Sentinel7 commited on
Commit
016bd41
·
verified ·
1 Parent(s): 70857d5

Upload 2610321/2930993/README.md with huggingface_hub

Browse files
Files changed (1) hide show
  1. 2610321/2930993/README.md +58 -0
2610321/2930993/README.md ADDED
@@ -0,0 +1,58 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: other
3
+ tags:
4
+ - concept
5
+ - furry
6
+ - ltx
7
+ - ltx 2.3
8
+ - nsfw
9
+ - reasoning
10
+ ---
11
+
12
+ # LTX 2.3 - Multi Step Video Reasoning lora VBVR - v0.1 I2V - 2930993
13
+
14
+ **Model Type**: LORA
15
+
16
+ **Base Model**: LTXV 2.3
17
+
18
+ **Trigger Words**: None
19
+
20
+ **Tags**: concept, furry, ltx, ltx 2.3, nsfw, reasoning
21
+
22
+ ## Gallery
23
+
24
+ <table>
25
+ <tr>
26
+ <td><video src="https://image.civitai.com/xG1nkqKTMzGDvpLrqFT7WA/1e7437aa-3799-4ac6-92b5-f3719cd4ebc0/original=true/130167608.mp4" width="200" controls muted autoplay loop></video></td>
27
+ </tr>
28
+ </table>
29
+
30
+ ## Description
31
+
32
+ **EXPERIMENTAL**
33
+ ----------------
34
+
35
+ This is a multi step reasoning lora trained on a subset of of the [**VBVR-MultiStep dataset.**](https://huggingface.co/datasets/Video-Reason/VBVR-MultiStep)
36
+ ------------------------------------------------------------------------------------------------------------------------------------------------------------
37
+
38
+ **V0.1 is trained on a 250 video subset from the Physics portion of the dataset. This lora was trained on my LTX 2.3 reasoning merge model that I made by merging my reasoning lora into. This lora stacks well with my other reasoning lora and physics lora and you should notice that it follows prompts better and object to object interactions are better as well.**
39
+ --------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------
40
+
41
+ **Currently training a version on 25k videos from the dataset and one on a few thousand.**
42
+ ------------------------------------------------------------------------------------------
43
+
44
+ **I highly recommend using the Sulfur 2 Base model or its rank 768 lora as it makes NSFW generations a ton better.**
45
+ --------------------------------------------------------------------------------------------------------------------
46
+
47
+ **Works the same on realistic and non NSFW generations**
48
+ --------------------------------------------------------
49
+
50
+ ---
51
+
52
+ Author: [MisticRain69](https://civitai.com/user/MisticRain69)
53
+
54
+ Model: [CivitAI Model Page](https://civitai.com/models/2610321?modelVersionId=2930993)
55
+
56
+ Archive: [CivArchive Page](https://civarchive.com/models/2610321?modelVersionId=2930993)
57
+
58
+ <!-- Version: 20260510_upload -->