Sentinel7 commited on
Commit
0d35516
·
verified ·
1 Parent(s): 596e65f

Upload 2429545/2731730/README.md with huggingface_hub

Browse files
Files changed (1) hide show
  1. 2429545/2731730/README.md +43 -2
2429545/2731730/README.md CHANGED
@@ -2,9 +2,50 @@
2
  license: other
3
  tags:
4
  - civitai
 
 
 
 
 
 
 
5
  ---
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
6
  Author: [qdr1en](https://civitai.com/user/qdr1en)
7
 
8
- Model: [https://civitai.com/models/2429545?modelVersionId=2731730](https://civitai.com/models/2429545?modelVersionId=2731730)
 
 
9
 
10
- Mirror: [https://civarchive.com/models/2429545?modelVersionId=2731730](https://civarchive.com/models/2429545?modelVersionId=2731730)
 
2
  license: other
3
  tags:
4
  - civitai
5
+ - i2v
6
+ - facial
7
+ - cumshot
8
+ - bukkake
9
+ - concept
10
+ - cum
11
+ - wan
12
  ---
13
+
14
+ # sh00tz : series of cumshots - 2731730
15
+
16
+ **Model Type**: LORA
17
+
18
+ **Base Model**: Wan Video 2.2 I2V-A14B
19
+
20
+ **Trigger Words**: sh00tz
21
+
22
+ **Tags**: i2v, facial, cumshot, bukkake, concept, cum, wan
23
+
24
+ ## Description
25
+
26
+ A full bukkake in just 5 seconds.
27
+
28
+ Trained on 24 81-frames square videos, all of which were structured this way:
29
+ initial state (5 frames) => cumshots (4x16 frames) => end state (12 frames).
30
+
31
+ Just start your prompt with the keyword "**sh00tz**", and wan will know what to do.
32
+
33
+ On the high-noise model: works best without any lightx2v lora and cfg at 3.5 (tested with 4/8 steps): semen looks more liquid and natural.
34
+
35
+ On the low-noise model: add dr34ml4y LoRa (for example, at 0.7 strength) for better realistic outcomes.
36
+
37
+ Consistency is relatively good most of times, so you should see a coherent progression between cuts.
38
+
39
+ Wan may draw a weird background floor. You can add "within the same background" in your prompt and/or "background changes" in the negative prompt to mitigate that effect, or just describe the location corresponding to your source image.
40
+
41
+ Since the training data focused mostly on the face, use a vertical format (like 9:16 or even 1:2) to include more of the woman's body within the frame.
42
+
43
+ ---
44
+
45
  Author: [qdr1en](https://civitai.com/user/qdr1en)
46
 
47
+ Model: [CivitAI Model Page](https://civitai.com/models/2429545?modelVersionId=2731730)
48
+
49
+ Archive: [CivArchive Page](https://civarchive.com/models/2429545?modelVersionId=2731730)
50
 
51
+ <!-- Version: 20260422_v4_update -->