Sentinel7 commited on
Commit
08ba6d8
·
verified ·
1 Parent(s): d41b99b

Upload 2655839/2982264/README.md with huggingface_hub

Browse files
Files changed (1) hide show
  1. 2655839/2982264/README.md +76 -0
2655839/2982264/README.md ADDED
@@ -0,0 +1,76 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: other
3
+ tags:
4
+ - blowjob
5
+ - cock lick
6
+ - cock worship
7
+ - concept
8
+ - handjob
9
+ - oral
10
+ ---
11
+
12
+ # Worship It - I2V - Low - 2982264
13
+
14
+ **Model Type**: LORA
15
+
16
+ **Base Model**: Wan Video 2.2 I2V-A14B
17
+
18
+ **Trigger Words**: None
19
+
20
+ **Tags**: blowjob, cock lick, cock worship, concept, handjob, oral
21
+
22
+ ## Gallery
23
+
24
+ <table>
25
+ <tr>
26
+ <td><video src="https://image.civitai.com/xG1nkqKTMzGDvpLrqFT7WA/1e8a84c4-3c84-4a43-bd6d-5603a1cb31f0/original=true/132021576.mp4" width="200" controls muted autoplay loop></video></td>
27
+ <td><video src="https://image.civitai.com/xG1nkqKTMzGDvpLrqFT7WA/841355ef-eed3-43e9-b651-4d71b2fd73bb/original=true/132021575.mp4" width="200" controls muted autoplay loop></video></td>
28
+ </tr>
29
+ </table>
30
+
31
+ ## Description
32
+
33
+ An attempt to make a lora focused on worshiping big cocks. It was trained on 69 clips (not on purpose, the 70th clip had a hard cut so it was cut from the dataset last minute). Never trained a motion Lora before.
34
+
35
+ **T2V is trained on Wan 2.2 T2V fp16 model
36
+ I2V is trained on Wan 2.2 I2V fp16model**
37
+
38
+ I started training the model as an I2V because those lora's always gave me better results even with T2V. Due to difficulties renting a GPU, I decided to try a different service to compare speed and price so I opted to train the T2V on the second service. I figured it it worked well enough I'd throw them up on Civitai.
39
+
40
+ I believe the workflow used to generate the samples was created by a former user - playtime\_ai
41
+ It utilizes the MoE ksampler.
42
+ I get best results using the following settings:
43
+
44
+ Sampler - er\_sde
45
+ Scheduler - beta57
46
+ Shift - 8
47
+ Steps - 8
48
+ Lightning - [i2v\_lightx2v\_4step\_1022](https://huggingface.co/lightx2v/Wan2.2-Distill-Loras/tree/main)
49
+ Str - 1 on both high and low.
50
+ (Yes, I use the i2v lightning lora for T2V generations. I don't know why, but it always gives more more dynamic and realistic results).
51
+
52
+ Trained with the following trigger words:
53
+
54
+ cock\_worship
55
+ cock\_lick
56
+ cock\_slap
57
+ blowjob
58
+ deepthroat
59
+ titfuck
60
+ handjob
61
+
62
+ Does somethings better than others. Slapping and titfuck it struggles with. Occasionally does some fun body horror.
63
+
64
+ **Follow up edit**: I've added some clarity to the description and will attach a zip file to the T2V Low noise model for all the captions used for Lora training. They all follow the same structure - start with the trigger word(s) featured in the video trained followed by solely focusing on the movement during the video. All videos were 320x320, 81 frames, 16 FPS.
65
+
66
+ Generate responsibly.
67
+
68
+ ---
69
+
70
+ Author: [alternative_penguin](https://civitai.com/user/alternative_penguin)
71
+
72
+ Model: [CivitAI Model Page](https://civitai.com/models/2655839?modelVersionId=2982264)
73
+
74
+ Archive: [CivArchive Page](https://civarchive.com/models/2655839?modelVersionId=2982264)
75
+
76
+ <!-- Version: 20260528_upload -->