欢迎您的到来! 您还不是本站会员,请:注册登录
人气 818

[PHOTOREALISTIC真实感] NeverEnding Dream (NED)无尽的梦想NED_v122BakedVae[ECEFB796FF] [复制链接]

莘莘学子 ~ 2024-7-28 10:00:54
neverendingDreamNED_v122BakedVae.safetensors
文件名称:
【CHECKPOINT MERGE】
资源大小:
3.22
程序版本:
SD1.5
资源类型:
STYLE风格 ANIME动漫 GIRLS女孩 REALISTIC现实的 
资源来源:
公共

马上注册,结交更多好友,享用更多功能,让你轻松玩转社区。

您需要 登录 才可以下载或查看,没有账号?立即注册

×
概述:
It has been a while since I made a model. I've been making LoRA's non stop for the last month, but I felt like I needed something. A big problem with DreamShaper is that it wasn't much compatibles with the LoRA's I was making. So I wanted to create a model that was "artistic" like DreamShaper but also able to use my LoRA's and booru tags for generating images. Plus I wanted this to be able to make good anime stuff out of the box, without needing an additional LoRA.
After a lot of tests and also fine tuning (plus LoRA merges) here is my newest model.
It came out a bit more realistic then I wanted, but I won't complain.
What is this model great at?
Generating cosplay images
Generating anime pictures
Work accurately with character LoRA
Generating good looking people
Generating realistic animals
Generating images using booru-like tags
What is this model not too good at?
Generating pictures from complex sentences
Making fantasy/sci-fi paintings
So this basically complements DreamShaper, and it also doesn't include Dreamlike in the mix.
I hope you'll enjoy it!
Some tips:
Use CLIP skip 2.
Select "auto" as vae if you're using the baked vae version.
Use highres fix or img2img to upscale the images after you get a preview. See the examples generation data for settings suggestions, I've tested various techniques.
If you're making images where the subject is far, remember you can inpaint eyes and faces selecting "only masked".
我已经有一段时间没有做模型了。上个月我一直在不停地制作 LoRA, 但我觉得我需要一些东西.DreamShaper 的一个大问题是它与我正在制作的 LoRA 不太兼容。所以我想创建一个像 DreamShaper 一样“艺术”的模型,但也能够使用我的 LoRA 和 booru 标签来生成图像。另外,我希望它能够开箱即用地制作出好的动漫作品,而不需要额外的 LoRA。
经过大量测试和微调(加上 LoRA 合并),这是我的最新模型。
它比我想要的更现实一些,但我不会抱怨。
这个模型擅长什么?
生成角色扮演图像
生成动漫图片
准确处理角色 LoRA
培养好看的人
生成逼真的动物
使用类似 booru 的标签生成图像
这个模型不太擅长什么?
从复杂的句子生成图片
制作奇幻/科幻画
因此,这基本上是对 DreamShaper 的补充,并且它也不包括 Dreamlike。
我希望你会喜欢它!
一些提示:
使用 CLIP skip 2。
如果您使用的是烘焙的 vae 版本,请选择“auto”作为 vae。
预览后,使用 highres fix 或 img2img 放大图像。有关设置建议,请参阅示例生成数据,我已经测试了各种技术。
如果您正在拍摄主题较远的图像,请记住您可以选择“仅蒙版”来绘制眼睛和面部。
Stable Diffusion 很棒,玩得开心!
Hash
parameter
SHA256ECEFB796FFCB7E4099DF12F6419DFFAD671CAA88780FF84FAC9D680947173A0F
CRC3241AFA92E
BLAKE31B6C1445E18C2CD6E473B8E53A2F8E264424A02B7CACE330585B7B8D873F736D
AUTOV1F964CEEB
AUTOV2ECEFB796FF


下载地址:
游客,如果您要查看本帖隐藏内容请回复


您需要登录后才可以回帖 登录 | 立即注册

本版积分规则

站长推荐

【CHECKPOINT】ArienMixXL Asian portrait东方女孩美感v40Pruned[E80A4FB006]

资源详情: Directional tweaks based on ArienRealWordV1 to change the stereotypes of Asian people at ...

ChilloutMix写实的人物模型chilloutmix_NiPrunedFp32Fix

说明: I've been coming to think face variation should be developed not on models, but on LORAs and ...

【CHECKPOINT】majicMIX realistic 麦橘写实majicmixRealistic_v7[7C819B6D13]

概述: 推荐参数 Recommended Parameters for V7: Sampler: Euler a, Euler, restart Steps: 20~40 Hires u ...

【LYCORIS】Swamp Escape Additional AssistanceSwampEscapeAA[AE5A029DF3]

名称:SwampEscapeAA.safetensors 类型:【LYCORIS】 程序版本:SD 1.5 文件大小:257.3MB 概述: Please a ...

【CHECKPOINT】DucHaiten-Pony-XL动感漫画ponyNoScoreV50[B5BDA9465C]

概述: Added the pony-no_score version, which is basically the pony model but can maintain 70-90% im ...

1 2 3 4 5

QQ|Archiver|手机版|小黑屋|心语笔记 ( 苏ICP备2020049347号-1|苏ICP备2020049347号-2 )

GMT+8, 2024-11-17 02:07 , Processed in 0.034962 second(s), 28 queries .

Powered by Discuz! X3.5

© 2001-2024 Discuz! Team.

快速回复 返回顶部 返回列表