Sentinel7 commited on
Commit
5784565
·
verified ·
1 Parent(s): f6a3589

Upload 2011853/2302508/README.md with huggingface_hub

Browse files
Files changed (1) hide show
  1. 2011853/2302508/README.md +46 -3
2011853/2302508/README.md CHANGED
@@ -1,11 +1,54 @@
1
-
2
  ---
3
  license: other
4
  tags:
5
  - civitai
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
6
  ---
 
7
  Author: [swan](https://civitai.com/user/swan)
8
 
9
- Model: [https://civitai.com/models/2011853?modelVersionId=2302508](https://civitai.com/models/2011853?modelVersionId=2302508)
 
 
10
 
11
- Mirror: [https://civarchive.com/models/2011853?modelVersionId=2302508](https://civarchive.com/models/2011853?modelVersionId=2302508)
 
 
1
  ---
2
  license: other
3
  tags:
4
  - civitai
5
+ - concept
6
+ - ejaculation
7
+ - futanari
8
+ - cumshot
9
+ - masturbation
10
+ ---
11
+
12
+ # Futa-Masturbation Cumshot - 2302508
13
+
14
+ **Model Type**: LORA
15
+
16
+ **Base Model**: Wan Video 2.2 I2V-A14B
17
+
18
+ **Trigger Words**: None
19
+
20
+ **Tags**: concept, ejaculation, futanari, cumshot, masturbation
21
+
22
+ ## Description
23
+
24
+ I created this LoRA by referring to [This](https://civitai.com/models/1368557/masturbation-cumshot-for-wan-i2v-14b).
25
+ I would like to pay my respects to the creator of that LoRA.
26
+
27
+ First of all, I did not train on any facial data. As far as I know, there are already enough (or many) facial-related LoRAs (such as *cum on face*, cum*\_in\_mouth*, etc.).
28
+
29
+ If want facial content, please use another great LoRA or use this one together with it (I have not tested the results when using them together).
30
+
31
+ ***(NEW)***
32
+ Using the **TripleKsampler** node gives even better results. I highly recommend trying it out.
33
+ <https://github.com/VraethrDalkr/ComfyUI-TripleKSampler>
34
+
35
+ **Prompt used:** **She moves hand rapidly up and down the shaft of her penis and she ejaculates a thick and huge amount white sticky liquid into air repeatedly from her penis.**
36
+
37
+ I used 20 videos of 80 frames / 5 seconds each as the dataset.
38
+
39
+ Regarding liquid ejection, compared to Wan 2.1 the results are different, and it seems to have become more difficult to generate. However, if you use the workflow of the video I uploaded as it is, the results should not be bad.
40
+
41
+ The noise issue in the **previous** **High\_noise** has been fixed, and older versions have been removed. The noise no longer occurs, and 121-frame sequences are now supported.
42
+ It might also be a good idea to adjust the lightX lora and This lora weights, or change the prompt, to create even better results.
43
+
44
+ **Future Plan: Once Wan 2.5 is released, I will make updating this my top priority.**
45
+
46
  ---
47
+
48
  Author: [swan](https://civitai.com/user/swan)
49
 
50
+ Model: [CivitAI Model Page](https://civitai.com/models/2011853?modelVersionId=2302508)
51
+
52
+ Archive: [CivArchive Page](https://civarchive.com/models/2011853?modelVersionId=2302508)
53
 
54
+ <!-- Version: 20260422_v4_update -->