Upload LDC_style_v10.safetensors
Browse files![02145-2980421217-(realistic_1.1),masterprice,keai, 1girl, dress, small breast,, on bed,looking at viewer, (detail eyes_1),.png](https://s3.amazonaws.com/moonup/production/uploads/642459e3956c16097c2673b8/uYYmJFM7ihO8uY5pJpXZL.png)
介绍:
这次的Lora主题为少女风的卧室摄影。所以起名为:闺房
首先我自我批判一下。这不是一件优秀的成品lora,不像我之前发的两个傻瓜式lora,这个lora需要使用者对prompt有一定的调试能力。真心不推荐新手使用!
由于是清明节前一天晚上腾出时间制作的,过于仓促,挑选的训练集内侧脸图片偏多,而正脸图片较少。导致生成的女孩容易闭眼或侧脸。本来不想放出这一版,但在大量测试后发现,只需对prompt进行一些简单处理,还是能得到不错的风格化图片。所以还是决定放出来供各位学习交流。
光说不练假把式,所以具体的效果和参数请看样图。
相关问题、或者渲染出来的优秀作品,都欢迎在评论区留言反馈。
使用事项:
注意!一旦下载这个lora,即证明你自愿遵守以下条款:
本Lora仅供个人学习交流,禁止任何形式的转载、传播;禁止用于任何商业用途。
Lora禁止用于从事非法活动,使用时请遵守所在地的法律法规。对于Lora使用者的非法行为,本人概不负责并坚决反对。
不鼓励将Lora用于生成NSFW内容。
样图参数(Sample image prompt):
(realistic:1.1),masterprice,keai, 1girl, dress, small breast,<lora:LDC_style-000002:0.6>, on bed,looking at viewer, (detail eyes:1),
Negative prompt: bad-picture-chill-75v, negativeembed,bad anatomy,side face,bad eyes,
Steps: 30, Sampler: Euler a, CFG scale: 7, Seed: 2980421217, Size: 568x776, Model hash: fc2511737a, Model: 真人_chilloutmix_NiPrunedFp32Fix, Denoising strength: 0.35, Clip skip: 2, ENSD: 31337, Hires upscale: 1.5, Hires upscaler: Latent
ps:不是我不愿意分享样图参数,而是c站现在不会自动读取图片的prompt,只能自己手动填写,真的没这么多精力和时间。请各位理解。如果你对我上传的某张样图比较感兴趣,你可以另存为后用图片信息功能识别。这个lora上传的样图全部是原图,里面自带所有的prompt参数。
EN
The theme of this Lora is a girl style bedroom photography. So I named this lora as “lady's chamber”
First let me be self-critical. This is not an excellent finished lora, unlike the two foolproof lora I posted before, this lora requires the user to have some debugging ability for prompt. Really not recommended for newbies!
Since it was made in the night before the Qingming Festival to spare time, it was too hasty, and there were more side face pictures and fewer front face pictures in the selected training set. The result is that the generated girls tend to have closed eyes or side faces. Originally I did not want to release this version, but after a lot of testing, I found that I only need to do some simple processing of the prompt, but still can get a good stylized picture. So I still decided to put it out for guys to communication and learn.
Please see the sample picture for the specific effect and parameters
Related questions, or rendering out excellent work, are welcome to leave feedback in the comments section.
Terms of Use:
Attention! By downloading this lora, you certify your voluntary compliance with the following terms:
My Lora is only for personal learning and communication.Any form of reproduction and dissemination is prohibited; any commercial use is prohibited.
Use for illegal activities is prohibited, and please observe the laws and regulations of your location when using Lora. I am not responsible for and strongly oppose any illegal actions by Lora users.
It's discouraged for generating NSFW content.
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2ba963ed0f8d88e14fa8d1fd963373320b6abd47bda5323ce63c1295a61ba288
|
3 |
+
size 75613475
|