Skip to content

Commit a9d3ef4

Browse files
mintlify[bot]mintlify[bot]
authored
Add Wan-Move documentation to Wan 2.1 series (#663)
* Update tutorials/video/wan/wan-move.mdx Co-Authored-By: mintlify[bot] <109931778+mintlify[bot]@users.noreply.github.com> * Update docs.json Co-Authored-By: mintlify[bot] <109931778+mintlify[bot]@users.noreply.github.com> * Update docs.json Co-Authored-By: mintlify[bot] <109931778+mintlify[bot]@users.noreply.github.com> * Update zh-CN/tutorials/video/wan/wan-move.mdx Co-Authored-By: mintlify[bot] <109931778+mintlify[bot]@users.noreply.github.com> * Update tutorials/video/wan/wan-move.mdx Co-Authored-By: mintlify[bot] <109931778+mintlify[bot]@users.noreply.github.com> * Update zh-CN/tutorials/video/wan/wan-move.mdx Co-Authored-By: mintlify[bot] <109931778+mintlify[bot]@users.noreply.github.com> --------- Co-authored-by: mintlify[bot] <109931778+mintlify[bot]@users.noreply.github.com>
1 parent 1e981a9 commit a9d3ef4

File tree

3 files changed

+144
-0
lines changed

3 files changed

+144
-0
lines changed

‎docs.json‎

Lines changed: 2 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -189,6 +189,7 @@
189189
"pages": [
190190
"tutorials/video/wan/wan-video",
191191
"tutorials/video/wan/vace",
192+
"tutorials/video/wan/wan-move",
192193
"tutorials/video/wan/wan-alpha",
193194
"tutorials/video/wan/wan-ati",
194195
"tutorials/video/wan/fun-control",
@@ -832,6 +833,7 @@
832833
"pages": [
833834
"zh-CN/tutorials/video/wan/wan-video",
834835
"zh-CN/tutorials/video/wan/vace",
836+
"zh-CN/tutorials/video/wan/wan-move",
835837
"zh-CN/tutorials/video/wan/wan-alpha",
836838
"zh-CN/tutorials/video/wan/wan-ati",
837839
"zh-CN/tutorials/video/wan/fun-control",

‎tutorials/video/wan/wan-move.mdx‎

Lines changed: 71 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,71 @@
1+
---
2+
title: "ComfyUI Wan-Move Workflow Example"
3+
description: "Wan-Move is a motion-controllable video generation model via latent trajectory guidance, enabling fine-grained point-level motion control for image-to-video generation."
4+
sidebarTitle: "Wan-Move"
5+
---
6+
7+
import UpdateReminder from '/snippets/tutorials/update-reminder.mdx'
8+
9+
**Wan-Move** is a motion-controllable video generation framework developed by Alibaba's Tongyi Lab. It enables users to control object motion in generated videos by specifying point trajectories on the input image, making image-to-video generation more precise and controllable.
10+
11+
**Key Features**:
12+
- **High-Quality 5s 480p Motion Control**: Generates 5-second, 480p videos with fine-grained motion controllability
13+
- **Latent Trajectory Guidance**: Represents motion conditions by propagating first frame features along trajectories
14+
- **Fine-grained Point-level Control**: Object motions are represented with dense point trajectories, enabling precise region-level control
15+
- **No Architecture Changes**: Seamlessly integrates into Wan-I2V-14B without extra motion modules
16+
17+
**Related Links**:
18+
- [GitHub](https://github.com/ali-vilab/Wan-Move)
19+
- [Hugging Face](https://huggingface.co/Ruihang/Wan-Move-14B-480P)
20+
- [Paper](https://arxiv.org/abs/2512.08765)
21+
22+
## Wan-Move image-to-video workflow
23+
24+
<a className="prose" target='_blank' href="https://raw.githubusercontent.com/Comfy-Org/workflow_templates/refs/heads/main/templates/video_wanmove_480p.json" style={{ display: 'inline-block', backgroundColor: '#0078D6', color: '#ffffff', padding: '10px 20px', borderRadius: '8px', borderColor: "transparent", textDecoration: 'none', fontWeight: 'bold', marginRight: '10px'}}>
25+
<p className="prose" style={{ margin: 0, fontSize: "0.8rem" }}>Download JSON Workflow File</p>
26+
</a>
27+
28+
<a className="prose" target='_blank' href="https://cloud.comfy.org/?template=video_wanmove_480p&utm_source=docs" style={{ display: 'inline-block', backgroundColor: '#28a745', color: '#ffffff', padding: '10px 20px', borderRadius: '8px', borderColor: "transparent", textDecoration: 'none', fontWeight: 'bold'}}>
29+
<p className="prose" style={{ margin: 0, fontSize: "0.8rem" }}>Run on ComfyUI Cloud</p>
30+
</a>
31+
32+
<UpdateReminder />
33+
34+
## Model links
35+
36+
**text_encoders**
37+
38+
- [umt5_xxl_fp8_e4m3fn_scaled.safetensors](https://huggingface.co/Comfy-Org/Wan_2.1_ComfyUI_repackaged/resolve/main/split_files/text_encoders/umt5_xxl_fp8_e4m3fn_scaled.safetensors)
39+
40+
**clip_vision**
41+
42+
- [clip_vision_h.safetensors](https://huggingface.co/Comfy-Org/Wan_2.1_ComfyUI_repackaged/resolve/main/split_files/clip_vision/clip_vision_h.safetensors)
43+
44+
**loras**
45+
46+
- [lightx2v_I2V_14B_480p_cfg_step_distill_rank64_bf16.safetensors](https://huggingface.co/Kijai/WanVideo_comfy/resolve/main/Lightx2v/lightx2v_I2V_14B_480p_cfg_step_distill_rank64_bf16.safetensors)
47+
48+
**diffusion_models**
49+
50+
- [Wan21-WanMove_fp8_scaled_e4m3fn_KJ.safetensors](https://huggingface.co/Kijai/WanVideo_comfy_fp8_scaled/resolve/main/WanMove/Wan21-WanMove_fp8_scaled_e4m3fn_KJ.safetensors)
51+
52+
**vae**
53+
54+
- [wan_2.1_vae.safetensors](https://huggingface.co/Comfy-Org/Wan_2.1_ComfyUI_repackaged/resolve/main/split_files/vae/wan_2.1_vae.safetensors)
55+
56+
**Model Storage Location**
57+
58+
```
59+
📂 ComfyUI/
60+
├── 📂 models/
61+
│ ├── 📂 text_encoders/
62+
│ │ └── umt5_xxl_fp8_e4m3fn_scaled.safetensors
63+
│ ├── 📂 clip_vision/
64+
│ │ └── clip_vision_h.safetensors
65+
│ ├── 📂 loras/
66+
│ │ └── lightx2v_I2V_14B_480p_cfg_step_distill_rank64_bf16.safetensors
67+
│ ├── 📂 diffusion_models/
68+
│ │ └── Wan21-WanMove_fp8_scaled_e4m3fn_KJ.safetensors
69+
│ └── 📂 vae/
70+
│ └── wan_2.1_vae.safetensors
71+
```

‎zh-CN/tutorials/video/wan/wan-move.mdx‎

Lines changed: 71 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,71 @@
1+
---
2+
title: "ComfyUI Wan-Move 工作流示例"
3+
description: "Wan-Move 是一个通过潜在轨迹引导实现运动可控视频生成的模型，支持图像到视频生成的精细点级运动控制。"
4+
sidebarTitle: "Wan-Move"
5+
---
6+
7+
import UpdateReminder from '/snippets/tutorials/update-reminder.mdx'
8+
9+
**Wan-Move** 是阿里巴巴通义实验室开发的运动可控视频生成框架。它允许用户通过在输入图像上指定点轨迹来控制生成视频中的物体运动，使图生视频更加精确可控。
10+
11+
**核心特性**：
12+
- **高质量 5 秒 480p 运动控制**：生成 5 秒、480p 分辨率的视频，具有精细的运动可控性
13+
- **潜在轨迹引导**：通过沿轨迹传播首帧特征来表示运动条件
14+
- **精细点级控制**：使用密集点轨迹表示物体运动，实现精确的区域级控制
15+
- **无需架构更改**：无缝集成到 Wan-I2V-14B，无需额外的运动模块
16+
17+
**相关链接**：
18+
- [GitHub](https://github.com/ali-vilab/Wan-Move)
19+
- [Hugging Face](https://huggingface.co/Ruihang/Wan-Move-14B-480P)
20+
- [论文](https://arxiv.org/abs/2512.08765)
21+
22+
## Wan-Move 图生视频工作流
23+
24+
<a className="prose" target='_blank' href="https://raw.githubusercontent.com/Comfy-Org/workflow_templates/refs/heads/main/templates/video_wanmove_480p.json" style={{ display: 'inline-block', backgroundColor: '#0078D6', color: '#ffffff', padding: '10px 20px', borderRadius: '8px', borderColor: "transparent", textDecoration: 'none', fontWeight: 'bold', marginRight: '10px'}}>
25+
<p className="prose" style={{ margin: 0, fontSize: "0.8rem" }}>下载 JSON 工作流文件</p>
26+
</a>
27+
28+
<a className="prose" target='_blank' href="https://cloud.comfy.org/?template=video_wanmove_480p&utm_source=docs" style={{ display: 'inline-block', backgroundColor: '#28a745', color: '#ffffff', padding: '10px 20px', borderRadius: '8px', borderColor: "transparent", textDecoration: 'none', fontWeight: 'bold'}}>
29+
<p className="prose" style={{ margin: 0, fontSize: "0.8rem" }}>在 ComfyUI Cloud 上运行</p>
30+
</a>
31+
32+
<UpdateReminder />
33+
34+
## 模型下载链接
35+
36+
**text_encoders**
37+
38+
- [umt5_xxl_fp8_e4m3fn_scaled.safetensors](https://huggingface.co/Comfy-Org/Wan_2.1_ComfyUI_repackaged/resolve/main/split_files/text_encoders/umt5_xxl_fp8_e4m3fn_scaled.safetensors)
39+
40+
**clip_vision**
41+
42+
- [clip_vision_h.safetensors](https://huggingface.co/Comfy-Org/Wan_2.1_ComfyUI_repackaged/resolve/main/split_files/clip_vision/clip_vision_h.safetensors)
43+
44+
**loras**
45+
46+
- [lightx2v_I2V_14B_480p_cfg_step_distill_rank64_bf16.safetensors](https://huggingface.co/Kijai/WanVideo_comfy/resolve/main/Lightx2v/lightx2v_I2V_14B_480p_cfg_step_distill_rank64_bf16.safetensors)
47+
48+
**diffusion_models**
49+
50+
- [Wan21-WanMove_fp8_scaled_e4m3fn_KJ.safetensors](https://huggingface.co/Kijai/WanVideo_comfy_fp8_scaled/resolve/main/WanMove/Wan21-WanMove_fp8_scaled_e4m3fn_KJ.safetensors)
51+
52+
**vae**
53+
54+
- [wan_2.1_vae.safetensors](https://huggingface.co/Comfy-Org/Wan_2.1_ComfyUI_repackaged/resolve/main/split_files/vae/wan_2.1_vae.safetensors)
55+
56+
**模型存放位置**
57+
58+
```
59+
📂 ComfyUI/
60+
├── 📂 models/
61+
│ ├── 📂 text_encoders/
62+
│ │ └── umt5_xxl_fp8_e4m3fn_scaled.safetensors
63+
│ ├── 📂 clip_vision/
64+
│ │ └── clip_vision_h.safetensors
65+
│ ├── 📂 loras/
66+
│ │ └── lightx2v_I2V_14B_480p_cfg_step_distill_rank64_bf16.safetensors
67+
│ ├── 📂 diffusion_models/
68+
│ │ └── Wan21-WanMove_fp8_scaled_e4m3fn_KJ.safetensors
69+
│ └── 📂 vae/
70+
│ └── wan_2.1_vae.safetensors
71+
```

0 commit comments

Comments
 (0)