UnifiedHorusRA commited on
Commit
aa30da7
·
verified ·
1 Parent(s): 0fe0f9c

Upload petals_diss_low_noisev1.0/README.md with huggingface_hub

Browse files
Files changed (1) hide show
  1. petals_diss_low_noisev1.0/README.md +67 -0
petals_diss_low_noisev1.0/README.md ADDED
@@ -0,0 +1,67 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ language:
3
+ - en
4
+ tags:
5
+ - art
6
+ ---
7
+
8
+ # Character petals dissipate
9
+
10
+ **Creator**: [Shu_ShengXia](https://civitai.com/user/Shu_ShengXia)
11
+ **Type**: LORA
12
+ **Base Model**: Wan Video 2.2 I2V-A14B
13
+ **Version**: petals diss low noisev1.0
14
+ **Trigger Words**: `N/A`
15
+
16
+ **Civitai Model ID**: 1874748
17
+ **Civitai Version ID**: 2121971
18
+
19
+ **Stats (at time of fetch for this version)**:
20
+ * Downloads: 124
21
+ * Rating: 0 (0 ratings)
22
+ * Favorites: N/A
23
+
24
+ ---
25
+
26
+ ## 📄 Description (Parent Model)
27
+
28
+ # 模型说明 (Model Description)
29
+ 本 LoRA 模型基于 Wan2.2 视频生成模型训练而成,使用了 20 个视频作为训练数据,总共训练 2000 步。
30
+ This LoRA model is trained on the Wan2.2 video generation model, using 20 videos as the dataset with a total of 2000 training steps.
31
+ # 底模区分 (Base Model Separation)
32
+ 针对 Wan2.2 high noise 和 Wan2.2 low noise 两个底模,分别训练了独立的 LoRA 模型。
33
+ Separate LoRA models were trained for the Wan2.2 high noise and Wan2.2 low noise base models.
34
+ # 使用建议 (Usage Recommendations)
35
+ - 不建议在推理时使用 Lighting 加速,会严重影响视频生成效果。
36
+ Lighting acceleration is not recommended during inference, as it significantly degrades video quality.
37
+ - 除了触发词外,可以在提示词中加入额外的限制条件,例如花瓣颜色、数量、大小等,以获得更可控的生成效果。
38
+ Beyond the trigger words, you may add additional constraints in the prompt (e.g., petal color, amount, size) to achieve more controllable results.
39
+ # 适用场景 (Applicable Scenarios)
40
+ - High noise LoRA:更适合动态效果和大幅度变化(如人物瓦解成花瓣、强烈动作)。
41
+ High noise LoRA: better suited for dynamic effects and drastic changes (e.g., character dissolving into petals, strong motions).
42
+ - Low noise LoRA:更适合保持细节和局部修改(如人脸结构、服饰纹理)。
43
+ Low noise LoRA: better suited for detail preservation and localized edits (e.g., face structure, clothing textures).
44
+ # 提示词扩展 (Prompt Enhancements)
45
+ - 颜色控制:如 "red petals, no white petals"
46
+ Color control: e.g., "red petals, no white petals"
47
+ - 数量与大小:如 "thousands of tiny petals, evenly scattered"
48
+ Quantity & size: e.g., "thousands of tiny petals, evenly scattered"
49
+ - 动态过程:如 "gradually dissolve into petals, petals drifting with wind"
50
+ Dynamic process: e.g., "gradually dissolve into petals, petals drifting with wind"
51
+ - 环境保持:如 "background untouched, petals only from subject"
52
+ Environment preservation: e.g., "background untouched, petals only from subject"
53
+
54
+ ## Civitai Links
55
+
56
+ * **[🔗 View This Version on Civitai →](https://civitai.com/models/1874748?modelVersionId=2121971)**
57
+ * [View Full Model Page →](https://civitai.com/models/1874748)
58
+ * [View Creator Profile →](https://civitai.com/user/Shu_ShengXia)
59
+
60
+ ---
61
+
62
+ ## File Information
63
+
64
+ * **Filename**: `low_noise_100.safetensors`
65
+ * **Size**: 292.59 MB
66
+ * **Hash (AutoV2)**: `4E8BD60BC2`
67
+ * **Hash (SHA256)**: `4E8BD60BC220DC6A63374B3B745CB69207CEEEDF8729F6D0EEB1F6916BD55A11`