• 中文
    • English
    • 繁体
  • 注册
  • AI模型 AI模型 关注:554 内容:3770
    CHECKPOINT MERGE

    chosen impasto-mix

  • 查看作者
  • 打赏作者
  • 13
  • AI模型
  • 大版主
    VIP 4
    靓号:666
    社区达人

    前言:

    如果您使用此模型有更好的创意产品,请在评论区 分享你的产品 和 参数

    非常感谢 ,分享不易,感谢支持,请小心处理生成的图像,并自行承担风险。

    禁止对社区的发展产生不利影响的行为和侵犯个人权利和隐私的使用行为。

    禁止用于生产(生成)违反国家禁止传播的内容和行为!!!

    禁止商业用途!!!

    用0.4 camellia大模型和0.4cetus还有0.2的meina融合而来的。

    效果还蛮不错的,和各路vae相性都很好,例如pastel kl-f8 8400之类的,它带有很鲜明的韩风厚涂的感觉,但是脸又带有一丝meina模型特有的扁平化感觉,形成了一种很有趣的风格,尤其适合跑碧蓝航线的各种舰娘,和那些lora相性都很棒。

    关于提示词,正面常用的是masterpiece , (8k, RAW photo, best quality, masterpiece:1.2), ultra-detailed,这些

    负面(worst quality:2), (low quality:2), (normal quality:2), lowres, normal quality, ((monochrome)), ((grayscale)), skin spots, acnes, skin blemishes, age spot, (outdoor:1.6), manboobs, backlight,(ugly:1.331), (duplicate:1.331), (morbid:1.21), (mutilated:1.21), (tranny:1.331), mutated hands, (poorly drawn hands:1.331), blurry, (bad anatomy:1.21), (bad proportions:1.331), extra limbs, (disfigured:1.331), (more than 2 nipples:1.331), (missing arms:1.331), (extra legs:1.331), (fused fingers:1.61051), (too many fingers:1.61051), (unclear eyes:1.331), bad hands, missing fingers, extra digit, (futa:1.1), bad body,

    采样方式,sde 或者dpm++2mkarras表现很不错,其他的采样方式也各具特色,推荐大家多试试,步数32即可,不用太高,然后要点上高分辨率重绘,重绘幅度推荐0.5,重绘方式R-ESRGAN 4x+ Anime6B,重绘步数12。分辨率格式是800*400,这样重绘放大一倍就是1600*800,清晰度已经蛮不错了。

    chosen impasto-mix

    (Masterpiece:1.2, high quality), (pixiv:1.4),

    <lora:Japanese scene_20230609163753-000018:0.8>

    Negative prompt: EasyNegative, badhandsv5-neg,

    ENSD: 31337, Size: 1664×856, Seed: 3918262461, Model: chosen impasto-mix, Steps: 32, Sampler: DPM adaptive, CFG scale: 7, Clip skip: 2, Model hash: 0ac9feaf4e, Denoising strength: 0.14, SD upscale overlap: 64, SD upscale upscaler: R-ESRGAN 4x+ Anime6B

    chosen impasto-mix

    (Masterpiece:1.2, high quality), (pixiv:1.4),

    <lora:Japanese scene_20230609163753-000018:0.8>

    Negative prompt: EasyNegative, badhandsv5-neg,

    ENSD: 31337, Size: 1664×856, Seed: 3918262465, Model: chosen impasto-mix, Steps: 32, Sampler: DPM adaptive, CFG scale: 7, Clip skip: 2, Model hash: 0ac9feaf4e, Denoising strength: 0.14, SD upscale overlap: 64, SD upscale upscaler: R-ESRGAN 4x+ Anime6B

    chosen impasto-mix

    (Masterpiece:1.2, high quality), (pixiv:1.4),

    <lora:Japanese scene_20230609163753-000018:0.8>

    Negative prompt: EasyNegative, badhandsv5-neg,

    ENSD: 31337, Size: 1664×856, Seed: 3918262469, Model: chosen impasto-mix, Steps: 32, Sampler: DPM adaptive, CFG scale: 7, Clip skip: 2, Model hash: 0ac9feaf4e, Denoising strength: 0.14, SD upscale overlap: 64, SD upscale upscaler: R-ESRGAN 4x+ Anime6B

    chosen impasto-mix

    (Masterpiece:1.2, high quality), (pixiv:1.4),

    <lora:Japanese scene_20230609163753-000018:0.8>

    Negative prompt: EasyNegative, badhandsv5-neg,

    ENSD: 31337, Size: 1664×856, Seed: 3918262529, Model: chosen impasto-mix, Steps: 32, Sampler: DPM adaptive, CFG scale: 7, Clip skip: 2, Model hash: 0ac9feaf4e, Denoising strength: 0.14, SD upscale overlap: 64, SD upscale upscaler: R-ESRGAN 4x+ Anime6B

    chosen impasto-mix

    (Masterpiece:1.2, high quality), (pixiv:1.4),

    <lora:Japanese scene_20230609163753-000018:0.8>

    Negative prompt: EasyNegative, badhandsv5-neg,

    ENSD: 31337, Size: 1664×856, Seed: 3918262453, Model: chosen impasto-mix, Steps: 32, Sampler: DPM adaptive, CFG scale: 7, Clip skip: 2, Model hash: 0ac9feaf4e, Denoising strength: 0.14, SD upscale overlap: 64, SD upscale upscaler: R-ESRGAN 4x+ Anime6B

    chosen impasto-mix

    (Masterpiece:1.2, high quality), (pixiv:1.4),

    <lora:Japanese scene_20230609163753-000018:0.8>

    Negative prompt: EasyNegative, badhandsv5-neg,

    ENSD: 31337, Size: 1664×856, Seed: 3918262557, Model: chosen impasto-mix, Steps: 32, Sampler: DPM adaptive, CFG scale: 7, Clip skip: 2, Model hash: 0ac9feaf4e, Denoising strength: 0.14, SD upscale overlap: 64, SD upscale upscaler: R-ESRGAN 4x+ Anime6B

    chosen impasto-mix

    (Masterpiece:1.2, high quality), (pixiv:1.4),

    <lora:Japanese scene_20230609163753-000018:0.8>

    Negative prompt: EasyNegative, badhandsv5-neg,

    ENSD: 31337, Size: 1664×856, Seed: 3918262493, Model: chosen impasto-mix, Steps: 32, Sampler: DPM adaptive, CFG scale: 7, Clip skip: 2, Model hash: 0ac9feaf4e, Denoising strength: 0.14, SD upscale overlap: 64, SD upscale upscaler: R-ESRGAN 4x+ Anime6B

    chosen impasto-mix

    (Masterpiece:1.2, high quality), (pixiv:1.4),

    <lora:Japanese scene_20230609163753-000018:0.8>

    Negative prompt: EasyNegative, badhandsv5-neg,

    ENSD: 31337, Size: 1664×856, Seed: 3918262501, Model: chosen impasto-mix, Steps: 32, Sampler: DPM adaptive, CFG scale: 7, Clip skip: 2, Model hash: 0ac9feaf4e, Denoising strength: 0.14, SD upscale overlap: 64, SD upscale upscaler: R-ESRGAN 4x+ Anime6B

    chosen impasto-mix

    (Masterpiece:1.2, high quality), (pixiv:1.4),

    <lora:Japanese scene_20230609163753-000018:0.8>

    Negative prompt: EasyNegative, badhandsv5-neg,

    ENSD: 31337, Size: 1664×856, Seed: 3918262529, Model: chosen impasto-mix, Steps: 32, Sampler: DPM adaptive, CFG scale: 7, Clip skip: 2, Model hash: 0ac9feaf4e, Denoising strength: 0.14, SD upscale overlap: 64, SD upscale upscaler: R-ESRGAN 4x+ Anime6B

    chosen impasto-mix

  • CHECKPOINT MERGE

  • chosen

  • 2023 年 5 月 7 日

  • V1.0

  • SD 1.5

  • 5.71GB

  • 隐藏内容需要回复可以看见

    回复
    青铜LV.2

    楼主这个模型感觉真好

    回复
    社区达人

    666

    回复
    黄金

    66666666666666

    回复

    999

    回复
    黑铁LV.10

    66666666

    回复
    青铜LV.1

    nice

    回复
    青铜LV.1

    thanks

    回复
    青铜LV.1

    666

    回复
    黑铁LV.10

    66666666

    回复
    青铜LV.1

    66666666

    回复

    请登录之后再进行评论

    登录

    我关注的圈子

    暂没有数据

    推广赚金币(邀请一人1000金币)

  • 发布
  • 任务
  • 实时动态
  • 模式切换
  • 到底部
  • 帖子间隔 侧栏位置: