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

Genshin_XL|原神甘雨 Ganyu

#Genshin Impact
Herramientas de IA
  • Generador de Anime con IA
  • Generador de imágenes IA
  • Generador de animación con IA
  • Generador de Figuras Anime
  • Generador de Hojas de Personaje
  • Generador de Portadas de Revista
  • Generador de Peluches
  • Generador de Estatuas Gigantes

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

  • Consigue la app de PixAI
  • App Store
  • Google Play
© 2026 PixAI
  • Condiciones de uso
  • Política de privacidad
  • Política de derechos de autor
  • Attributions
  • Ley de Transacciones Comerciales Especificadas
Genshin_XL|原神甘雨 Ganyu - AI Model cover image
Subido en
4 mar 2024, 10:27
Utiliza
1.7k
Reseñas
Excelente  (2)
Palabras clave

ganyu \(genshin impact\)

Permisos
  • Permitir la generación y el intercambio de imágenes
  • Permita que los usuarios descarguen su modelo
  • Usos comerciales

LoRAs recomendadas

SSJ4 Gogeta (Pony) - AI Model cover image

LoRA de usuario

SSJ4 Gogeta (Pony)
22
Du Xie  - AI Model cover image

LoRA de usuario

Du Xie
1
Uzumaki Karin (BORUTO) - AI Model cover image

LoRA de usuario

Uzumaki Karin (BORUTO)
8
AlL9LovelyoFanime - Full outfit - AI Model cover image

LoRA de usuario

AlL9LovelyoFanime - Full outfit
12

Descripción

v3.0-alpha:该版本尝试训练甘雨的不同形态和衣服(但没有完全成功)。ganyu (twilight blossom)ganyu_(heytea)(genshin_impact)ganyu(child)ganyu_(china_merchants_bank)--Training model: Animagine XL V32.5版本更新:使用4800张甘雨图片训练,更强的泛化。删标训练,删除了眼睛和头发的tag。2.0版本更新:更小的体积,使用DIM4进行训练2.0版本一共使用了300张精选图片进行训练触发词:1girl,ganyu_(genshin_impact),solo,blue_hair,breasts,long_hair,detached_sleeves,bell,horns,gloves,bare_shoulders,bangs,gold_trim,looking_at_viewer,purple_eyes,white_sleeves,sidelocks,ahoge,thighlet,black_gloves,white_flower,neck_bell,medium_breasts,Version 2.0 update:Smaller volume, trained with DIM4.Version 2.0 used a total of 300 selected pictures for training.keyword:1girl,ganyu_(genshin_impact),solo,blue_hair,breasts,long_hair,detached_sleeves,bell,horns,gloves,bare_shoulders,bangs,gold_trim,looking_at_viewer,purple_eyes,white_sleeves,sidelocks,ahoge,thighlet,black_gloves,white_flower,neck_bell,medium_breasts,1.5版本:我使用了超过300张图片去训练这个模型,基于这个原因,我没有使用正则化。因为我认为,300张图片已经足够泛化了。另外,打标我使用的是全标,你可能需要更多触发词去唤出角色(是的,触发词失效了)Version 1.5:I used over 300 images to train this model, which is why I didn't use regularization.Because I believe that 300 images are sufficient for generalization.Additionally, I used full annotations for labeling, so you may need more trigger words to evoke specific characters. (Yes, trigger words are not effective anymore.)训练模型:SDXL1.0官模测试模型:Kohaku-XL建议权重:0.6~0.8触发词:(\gan yu)Training model: SDXL1.0 Official ModelTesting model: Kohaku-XLRecommended weights: 0.8Key word :(\gan yu)The English portion is translated by GPT and may contain errors.值得注意的是,在该模型的训练中,我使用waifuc来通过搜集和处理训练集,他可以轻易过滤掉我所不需要的双人图,杂图和黑白图片,这使我的训练集的质量得到提高。https://deepghs.github.io/waifuc/main/tutorials-CN/installation/index.htmlIt is worth noting that in the training of this model, I used waifuc to collect and process the training dataset. It can easily filter out unwanted images such as double exposure, miscellaneous images, and black and white images, which improves the quality of my training dataset.https://deepghs.github.io/waifuc/main/index.html

credits:- https://civitai.com/models/152134/genshinxl-ganyu Not my trained model. credits to above link

Comentarios