Sentinel7 commited on
Commit
31dc66b
·
verified ·
1 Parent(s): bd0b089

Upload lora/povnsfw-v3-complete_README.md with huggingface_hub

Browse files
Files changed (1) hide show
  1. lora/povnsfw-v3-complete_README.md +54 -0
lora/povnsfw-v3-complete_README.md ADDED
@@ -0,0 +1,54 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: other
3
+ tags:
4
+ - concept
5
+ - ltx2
6
+ - nsfw
7
+ - porn
8
+ - pov
9
+ ---
10
+
11
+ # POV NSFW LTX2 (Updated v3.0) - v3.0 - 2642615
12
+
13
+ **Model Type**: LORA
14
+
15
+ **Base Model**: LTXV2
16
+
17
+ **Trigger Words**: None
18
+
19
+ **Tags**: concept, ltx2, nsfw, porn, pov
20
+
21
+ ## Description
22
+
23
+ **v3.0:** 24k steps trained on a cleaner set of 132 POV videos.
24
+
25
+ Trained concepts: boobjobs, cumshots, handjobs, vaginal sex (front/back), licking and blowjobs.
26
+
27
+ Significantly improved dialog and speech issues.
28
+
29
+ I'm working on NSFW merges on my Huggingface, which will be better than using this LORA alone.
30
+
31
+ **v2.0 doesn't exist, it was a failed run.**
32
+
33
+ **v1.0:** 16k steps trained on 126 random POV pornographic video/audio data. Used ai-trainer. Rank 64 LORA.
34
+
35
+ Cumshots, handjobs, vaginal sex, boobjobs, blowjobs and some licking included in the dataset. Overall works pretty good, but not great.
36
+
37
+ Only use with I2V, which the model was trained with. First to last frame for absolute best results. T2V probably sucks.
38
+
39
+ I'm working on an actual merge with other good NSFW LORAs. See my workflows and merges here: <https://huggingface.co/Phr00t/LTX2-Rapid-Merges>
40
+
41
+ My example was using my "DoEverything" workflow with this LORA at 1.0 strength on top of my "v3 SFW" LTX2 merge.
42
+
43
+ **TRAINING TIPS:** Loss graphs are kinda garbage and I didn't really see a drop in error until after ~8k steps, and loss only went from like 1.05 to 0.8, yet results are pretty good. Short videos that focus on a specific action seem to work pretty good with clear prompting of both visuals, motion and audio. Set "caption dropout" to 0 (ai-toolkit defaults to 0.05) and use the "experimental" differential guidance set to 2.5 (at least those are the settings I used). I'd focus far more on video data than image data.
44
+ **Want to help me pay for runpod time?** Paypal donations accepted at phr00t at gmail dot com!
45
+
46
+ ---
47
+
48
+ Author: [Phr00t_](https://civitai.com/user/Phr00t_)
49
+
50
+ Model: [CivitAI Model Page](https://civitai.com/models/2334739?modelVersionId=2642615)
51
+
52
+ Archive: [CivArchive Page](https://civarchive.com/models/2334739?modelVersionId=2642615)
53
+
54
+ <!-- Version: 20260428_single_create -->