Sentinel7 commited on
Commit
0b61378
·
verified ·
1 Parent(s): 22f6c0d

Upload 1905415/2156688/README.md with huggingface_hub

Browse files
Files changed (1) hide show
  1. 1905415/2156688/README.md +45 -3
1905415/2156688/README.md CHANGED
@@ -1,11 +1,53 @@
1
-
2
  ---
3
  license: other
4
  tags:
5
  - civitai
 
 
 
6
  ---
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
7
  Author: [tigertakato](https://civitai.com/user/tigertakato)
8
 
9
- Model: [https://civitai.com/models/1905415?modelVersionId=2156688](https://civitai.com/models/1905415?modelVersionId=2156688)
 
 
10
 
11
- Mirror: [https://civarchive.com/models/1905415?modelVersionId=2156688](https://civarchive.com/models/1905415?modelVersionId=2156688)
 
 
1
  ---
2
  license: other
3
  tags:
4
  - civitai
5
+ - japanese
6
+ - style
7
+ - woman
8
  ---
9
+
10
+ # Virtual Japanese Woman RIAN(wan) - 2156688
11
+
12
+ **Model Type**: LORA
13
+
14
+ **Base Model**: Wan Video 14B t2v
15
+
16
+ **Trigger Words**: None
17
+
18
+ **Tags**: japanese, style, woman
19
+
20
+ ## Description
21
+
22
+ 🌸 Virtual Japanese Woman RIAN
23
+ -----------------------------
24
+
25
+ 💡 **Note**
26
+ In my environment, when **HighNoise and LowNoise were trained separately**, the **face** turned out **slightly different**.
27
+ Therefore, as with Wan2.1, please use a **single merged LoRA**, applied at **1.0 for both HighNoise and LowNoise**, when generating videos or images.
28
+ If you **don’t use both**, it hasn’t been thoroughly tested, but **LowNoise alone should work fine**.
29
+ **Regarding the face**, I’ve made substantial adjustments; however, overseas users—and even people from East Asia—may perceive them as only subtle differences. Thank you for your understanding.
30
+
31
+ ---
32
+
33
+ Trained on 1024x1536 images to reproduce a photorealistic Japanese woman style named **RIAN**.
34
+ Not a glamorous idol, but rather the vibe of a *“cute woman you might encounter in everyday Japan.”*
35
+
36
+ 🔹 **Trigger word:** `rian` (likely works even without the trigger)
37
+ 🔹 **Recommended weight:** 0.7 – 1.0
38
+
39
+ ⚠️ This character is fictional and does not exist in reality.
40
+ ⚠️ Facial appearance may vary depending on other LoRAs or workflows used.
41
+ ⚠️ Highly prompt-dependent: please refine features via prompt (e.g., bangs, blush, lip gloss, gaze, angle, expressions).
42
+
43
+ 🟢 Limited testing showed good results. As it’s still in an experimental phase, generation may occasionally fail.
44
+
45
+ ---
46
+
47
  Author: [tigertakato](https://civitai.com/user/tigertakato)
48
 
49
+ Model: [CivitAI Model Page](https://civitai.com/models/1905415?modelVersionId=2156688)
50
+
51
+ Archive: [CivArchive Page](https://civarchive.com/models/1905415?modelVersionId=2156688)
52
 
53
+ <!-- Version: 20260422_v4_update -->