Assinatura PixAI
PixAI
PixAI
Generate
Sign in
Página Inicial
Geração
Modelos
Estúdio
NEW
Concurso
Criar com Mio.2
Caixa de Ferramentas
NEW
Documento PixAI

SDXL

RealVisXL V4.0

#Mature Female#Realistic#Photorealistic#Girl

Criar

  • Gerador de Imagens com IA
  • Gerador de Animação com IA
  • Caixa de Ferramentas
  • Geradores Temáticos
  • Treinar LoRA
  • Agente Mio.2
  • Estúdio

Descobrir

  • Tags de Tendências
  • Classificação
  • Mercado de Modelos
  • Concurso
  • Notícias

Sobre

  • Documento PixAI
  • Como Usar a PixAI
  • Tsubaki.2
  • Conheça a Mio
  • Regras de Conteúdo

Preços e Ajuda

  • Assinatura
  • Pacotes de Créditos
  • Contato

Aplicativo Móvel

  • Baixe o app PixAI
  • Loja de Aplicativos
  • Google Play
© 2026 PixAI
  • Termos de Serviço
  • Política de Privacidade
  • Política de Direitos Autorais
  • Attributions
  • Lei de Transações Comerciais Especificadas
RealVisXL V4.0 - AI Model cover image
Enviado em
7 de mar. de 2024, 22:10
Usos
3.3k
Avaliações
Satisfatório  (1)
Permissões
  • Permitir geração e compartilhamento de imagens
  • Permitir que usuários baixem seu modelo
  • Usos comerciais

LoRAs recomendados

KIDS - AI Model cover image

LoRA de Usuário

KIDS
56
Small Body - AI Model cover image

LoRA de Usuário

Small Body
34
Kids body - AI Model cover image

LoRA de Usuário

Kids body
23
sketch style - AI Model cover image

LoRA de Usuário

sketch style
318

Descrição

Use Turbo models with DPM++ SDE Karras sampler, 4-10 steps and CFG Scale 1-2.5Use Lightning models with DPM++ SDE Karras / DPM++ SDE sampler, 4-6 steps and CFG Scale 1-2Please pay attention to the model file name, the part of the name after the underscore is the true version of the model.The model is already available on Mage.Space (main sponsor)RealVisXL Hugging Face Full CollectionIt's important! Read it!The model is still in the training phase. This is not the final version and may contain artifacts and perform poorly in some cases.RealVisXL V5.0 Status (Updated: Feb 15, 2024):

  • Training Images: +0 (V4.0: 3340)
  • Training Steps: +0k (V4.0: 672k)
  • Approximate percentage of completion: ~0%The model is aimed at photorealism. Can produce sfw and nsfw images of decent quality.ᅠRecommended Negative Prompt:(worst quality, low quality, illustration, 3d, 2d, painting, cartoons, sketch), open mouthor another negative promptᅠRecommended Generation Parameters:Sampling Steps: 15-30+Sampling Method: DPM++ 2M Karras / or anotherᅠHires Fix Parameters:Upscaler: 4x-UltraSharp upscaler / or anotherDenoising strength: 0.1-0.5Upscale by: 1.1-1.5ᅠOptional Parameters:ENSD: 31337ᅠThis model is:The training took place locally on a single video card and took about 202 hours. Version 3.0 is not the final version, the model will be updated.ᅠHuge thanks to the creators of these great models that were used in the merge.DreamShaper XL1.0 by LykonJuggernaut XL by KandooAISDVN6-RealXL by StableDiffusionVNTalmendoXL - SDXL Uncensored Full Model by talmendoWyvernMix (1.5 & XL) by wierCrystal Clear XL by WarAnakinProtoVision XL and DynaVision XL by socalguitaristCinemax Alpha | SDXL | Cinema | Filmic | NSFW by viakoleImperfect portrait by MakeThemComeAliveAIArtJib Mix Realistic XL by J1BLEOSAM's HelloWorld XL by LEOSAM

Comentários