Sentinel7 commited on
Commit
13864b5
·
verified ·
1 Parent(s): 3ee0150

Upload 2198068/2699576/README.md with huggingface_hub

Browse files
Files changed (1) hide show
  1. 2198068/2699576/README.md +32 -2
2198068/2699576/README.md CHANGED
@@ -2,9 +2,39 @@
2
  license: other
3
  tags:
4
  - civitai
 
 
 
5
  ---
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
6
  Author: [Cellsa](https://civitai.com/user/Cellsa)
7
 
8
- Model: [https://civitai.com/models/2198068?modelVersionId=2699576](https://civitai.com/models/2198068?modelVersionId=2699576)
 
 
9
 
10
- Mirror: [https://civarchive.com/models/2198068?modelVersionId=2699576](https://civarchive.com/models/2198068?modelVersionId=2699576)
 
2
  license: other
3
  tags:
4
  - civitai
5
+ - silicone
6
+ - fake boobs
7
+ - concept
8
  ---
9
+
10
+ # High Profile Breast Implants - 2699576
11
+
12
+ **Model Type**: LORA
13
+
14
+ **Base Model**: Flux.2 Klein 9B-base
15
+
16
+ **Trigger Words**: implants
17
+
18
+ **Tags**: silicone, fake boobs, concept
19
+
20
+ ## Description
21
+
22
+ The goal is to show high profile, round implants in your generations.
23
+
24
+ For Klein9Base - initial attempt. Seems to work well around 0.5 to 1 and above in strength. Haven't had a chance to see if it works well with other LORAs.
25
+
26
+ For V3 Zbase: Much better than the previous versions. Use this one. This is technically a LOKR, used V1's dataset. Works well with and without clothes, use captions of covered and clothed to help guide the model. V3 works at strengths up to 2 pretty well, depends how much you want to go into "ask your surgeon for a refund" territory.
27
+
28
+ For V2: More of a quick attempt to see what a larger dataset without captioning gets me while trying out the base model for LORAs. I will try V1's dataset/captioning at some point for a 1:1. Strength is same as the distilled model's lora. Seems overall to do a lot better but still not perfect.
29
+
30
+ For V1:Trained on 25 1024x1024 image dataset, captioned by LLM then edited by hand. Largely avoids faces. Used the first gen adapter on. For the V1 lora, I have found strength seems to be best between 0.40 - 0.8. Despite having plenty of areolae in its dataset, it does struggle, especially with nipples. It'll get it right eventually.
31
+
32
+ ---
33
+
34
  Author: [Cellsa](https://civitai.com/user/Cellsa)
35
 
36
+ Model: [CivitAI Model Page](https://civitai.com/models/2198068?modelVersionId=2699576)
37
+
38
+ Archive: [CivArchive Page](https://civarchive.com/models/2198068?modelVersionId=2699576)
39
 
40
+ <!-- Version: 20260422_v4_update -->