA de usuario

Wotoha ଳ をとは
12
Silv - AI Model cover image

LoRA de usuario

Silv
0
♢LoRA - AI Model cover image

LoRA de usuario

♢LoRA
0

Descripción

LoCon trained on Fiz-Rot's artstyle for ponydiff: https://civitai.com/models/257749Artist: He's back but his new stuff isn't making it into my dataset, find him yourself on PixivBecause of my lack of experience and time, the version number may be based on changes that have made certain aspects worse. As such a previous version may perform better than a later version.If you need it for some reason the (old) standard LoRA version exists here: https://civitai.com/models/288465I'm still learning the ins and outs of the model and LoRA training in general, please leave reproducible feedback or tips so that I may improve over time.Check the "About this version" section for any quirks or pitfalls I'm aware of or have experienced.Some Q's:What's your workflow?Sampler from images is done with Restarts with segments of [3,2,0.06,0.30], which are values from the paper on Restarts21.1 The scheduler is KarrasInitial resolution is selected from the SDXL whitepaper appendix I: https://arxiv.org/pdf/2307.01952Perturbed Attention Guidance is used for the initial imageUpscaler is usually 4x_fatal_Anime_500000_G or 4x_NMKD-Siax_200kSecond sample pass is the same as the first (params are on civit's meta interface) but at ~.35 denoiseA facedetailer is usedI use ComfyUI, sorryWhat strength should I be using?Base Pony: .9 - 1AutismMix: 121.1 I recommend Autism_Confetti at .8-1 strength, or <.8 if mixing with other resourcesI absolutely recommend finding a merge at this point, Autismmix Confetti is my go-to but there are plenty of good ones like ponyFaetality or cashmoneyAnimePairs of images?Left image is AutismMix, Right image is base Pony21.1 All images are AutismMix ConfettiWhy not put this as a version on the existing model?As far as I'm aware civit does not allow me to independently tag standard LoRA versions and LyCORIS versions on the same model page, so I've separated them to reflect this.What does your filename structure mean?It's split into 4 parts of [XX]-MAnon-[YYYY]-[ZZZZZZ][XX] - Artist initialsMAnon - My moniker[YYYY] - SD version and Model version (Ex. XLV4.1 is on SDXL [Not 1.5] and it's version 4.1 of the model)[ZZZZZZ] - The epochs, only useful to meThis sucksGod as my witness I'll make it good one dayGod as my witness I think it's good nowGod as my witness It's firmly mid

Comentarios