BlindBox Artstyle
更新了V3版本，调整了眼睛，俗话说眼睛是心灵的窗口。但是目前还是实验性质的，从稳定性上还是推荐v1_mix版本。
如果你喜欢我的作品，可以点个Like，或者请我 喝杯咖啡。
爱来自瓷器。
[机翻英语]
Updated v3 version, adjusted the eyes, as the saying goes, the eyes are the windows to the soul. But it is still experimental, from the stability or recommended v1_mix version.
If you like my work, you can click "Like" or buy me a coffee.
Love from China.
blindbox_v1_mix 👍
Add the prompt full body,chibi,
weigh : 1
checkpoint : RevAnimated or other you like
mix PVC material, is good.
🖖I would appreciate it if you could share with me the results of your use.
blindbox v1
Add the prompt full body,chibi,
Recommeneded weigh : 1
checkpoint : RevAnimated
Other checkpoint may produce fantastic results, try it yourself.
Can be used with other LoRA.
blindbox v2
Reduces the probability of a big head (maybe)
Lowered network_dim value, smaller file size
More Chibi, Less blindbox
v1 version has good blindbox artstyle
blindbox v3
调整眼部细节
ーーーーーーーーーーーーーーーーーーーーーーーーーーーーーーーー
盲盒风格的LoRA，一开始是这么想的。
v1版本 还是比较盲盒的。
增加了PVC的质感，更新了v1_mix，效果很不错，建议使用👍
增加关键词chibi, full body,
减少负面描述会好一点，也可自行尝试。
经过测试，如果要和别的LoRA一起使用，还是把那些负面关键词加上吧😅
推荐使用RevAnimated模型。
跟一些角色LoRA也有比较好的相性。
v2版本减少了大头的概率，更偏向二头身。
适合一些动漫画风了，也许。
有问题可以去B站问，如果我能解决的话😄
姑且放上一个没人气的视频
Description
调整眼部细节，实验版本
FAQ
Comments (44)
为啥我生成的颜色不如你展示的，然后边缘锐度也不如
Use proper VAE : vae-ft-mse-840000-ema-pruned or kl-f8-anime2.ckpt
And if it's still not precise, then discover the marvelous world of inpaint.
txt2img is not even 1% of the job you need to do before reaching very nice results with SD.
这才是猛男最爱（☺）
所需要添加的关键词：chibi。是什么意思
小的，卡通的。
日本語 ちびっ子
我还以为是 赤壁
Q版萌
矮子
@YZo 哈哈，你是懂翻译的
I absolutely love this one!!! Thank you!
通过与其他几个LORA相乘而产生的图像可以作为NFT出版和销售吗？ 将在信息中注明出处。
awsl
I can do almost the same as you expect for opened mouths, mine always do 2D open mouths or realistic tooths which is not my type.
Any idea how to do this ? i tested many prompts i'm stuck here.
这太可爱了，好喜欢
good job
大佬用什么控制手的，我出的图手总是崩
this lora is amazing , thank you
OMG the images looks so, so, cute!!
use the same prompt,but create stange face,so wired
佬你的模型是不是被QQ空间那个sb活动给摸过去了？看起来好像也是ai生成跟这种画风很像的图
Hi, love this lora. Any tips on how to prompt to remove the circle platform under their feet. It's not always that appears but it does most of the time. Thanks.
Very nice.
商务合作，如有兴趣请联系vx：heli1342，谢谢
SDXL Version Please !!!
Love you China lol
很棒，看起来很有质感
求xl版本！！！
真好
so good
是在太可爱了，我喜欢
Is there a way to remove the round pedestal under the character ? It seems to happen a lot. Thanks
我发现基础模型用dreamshaper也不错
为什么图生图模型细节不够，颜色也和原图不一样，怎么调的怎么清楚，是加了别的LORA吗？
感觉这个还是最棒的，考虑适配一个官方的SDXL版本么？
Any chance of converting this lora for pony? I think it would work amazingly!
Why did I choose the same model and prompt words, and when it runs, it produces a completely black image.
A little late to the party, I know; but I just had this issue yesterday with another checkpoint.
In my case, CLIP Skip was set to 1 (-1 actually because ComfyUI), and it was nothing but a black image. Setting CLIP skip to anything other than 1 worked just fine.