UnifiedHorusRA commited on
Commit
5a07dde
·
verified ·
1 Parent(s): df98c40

Upload Wan_2.2_T2V_Low/README.md with huggingface_hub

Browse files
Files changed (1) hide show
  1. Wan_2.2_T2V_Low/README.md +60 -0
Wan_2.2_T2V_Low/README.md ADDED
@@ -0,0 +1,60 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ language:
3
+ - en
4
+ tags:
5
+ - art
6
+ ---
7
+
8
+ # BBC Ride Wan (2.2!)
9
+
10
+ **Creator**: [dngstn32](https://civitai.com/user/dngstn32)
11
+ **Type**: LORA
12
+ **Base Model**: Wan Video 2.2 T2V-A14B
13
+ **Version**: Wan 2.2 (T2V Low)
14
+ **Trigger Words**: `N/A`
15
+
16
+ **Civitai Model ID**: 1452829
17
+ **Civitai Version ID**: 2105553
18
+
19
+ **Stats (at time of fetch for this version)**:
20
+ * Downloads: 2009
21
+ * Rating: 0 (0 ratings)
22
+ * Favorites: N/A
23
+
24
+ ---
25
+
26
+ ## 📄 Description (Parent Model)
27
+
28
+ Wan 2.2!
29
+ Re-trained the dataset on Wan 2.2, make sure to grab BOTH Loras (High and Low)!
30
+ Getting great results with
31
+ K3NK
32
+ 's workflow -
33
+ https://civitai.com/models/1824027/wan-22-t2v-i2v4-stepskijais-wrapper-workflowk3nk
34
+ Update 6.17
35
+ I realized while trying to improve this LoRA that I never uploaded a T2V version, so... here it is. Enjoy!
36
+ -- -- --
37
+ My second LoRA... I've made some drastic changes to my captioning approach, and the results show some nice improvement.
38
+ Please share anything you make with this, I'd love to see some better prompts!
39
+ This was trained on WAN 14B I2V, on 45 videos normalized to 480P / 24FPS and trimmed to 3 seconds using diffusion-pipe. However, it works okay with the T2V model, and I've included some examples from that.
40
+ My captioning approach:
41
+ 45 videos, resized to 480P, 3 seconds, 24FPS.
42
+ Ran each one through
43
+ ComfyUI_Qwen2-VL-Instruct
44
+ to generate a base video description, but this unfortunately doesn't pick up on any NSFW bits. This usually took a few tries on the same image, since the LLM almost seemed "disgusted" by the suggestion. :D
45
+ Grabbed my "favorite" frame and ran that through Joy Caption 2, then I manually combined the Qwen description and the Joy Caption Two caption to make the final .txt file.
46
+
47
+ ## Civitai Links
48
+
49
+ * **[🔗 View This Version on Civitai →](https://civitai.com/models/1452829?modelVersionId=2105553)**
50
+ * [View Full Model Page →](https://civitai.com/models/1452829)
51
+ * [View Creator Profile →](https://civitai.com/user/dngstn32)
52
+
53
+ ---
54
+
55
+ ## File Information
56
+
57
+ * **Filename**: `bbcRide_wan22_T2V_low_e20.safetensors`
58
+ * **Size**: 292.59 MB
59
+ * **Hash (AutoV2)**: `E2D9E03C6D`
60
+ * **Hash (SHA256)**: `E2D9E03C6D30EC26092406EE2F5DC26AAFA8ACDEE3C8ECDD158CE2ECDD57AFDF`