Models>

Gacha Splash Alter

[(white background:1.15), ::2]1girl, solo, mid shot, full body, <lora:GachaSplashAlter_2:0.8>
(moon:1.1),(sun:1.1) ,(crucifix :1.1),magic circle,( flying bird),
evealing clothes, (infographic:1.2),(mathematical formula, number:1.2)
bat, candy, ghost, halloween, halloween_bucket, halloween_costume, happy_halloween, jack-o'-lantern, pumpkin, pumpkin_hair_ornament, pumpkin_hat, trick_or_treat, witch_hat, manjuu_\(azur_lane\), candy_cane, emoji, holding_vegetable, star_\(symbol\), tombstone, lollipop, ghost_costume, hat, moon, silk, crescent_moon, spider_web, 1girl, long_hair, mini_witch_hat, graveyard, swirl_lollipop, orange_ribbon, lantern, vegetable, food, mimikyu, basket, grave, bat_hair_ornament, cookie, orange_bow, candy_wrapper, witch, vampire_costume, bat_wings, pennant, orange_bowtie, broom, hata_no_kokoro, bow, full_moon, chick, food-themed_hair_ornament, bat_print, basketball, bloomers, solo, luma_\(mario\), orange_dress, orange_legwear, blonde_hair, spider, yellow_eyes, spider_web_print, candle
[(white background:1.15), ::2]1girl, solo, mid shot, full body, <lora:GachaSplashAlter_2:0.8> 
masterpiece, best quality, masterpiece,best quality,watercolor-painting,watercolor-paper,2020s_(style),extremely detailed CG unity 8k wallpaper,ultra-detailed, best illustration, detailed light, over exposure,an extremely delicate and beautiful,solo,1 girl close up,a girl looking at viewer,shiny,beautiful detailed eyes,round eyes,messy floating hair, small breasts,Shiny-messy-hair, extremely detailed background,depth of field,dynamic composition,cinematic-lighting,ink painting-background, fantasy,in-the-library,magic circle,bookshelfs,many books,long coat with fringe,European,scolar,10-years-old,black robe with embroidery,hat with embroidery,boots,long skirt,gorgeous fringe,thin-metal-decorations,antique,blonde-hair,daytime,vintage color,french braid,magic books,tower of books,floating many books,clock,long hair,detailed clothes,100-layer-dress, parted bangs,
[(white background:1.15), ::2]1girl, solo, mid shot, full body, <lora:GachaSplashAlter_2:0.8> 
1girl, solo, gothic, watercolor, black dress, lace patterns, puffed sleeves, silver cross necklace, raven hair, bob cut, shoulder-length, black ribbon hair accessory, piercing blue eyes, wide and innocent eye shape, serene facial expression, petite figure, modest bust, knee-length black boots, moonlit castle backdrop, wrought iron gate, cobbled pathway, full moon, hanging lanterns, swirling mist, delicate spiderweb details, black lace gloves, silver bracelet with intricate filigree, dark lipstick, pale skin, subtle blush, gothic cathedral window in the background, candlelit atmosphere, black lace parasol, vintage key pendant, silver choker with a black gemstone, black lace stockings, moonlit roses, crow perched on a nearby branch, gloomy atmosphere, black lace veil, silver dagger tucked into the belt, moonlit silhouette of bats, ornate black velvet armchair, silver moon pendant, gloved hand holding a black rose, Gothic architecture, moonlit graveyard, small tombstone, shadowy figures lurking in the distance, hauntingly beautiful melody in the air, gothic arched doorway, mysterious aura, moonlit cobwebs, ethereal glow surrounding the girl, black lace fan, solitary figure gazing out into the night, black lace trim on the dress, pale moonlight illuminating her features.
Quick Generate
Select a style, write what you want to see and click Generate
What you want in the image.
Clear
Random
* This model is available for use and will generate similar character to the ones seen in the images.

Model Description by Creator

Introducing a better way to use this LoRA with refiner. All sample images are generated in this way:

Settings:

  1. Check Hires fix: show hires checkpoint and sampler selection

  2. Set "Hires fix: which pass to enable refiner for" to first pass.

  3. Merge LoRA into your base model. Recommend SilvermoonxMix Base mode. Here is a merged version: https://civitai.com/models/54152?modelVersionId=282796

Instruciton:

  1. Set base checkpoint to merged one in Settings#3.

  2. Set Hires, refiner, ADetailer (optional) checkpoint to the one with your desired style (For example, pastel mix)

  3. Suggested configurations:
    DPM++ SDE Karras
    Sampling steps 28

    Refiner switch at 0.425

基于refiner的模型使用手法 https://www.bilibili.com/video/BV1rN4y1B7eg/

前期设置:

使用设置:

  1. 把基础模型设置为融合了立绘法LoRA的模型

  2. 把高清修复和Refiner模型设置为你想用的风格化模型

  3. 根据我的测试,SDE采样器,迭代步数28,refiner切入时机设置为0.425

  4. 如果你使用了ADetailer插件,把ADetailer的inpaint模型也改成同样的风格化模型

不同的模型需要不同的white background权重。如果没有立绘效果,请适当加权。

Different models need different weights of "white background" to get the effect. Increase the weight as you need.

Sample images were generated by https://civitai.com/models/54152/silvermoonmix-base-model

Check my profile for more LoRAs https://civitai.com/user/silvermoong/models

Images Generated With This Model

Loading...

Train Models

Train AI Models On Your Own Pictures

You can use your own pictures to train AI models. Reimagine yourself in new ways with our AI-powered image generator.
Create pictures of yourself around the world, in your dream outfit, as a video game character, or in countless art styles. The possibilities are endless.
Train Your Own Model

Generate AI Images. Simple and Easy

AIEasyPic is the #1 AI image generator. Generate images with simple prompts, swap faces, train models to reimagine yourself, and more.