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

🫑 Green XL 🫑

#Bara

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
🫑 Green XL 🫑 - AI Model cover image
Enviado em
28 de mai. de 2026, 20:02
Usos
5.5k
Avaliações
Sem avaliações
Permissões
  • Permitir geração e compartilhamento de imagens
  • Permitir que usuários baixem seu modelo
  • Usos comerciais

LoRAs recomendados

Tachibana Hinano 橘ひなの / VSPO - AI Model cover image

LoRA de Usuário

Tachibana Hinano 橘ひなの / VSPO
64
Kaminari Qpi/神成きゅぴ2025Ver (VSPO!/ぶいすぽっ!/VTuber) - AI Model cover image

LoRA de Usuário

Kaminari Qpi/神成きゅぴ2025Ver (VSPO!/ぶいすぽっ!/VTuber)
35
ICHINOSE URUHA(vspo)一ノ瀬うるは - AI Model cover image

LoRA de Usuário

ICHINOSE URUHA(vspo)一ノ瀬うるは
52
[Pony] Tosaki Mimi 兎咲ミミ  / Vspo! ぶいすぽ! - AI Model cover image

LoRA de Usuário

[Pony] Tosaki Mimi 兎咲ミミ / Vspo! ぶいすぽ!
36

Descrição

A merge of multiples checkpoints to attain a style that appeals to me, and hopefully you too~The goal of this merge was to achieve the versatility of the more popular models while adding a sprinkle of cuteness, rendering the characters a little more youthful or anime-likeTo use the model on-site, you need to Bid on it with your Yellow Buzz and it needs to reach the top 200 of the week to be usable for a week.You can do different body types, and call on multiple pre-integrated characters and artists styles without the need of any LorasRecommendations:Positive: masterpiece, best quality, amazing quality, very aesthetic, absurdres, very awa, scenery, cinematic

Negative: low quality, worst quality, normal quality, text, signature, jpeg artifacts, bad anatomy, old, early, copyright name, watermark, artist name, username, bad hands, monochrome, grayscale Steps: 24-40 (32 is good for me) CFGScale: 3-4 Euler a - Automatic

Hires. fix: Upscaler: R-ESRGAN 4x+ Anime6B or Remacri UpscaleBy: 1.5 Steps: (PromtSteps*DenoisingStrenght) DenoisingStrenght: 0.45

ADetailer (not always necessary): Model: face_yolov8n.pt or FurryV1.2.pt Model confidence: 0.3 MaskBlur: 12 InpaintDenoisingStrenght: 0.3 InpaintOnlyMask: 64 ADetailerSteps: 18Green XL is really good at making really big boys because of the Homosimile Merge. Just using huge or hyper on your prompt will really blow your guy up! Green XL as a pretty good anime-like aesthetic too and I find to be a lot more clean.Tips: although it may not be necessary depending on your usage, you can reliably make humans by using the (human:1.8) prompt and specifying the hair shape and color as well as the skin tone. If you tend to get helmets or blob creatures, those are due to your style loras, not the checkpoint.Known issues:1) This model makes very strong highlights! Adding "shiny skin, shiny clothes" in your negatives will fix this if it's not something that you want2) Version 3.2.1 tends to push for full body if your prompt is not precise enough. Just try to be a bit more descriptive.If you want to make better furries, try Citrus XL!

Comentários