Sentinel7 commited on
Commit
ed2fa8f
·
verified ·
1 Parent(s): a82ba3d

Upload 2036919/2308688/README.md with huggingface_hub

Browse files
Files changed (1) hide show
  1. 2036919/2308688/README.md +58 -4
2036919/2308688/README.md CHANGED
@@ -1,11 +1,65 @@
1
-
2
  ---
3
  license: other
4
  tags:
5
- - civitai
 
 
 
 
6
  ---
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
7
  Author: [HearmemanAI](https://civitai.com/user/HearmemanAI)
8
 
9
- Model: [https://civitai.com/models/2036919?modelVersionId=2308688](https://civitai.com/models/2036919?modelVersionId=2308688)
 
 
10
 
11
- Mirror: [https://civarchive.com/models/2036919?modelVersionId=2308688](https://civarchive.com/models/2036919?modelVersionId=2308688)
 
 
1
  ---
2
  license: other
3
  tags:
4
+ - breasts
5
+ - fix
6
+ - nipples
7
+ - style
8
+ - tits
9
  ---
10
+
11
+ # Breasts and Nipple Enhancer Qwen - Rank 64 Version - 2308688
12
+
13
+ **Model Type**: LORA
14
+
15
+ **Base Model**: Qwen
16
+
17
+ **Trigger Words**: None
18
+
19
+ **Tags**: breasts, fix, nipples, style, tits
20
+
21
+ ## Gallery
22
+
23
+ <table>
24
+ <tr>
25
+ <td><img src="https://image.civitai.com/xG1nkqKTMzGDvpLrqFT7WA/d97de5bc-c58c-469b-8e7d-dafd92ea6c17/original=true/105803433.jpeg" width="200"></td>
26
+ </tr>
27
+ </table>
28
+
29
+ ## Description
30
+
31
+ Edit Oct 13:
32
+
33
+ ```
34
+ After several users approached me and mentioned that 2GB is too much for a breasts LoRA (very rightfully so) I have released an additional version that's 1GB (Rank 64), the results are not as good as the full 2GB version but definitely works.
35
+ ```
36
+
37
+ I have done multiple training runs on 2xH200 on RunPod with ranks 16/32/64/128 and ended up uploading the 128 variant as it seems to be generating the best results.
38
+
39
+ Dataset was trained with the following key words:
40
+ tiny/small/medium/large sized areoles
41
+ tiny/small/medium/large sized breasts
42
+ pale/brown/dark/ghost areoles
43
+ hard/erect nipples
44
+
45
+ These definitely help with generating variations in results.
46
+
47
+ Most of my testings were done with my Qwen character LoRAs (none of them had naked images in the dataset)
48
+ I've also did some testing without my character LoRAs and the results were similar.
49
+
50
+ This is not perfect but much better than base Qwen.
51
+
52
+ Join my Discord server for updates on new LoRAs, tips & tricks, Workflows, RunPod templates and the holy right to be close to an amazing charismatic person like myself:
53
+ <https://discord.gg/fyha5Pzm>
54
+
55
+ Enjoy!
56
+
57
+ ---
58
+
59
  Author: [HearmemanAI](https://civitai.com/user/HearmemanAI)
60
 
61
+ Model: [CivitAI Model Page](https://civitai.com/models/2036919?modelVersionId=2308688)
62
+
63
+ Archive: [CivArchive Page](https://civarchive.com/models/2036919?modelVersionId=2308688)
64
 
65
+ <!-- Version: 20260425_upload -->