If you want to use more my checkpoint online generation, please visit here.
https://tensor.art/u/762555264535746522
V15
关于例图, 我使用了1024x1360的大小,都是直接输出没有经过AD跟高修.
For the example images
V15, I used 1024x1360,
generated directly without AD or hires fix.
调整了数据,不在需要正负面质量词.
The data has been adjusted, and positive/negative quality tags are no needed.
Recommended Setting
Steps: 30
CFG scale: 7
Sampler: Euler a
V14
关于例图, 我使用了1024x1360的大小,都是直接输出没有经过AD跟高修.
For the example images
V14, I used 1024x1360,
generated directly without AD or hires fix.
重新调整了整体色彩,构图,背景.
The overall color, composition, and background have been re-adjusted.
Recommended Setting
Steps: 30
CFG scale: 7
Sampler: Euler a
Positive Prompt
score_9, score_8_up, score_7_up,Negative Prompt
score_6,score_5,score_4,, worst quality, low quality, bad anatomy, bad hands, missing fingers, fewer digits, source_furry, sourcwe_pony, source_cartoon,3d, blurry,V13
v13主要是进行了色调跟数据调整,对脸部基本没有太大调整.
Version 13 mainly focuses on color tone and data adjustments, with minimal changes to the face.
把cfg稳定在了7,方便后面版本的调整.
The CFG has been stabilized at 7 to facilitate adjustments in future versions.
v13 Recommended Setting
Steps: 30
CFG scale: 7
Sampler: Euler a
Positive Prompt
score_9, score_8_up, score_7_up,source_real,real skin,
BREAKNegative Prompt
worst quality,low quality,
source_furry, source_pony, source_cartoon,2d,
,bad anatomy, bad hands,blurry,3d,__________________________________________________________________________________________________
v12 Recommended Setting
Steps: 30
CFG scale: 5~7
Sampler: Euler a
12 steps Recommended Setting
Steps: 12
CFG scale: 1
Sampler: Euler a
two versions same Prompt
Positive Prompt
score_9, score_8_up, score_7_up,source_real,real skin,
BREAKNegative Prompt
worst quality,low quality,
worst detail,low detail,
source_furry, source_pony, source_cartoon,2d,
,bad anatomy, bad hands, text, error, missing fingers, (extra digit:1.4), fewer digits, cropped, bad artist, outlines,jpeg artifacts, signature, watermark, username, blurry,3d,_______________________________________________________________________
V11
Recommended Setting
Steps: 30
CFG scale: 5~7
Sampler: Euler a
ADetailer face_yolov8s.pt use (ADetailer sampler: DPM++ 2M, ADetailer scheduler: Karras )
Positive Prompt
score_9, score_8_up, score_7_up,source_real,real skin,
BREAKNegative Prompt
worst quality,low quality,
worst detail,low detail,
source_furry, source_pony, source_cartoon,2d,
,bad anatomy, bad hands, text, error, missing fingers, (extra digit:1.4), fewer digits, cropped, bad artist, outlines,jpeg artifacts, signature, watermark, username, blurry,3d,__________________________________________________________________________________________________
V10
Recommended Setting
Steps: 30
CFG scale: 3.5~7
Sampler: Euler a
ADetailer face_yolov8n/s.pt use (ADetailer sampler: DPM++ 2M, ADetailer scheduler: Karras )
Positive Prompt
score_9, score_8_up, score_7_up,source_real,realistic,photorealistic,
BREAKNegative Prompt
worst quality,low quality,
worst detail,low detail,
source_furry, source_pony, source_cartoon,2d,
,bad anatomy, bad hands, text, error, missing fingers, (extra digit:1.4), fewer digits, cropped, bad artist, outlines,jpeg artifacts, signature, watermark, username, blurry,3d,__________________________________________________________________________________________________
V2toV9
Recommended Setting
Steps: 30-50
CFG scale: 7
Sampler: Euler a
Sampler: Euler a ADetailer face_yolov8n/s.pt use more better
Positive Prompt
score_9, score_8_up, score_7_up,Negative Prompt
score_6,score_5,score_4, worst quality, low quality, bad anatomy, bad hands, missing fingers, fewer digits, source_furry, source_pony, source_cartoon,3d, blurry,________________________________________________________________________________________________
v1
Recommended Setting
Steps: 30
CFG scale: 3.5-7
Sampler: Euler a or DPM++ 2M Karras
ADetailer face_yolov8n/s.pt use more better
Positive Prompt
score_9, score_8_up, score_7_up,Negative Prompt
score_6,score_5,score_4,bad anatomy, bad hands, missing fingers, fewer digits, source_furry, source_pony, source_cartoon,3d, blurry, Description
FAQ
Comments (26)
老大把麦橙的脸模融合进去,这个小马直接完美
V4好像更二次元了,我加了真实写实这些提示词也不太行
这个没办法,为了提高模型的灵活性牺牲了这点,只能说更改正反提示词多尝试。
When can it be generated online?
Seems like I don't have the qualification to enable online generation yet.
为什么我用comfyui生成质量很差呢
comfyui 我没有测试过 帮不了你
皮肤的真实感再强一些就爽了,感觉磨皮的过了
This model is incredible, but I have one small issue: it does not like to express darker-skinned/tan women! Lol
Any chance you could fix this? Even when prompting for cosplay of very dark-skinned characters, they come out quite pale.
I will fix this next
I can't confirm that! On the contrary, this checkpoint responds to 'all' the prompts I've tried so far!
不如另外做一个更偏现实的2.5D,不然两边不到岸,皮肤纹理太光滑了
慢慢改,最终是会接近写实更多一点。觉得不够写实可以用前面的版本
建议放一下更新计划。
我一般是一个周末看一次,总是刚更新上个版本,第二天就有更新的出来了。等一个周不更新,以为差不多了,下载完一看例图又更新了。。
工作休息日不怎么规律,有空随缘更新,不更新我会说,没说就是会维护下去的,周期不一定
还好没更新,4.0到5.0之间只差了三天,不然vpn 6个G的流量没了
你点下载之后停掉 把下载链接复制到迅雷里面就行了 不需要梯子的 速度还快
@fr903526994702
@fr903526994702 大佬说的对,访问获取下载链接地址,下载时关VPN即可
V5.0
试用了5.0,光影和皮肤确实比较好,但是好像又失去了 pony prompting 的优势,同样的prompt V4.0 反而比较贴近。
不管如何,希望大佬也可以继续实验,做到一个自己满意大家也喜欢的 checkpoint。
V4.0
不错的更新,之前的版本确实背景常常遇到问题
我个人用了之后觉得之后可以再改进的地方:
1. 光影 (现在每个版本的亮度好像有点过于高了,我需要放 low brightness 才能得到比较好的效果。(我个人用了Pony Realistic Tweaker有比较好的效果,可能可以参考一下)
2. 皮肤质感 (我也看到很多评论有提到这个,目前的效果我本身觉得是可过的,当然希望大佬以后能够继续改进)
不管如何,我觉得每个新版本都越来越不错,希望大佬可以继续下去
多谢评论,虽然平衡点难找。我尽量吧
@WAI0731 慢慢研发吧,希望可以找得到,期待下个版本~







