一、简介
今天给大家分享使用Stable Diffusion图生图进行真人转动漫,木木共使用了五种模型进行真人转动漫测试,重绘幅度在0.45~0.6之间,如果重绘幅度过大,会导致生成的图片偏离主体样貌,下面直接开始操作!!!喜欢的小伙伴帮忙点赞加关注,谢谢!!!
二、实操案例
1.图生图示例-02
Stable Diffusion 模型:2.5D动漫V1.0_V1.0.safetensors
外挂 VAE 模型:vae-ft-mse-840000-ema-pruned-small.vae.pt
Lora模型:
反向tag:空
CLIP 终止层数:2
正向提示词:1girl, solo, long hair, looking at viewer, headphones, black hair, upper body, blurry, blurry background, lips, realistic, shirt, closed mouth, white shirt,
反向提示词:NSFW, (worst quality:2), (low quality:2), (normal quality:2), lowres, normal quality, ((monochrome)), ((grayscale)), skin spots, acnes, skin blemishes, age spot, (ugly:1.331), (duplicate:1.331), (morbid:1.21), (mutilated:1.21), (tranny:1.331), mutated hands, (poorly drawn hands:1.5), blurry, (bad anatomy:1.21), (bad proportions:1.331), extra limbs, (disfigured:1.331), (missing arms:1.331), (extra legs:1.331), (fused fingers:1.61051), (too many fingers:1.61051), (unclear eyes:1.331), lowers, bad hands, missing fingers, extra digit,bad hands, missing fingers, (((extra arms and legs))),
迭代步数 (Steps):20
采样方法 (Sampler):DPM++ 2M Karras
宽度:512
高度:768
总批次数:3
单批数量:1
提示词引导系数 (CFG Scale):7
重绘幅度:0.45
随机数种子 (Seed):453604059
2.图生图示例-02
Stable Diffusion 模型:CamelliaMix_2.5D_V1.safetensors
外挂 VAE 模型:vae-ft-mse-840000-ema-pruned-small.vae.pt
Lora模型:
反向tag:空
CLIP 终止层数:2
正向提示词:1girl, solo, long hair, looking at viewer, headphones, black hair, upper body, blurry, blurry background, lips, realistic, shirt, closed mouth, white shirt,
反向提示词:NSFW, (worst quality:2), (low quality:2), (normal quality:2), lowres, normal quality, ((monochrome)), ((grayscale)), skin spots, acnes, skin blemishes, age spot, (ugly:1.331), (duplicate:1.331), (morbid:1.21), (mutilated:1.21), (tranny:1.331), mutated hands, (poorly drawn hands:1.5), blurry, (bad anatomy:1.21), (bad proportions:1.331), extra limbs, (disfigured:1.331), (missing arms:1.331), (extra legs:1.331), (fused fingers:1.61051), (too many fingers:1.61051), (unclear eyes:1.331), lowers, bad hands, missing fingers, extra digit,bad hands, missing fingers, (((extra arms and legs))),
迭代步数 (Steps):29
采样方法 (Sampler):DPM++ 2M Karras
宽度:512
高度:768
总批次数:3
单批数量:1
提示词引导系数 (CFG Scale):7
重绘幅度:0.45
随机数种子 (Seed):453604059
3.图生图示例-03
Stable Diffusion 模型:cutekawaii_v1.0.safetensors
外挂 VAE 模型:vae-ft-mse-840000-ema-pruned-small.vae.pt
Lora模型:
反向tag:空
CLIP 终止层数:2
正向提示词:1girl, solo, long hair, looking at viewer, headphones, black hair, upper body, blurry, blurry background, lips, realistic, shirt, closed mouth, white shirt,
反向提示词:NSFW, (worst quality:2), (low quality:2), (normal quality:2), lowres, normal quality, ((monochrome)), ((grayscale)), skin spots, acnes, skin blemishes, age spot, (ugly:1.331), (duplicate:1.331), (morbid:1.21), (mutilated:1.21), (tranny:1.331), mutated hands, (poorly drawn hands:1.5), blurry, (bad anatomy:1.21), (bad proportions:1.331), extra limbs, (disfigured:1.331), (missing arms:1.331), (extra legs:1.331), (fused fingers:1.61051), (too many fingers:1.61051), (unclear eyes:1.331), lowers, bad hands, missing fingers, extra digit,bad hands, missing fingers, (((extra arms and legs))),
迭代步数 (Steps):29
采样方法 (Sampler):DPM++ 2M Karras
宽度:512
高度:768
总批次数:3
单批数量:1
提示词引导系数 (CFG Scale):7
重绘幅度:0.5
随机数种子 (Seed):453604059
4.图生图示例-04
Stable Diffusion 模型:Dark Sushi Mix 大颗寿司Mix_BrighterPruned.safetensors
外挂 VAE 模型:vae-ft-mse-840000-ema-pruned-small.vae.pt
Lora模型:
反向tag:空
CLIP 终止层数:2
正向提示词:1girl, solo, long hair, looking at viewer, headphones, black hair, upper body, blurry, blurry background, lips, realistic, shirt, closed mouth, white shirt,
反向提示词:NSFW, (worst quality:2), (low quality:2), (normal quality:2), lowres, normal quality, ((monochrome)), ((grayscale)), skin spots, acnes, skin blemishes, age spot, (ugly:1.331), (duplicate:1.331), (morbid:1.21), (mutilated:1.21), (tranny:1.331), mutated hands, (poorly drawn hands:1.5), blurry, (bad anatomy:1.21), (bad proportions:1.331), extra limbs, (disfigured:1.331), (missing arms:1.331), (extra legs:1.331), (fused fingers:1.61051), (too many fingers:1.61051), (unclear eyes:1.331), lowers, bad hands, missing fingers, extra digit,bad hands, missing fingers, (((extra arms and legs))),
迭代步数 (Steps):29
采样方法 (Sampler):DPM++ 2M Karras
宽度:512
高度:768
总批次数:3
单批数量:1
提示词引导系数 (CFG Scale):7
重绘幅度:0.5
随机数种子 (Seed):453604059
5.图生图示例-05
Stable Diffusion 模型:明快 CrispMix_v1 cucumber.safetensors
外挂 VAE 模型:vae-ft-mse-840000-ema-pruned-small.vae.pt
Lora模型:
反向tag:空
CLIP 终止层数:2
正向提示词:1girl, solo, long hair, looking at viewer, headphones, black hair, upper body, blurry, blurry background, lips, realistic, shirt, closed mouth, white shirt,
反向提示词:NSFW, (worst quality:2), (low quality:2), (normal quality:2), lowres, normal quality, ((monochrome)), ((grayscale)), skin spots, acnes, skin blemishes, age spot, (ugly:1.331), (duplicate:1.331), (morbid:1.21), (mutilated:1.21), (tranny:1.331), mutated hands, (poorly drawn hands:1.5), blurry, (bad anatomy:1.21), (bad proportions:1.331), extra limbs, (disfigured:1.331), (missing arms:1.331), (extra legs:1.331), (fused fingers:1.61051), (too many fingers:1.61051), (unclear eyes:1.331), lowers, bad hands, missing fingers, extra digit,bad hands, missing fingers, (((extra arms and legs))),
迭代步数 (Steps):29
采样方法 (Sampler):DPM++ 2M Karras
宽度:512
高度:768
总批次数:3
单批数量:1
提示词引导系数 (CFG Scale):7
重绘幅度:0.5
随机数种子 (Seed):453604059
6.图生图示例-06
Stable Diffusion 模型:cutekawaii_v1.0.safetensors
外挂 VAE 模型:vae-ft-mse-840000-ema-pruned-small.vae.pt
Lora模型:粉色机甲少女(跪求返图)_v1.0
反向tag:空
CLIP 终止层数:2
正向提示词:1girl, solo, long hair, looking at viewer, headphones, black hair, upper body, blurry, blurry background, lips, realistic, shirt, closed mouth, white shirt, lora:粉色机甲少女(跪求返图)_v1.0:1
反向提示词:NSFW, (worst quality:2), (low quality:2), (normal quality:2), lowres, normal quality, ((monochrome)), ((grayscale)), skin spots, acnes, skin blemishes, age spot, (ugly:1.331), (duplicate:1.331), (morbid:1.21), (mutilated:1.21), (tranny:1.331), mutated hands, (poorly drawn hands:1.5), blurry, (bad anatomy:1.21), (bad proportions:1.331), extra limbs, (disfigured:1.331), (missing arms:1.331), (extra legs:1.331), (fused fingers:1.61051), (too many fingers:1.61051), (unclear eyes:1.331), lowers, bad hands, missing fingers, extra digit,bad hands, missing fingers, (((extra arms and legs))),
迭代步数 (Steps):29
采样方法 (Sampler):DPM++ 2M Karras
宽度:512
高度:768
总批次数:3
单批数量:1
提示词引导系数 (CFG Scale):7
重绘幅度:0.6
随机数种子 (Seed):453604059
7.操作截图
以上即为本期Stable Diffusion图生图(真人转动漫)的操作流程,那么怎么得到本期使用模型呢?
关于AI绘画技术储备
学好 AI绘画 不论是就业还是做副业赚钱都不错,但要学会 AI绘画 还是要有一个学习规划。最后大家分享一份全套的 AI绘画 学习资料,给那些想学习 AI绘画 的小伙伴们一点帮助!
对于0基础小白入门:
如果你是零基础小白,想快速入门AI绘画是可以考虑的。
一方面是学习时间相对较短,学习内容更全面更集中。
二方面是可以找到适合自己的学习方案
包括:stable diffusion安装包、stable diffusion0基础入门全套PDF,视频学习教程。带你从零基础系统性的学好AI绘画!
需要的可以微信扫描下方优快云官方认证二维码免费领取【保证100%免费】
1.stable diffusion安装包 (全套教程文末领取哈)
随着技术的迭代,目前 Stable Diffusion 已经能够生成非常艺术化的图片了,完全有赶超人类的架势,已经有不少工作被这类服务替代,比如制作一个 logo 图片,画一张虚拟老婆照片,画质堪比相机。
最新 Stable Diffusion 除了有win多个版本,就算说底端的显卡也能玩了哦!此外还带来了Mac版本,仅支持macOS 12.3或更高版本。
2.stable diffusion视频合集
我们在学习的时候,往往书籍代码难以理解,阅读困难,这时候视频教程教程是就很适合了,生动形象加上案例实战,一步步带你入门stable diffusion,科学有趣才能更方便的学习下去。
3.stable diffusion模型下载
stable diffusion往往一开始使用时图片等无法达到理想的生成效果,这时则需要通过使用大量训练数据,调整模型的超参数(如学习率、训练轮数、模型大小等),可以使得模型更好地适应数据集,并生成更加真实、准确、高质量的图像。
4.stable diffusion提示词
提示词是构建由文本到图像模型解释和理解的单词的过程。可以把它理解为你告诉 AI 模型要画什么而需要说的语言,整个SD学习过程中都离不开这本提示词手册。
5.AIGC视频教程合集
观看全面零基础学习视频,看视频学习是最快捷也是最有效果的方式,跟着视频中老师的思路,从基础到深入,还是很容易入门的。
实战案例
纸上得来终觉浅,要学会跟着视频一起敲,要动手实操,才能将自己的所学运用到实际当中去,这时候可以搞点实战案例来学习。
这份完整版的学习资料已经上传优快云,朋友们如果需要可以微信扫描下方优快云官方认证二维码免费领取【保证100%免费】