Skip to content

Commit 3d874e1

Browse files
authored
Update fun camera docs (#176)
* Update fun camera docs * Update Chinese VACE docs
1 parent c1dc250 commit 3d874e1

File tree

7 files changed

+254
-2
lines changed

7 files changed

+254
-2
lines changed

docs.json

Lines changed: 2 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -124,6 +124,7 @@
124124
"tutorials/video/wan/wan-video",
125125
"tutorials/video/wan/vace",
126126
"tutorials/video/wan/fun-control",
127+
"tutorials/video/wan/fun-camera",
127128
"tutorials/video/wan/fun-inp",
128129
"tutorials/video/wan/wan-flf"
129130
]
@@ -583,6 +584,7 @@
583584
"pages": [
584585
"zh-CN/tutorials/video/wan/wan-video",
585586
"zh-CN/tutorials/video/wan/fun-control",
587+
"zh-CN/tutorials/video/wan/fun-camera",
586588
"zh-CN/tutorials/video/wan/fun-inp",
587589
"zh-CN/tutorials/video/wan/wan-flf",
588590
"zh-CN/tutorials/video/wan/vace"
946 KB
Loading
897 KB
Loading

tutorials/video/wan/fun-camera.mdx

Lines changed: 125 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,125 @@
1+
---
2+
title: "ComfyUI Wan2.1 Fun Camera Official Examples"
3+
description: "This guide demonstrates how to use Wan2.1 Fun Camera in ComfyUI for video generation"
4+
sidebarTitle: "Wan2.1 Fun Camera"
5+
---
6+
7+
import UpdateReminder from '/snippets/tutorials/update-reminder.mdx'
8+
9+
## About Wan2.1 Fun Camera
10+
11+
**Wan2.1 Fun Camera** is a video generation project launched by the Alibaba team, focusing on controlling video generation effects through camera motion.
12+
13+
**Model Weights Download**:
14+
- [14B Version](https://huggingface.co/alibaba-pai/Wan2.1-Fun-V1.1-14B-Control-Camera)
15+
- [1.3B Version](https://huggingface.co/alibaba-pai/Wan2.1-Fun-V1.1-1.3B-Control-Camera)
16+
17+
**Code Repository**: [VideoX-Fun](https://github.com/aigc-apps/VideoX-Fun)
18+
19+
**ComfyUI now natively supports the Wan2.1 Fun Camera model**.
20+
21+
<UpdateReminder/>
22+
23+
## Model Installation
24+
25+
These models only need to be installed once. Additionally, model download information is included in the corresponding workflow images, so you can choose your preferred way to download the models.
26+
27+
All of the following models can be found at [Wan_2.1_ComfyUI_repackaged](https://huggingface.co/Comfy-Org/Wan_2.1_ComfyUI_repackaged)
28+
29+
**Diffusion Models** choose either 1.3B or 14B:
30+
- [wan2.1_fun_camera_v1.1_1.3B_bf16.safetensors](https://huggingface.co/Comfy-Org/Wan_2.1_ComfyUI_repackaged/resolve/main/split_files/diffusion_models/wan2.1_fun_camera_v1.1_1.3B_bf16.safetensors)
31+
- [wan2.1_fun_camera_v1.1_14B_bf16.safetensors](https://huggingface.co/Comfy-Org/Wan_2.1_ComfyUI_repackaged/resolve/main/split_files/diffusion_models/wan2.1_fun_camera_v1.1_14B_bf16.safetensors)
32+
33+
If you've used Wan2.1 related models before, you should already have the following models. If not, please download them:
34+
35+
**Text Encoders** choose one:
36+
- [umt5_xxl_fp16.safetensors](https://huggingface.co/Comfy-Org/Wan_2.1_ComfyUI_repackaged/resolve/main/split_files/text_encoders/umt5_xxl_fp16.safetensors)
37+
- [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)
38+
39+
**VAE**
40+
- [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)
41+
42+
**CLIP Vision**
43+
- [clip_vision_h.safetensors](https://huggingface.co/Comfy-Org/Wan_2.1_ComfyUI_repackaged/resolve/main/split_files/clip_vision/clip_vision_h.safetensors)
44+
45+
File Storage Location:
46+
47+
```
48+
📂 ComfyUI/
49+
├── 📂 models/
50+
│ ├── 📂 diffusion_models/
51+
│ │ ├── wan2.1_fun_camera_v1.1_1.3B_bf16.safetensors # 1.3B version
52+
│ │ └── wan2.1_fun_camera_v1.1_14B_bf16.safetensors # 14B version
53+
│ ├── 📂 text_encoders/
54+
│ │ └── umt5_xxl_fp8_e4m3fn_scaled.safetensors
55+
│ ├── 📂 vae/
56+
│ │ └── wan_2.1_vae.safetensors
57+
│ └── 📂 clip_vision/
58+
│ └── clip_vision_h.safetensors
59+
```
60+
61+
## ComfyUI Wan2.1 Fun Camera 1.3B Native Workflow Example
62+
63+
### 1. Workflow Related Files Download
64+
65+
#### 1.1 Workflow File
66+
67+
Download the video below and drag it into ComfyUI to load the corresponding workflow:
68+
69+
<video
70+
controls
71+
className="w-full aspect-video"
72+
src="https://raw.githubusercontent.com/Comfy-Org/example_workflows/refs/heads/main/video/wan/fun-camera/v1.1/wan2.1_fun_camera_1.3B.mp4"
73+
></video>
74+
75+
<a className="prose" target='_blank' href="https://raw.githubusercontent.com/Comfy-Org/example_workflows/refs/heads/main/video/wan/fun-camera/v1.1/wan2.1_fun_camera_1.3B.json" style={{ display: 'inline-block', backgroundColor: '#0078D6', color: '#ffffff', padding: '10px 20px', borderRadius: '8px', borderColor: "transparent", textDecoration: 'none', fontWeight: 'bold'}}>
76+
<p className="prose" style={{ margin: 0, fontSize: "0.8rem" }}>Download Json Workflow File</p>
77+
</a>
78+
79+
<Note>
80+
If you want to use the 14B version, simply replace the model file with the 14B version, but please be aware of the VRAM requirements.
81+
</Note>
82+
83+
#### 1.2 Input Image Download
84+
85+
Please download the image below, which we will use as the starting frame:
86+
87+
![Input Reference Image](https://raw.githubusercontent.com/Comfy-Org/example_workflows/refs/heads/main/video/wan/fun-camera/v1.1/wan2.1_fun_camera_1.3B_input.jpg)
88+
89+
### 2. Complete the Workflow Step by Step
90+
91+
![Wan2.1 Fun Camera Workflow Steps](/images/tutorial/video/wan/wan2-1-fun-camera-1-3b-step-guide.jpg)
92+
93+
1. Ensure the correct version of model file is loaded:
94+
- 1.3B version: `wan2.1_fun_camera_v1.1_1.3B_bf16.safetensors`
95+
- 14B version: `wan2.1_fun_camera_v1.1_14B_bf16.safetensors`
96+
2. Ensure the `Load CLIP` node has loaded `umt5_xxl_fp8_e4m3fn_scaled.safetensors`
97+
3. Ensure the `Load VAE` node has loaded `wan_2.1_vae.safetensors`
98+
4. Ensure the `Load CLIP Vision` node has loaded `clip_vision_h.safetensors`
99+
5. Upload the starting frame to the `Load Image` node
100+
6. Modify the Prompt if you're using your own input image
101+
7. Set camera motion in the `WanCameraEmbedding` node
102+
8. Click the `Run` button or use the shortcut `Ctrl(cmd) + Enter` to execute generation
103+
104+
## ComfyUI Wan2.1 Fun Camera 14B Workflow and Input Image
105+
106+
<video
107+
controls
108+
className="w-full aspect-video"
109+
src="https://raw.githubusercontent.com/Comfy-Org/example_workflows/refs/heads/main/video/wan/fun-camera/v1.1/wan2.1_fun_camera_14B.mp4"
110+
></video>
111+
112+
<a className="prose" target='_blank' href="https://raw.githubusercontent.com/Comfy-Org/example_workflows/refs/heads/main/video/wan/fun-camera/v1.1/wan2.1_fun_camera_14B.json" style={{ display: 'inline-block', backgroundColor: '#0078D6', color: '#ffffff', padding: '10px 20px', borderRadius: '8px', borderColor: "transparent", textDecoration: 'none', fontWeight: 'bold'}}>
113+
<p className="prose" style={{ margin: 0, fontSize: "0.8rem" }}>Download Json Workflow File</p>
114+
</a>
115+
116+
**Input Image**
117+
![Input Image](https://raw.githubusercontent.com/Comfy-Org/example_workflows/refs/heads/main/video/wan/fun-camera/v1.1/wan2.1_fun_camera_14B_input.jpg)
118+
119+
## Performance Reference
120+
121+
**1.3B Version**:
122+
- 512×512 resolution on RTX 4090 takes about 72 seconds to generate 81 frames
123+
124+
**14B Version**:
125+
- RTX4090 24GB VRAM may experience insufficient memory when generating 512×512 resolution, and memory issues have also occurred on A100 when using larger sizes

tutorials/video/wan/vace.mdx

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -105,7 +105,7 @@ Download the video below and drag it into ComfyUI to load the corresponding work
105105

106106
### 2. Complete the Workflow Step by Step
107107

108-
![](/images/tutorial/video/wan/wan-vace-t2v-step-guide.jpg)
108+
![image](/images/tutorial/video/wan/wan-vace-t2v-step-guide.jpg)
109109

110110
Please follow the numbered steps in the image to ensure smooth workflow execution
111111

Lines changed: 125 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,125 @@
1+
---
2+
title: "ComfyUI Wan2.1 Fun Camera 官方原生示例"
3+
description: "本文介绍了如何在 ComfyUI 中使用 Wan2.1 Fun Camera 完成视频生成"
4+
sidebarTitle: "Wan2.1 Fun Camera"
5+
---
6+
7+
import UpdateReminder from '/snippets/zh/tutorials/update-reminder.mdx'
8+
9+
## 关于 Wan2.1 Fun Camera
10+
11+
**Wan2.1 Fun Camera** 是阿里团队推出的视频生成项目,专注于通过摄像机运动来控制视频生成效果。
12+
13+
**模型权重下载地址**
14+
- [14B 版本](https://huggingface.co/alibaba-pai/Wan2.1-Fun-V1.1-14B-Control-Camera)
15+
- [1.3B 版本](https://huggingface.co/alibaba-pai/Wan2.1-Fun-V1.1-1.3B-Control-Camera)
16+
17+
**代码仓库**[VideoX-Fun](https://github.com/aigc-apps/VideoX-Fun)
18+
19+
**目前 ComfyUI 已原生支持了 Wan2.1 Fun Camera 模型**
20+
21+
<UpdateReminder/>
22+
23+
## 相关模型安装
24+
25+
这些模型你仅需要安装一次,另外在对应的工作流图片中也包含了模型下载信息,你可以选择你喜欢的方式下载模型。
26+
27+
下面的所有模型你可以在 [Wan_2.1_ComfyUI_repackaged](https://huggingface.co/Comfy-Org/Wan_2.1_ComfyUI_repackaged) 找到
28+
29+
**Diffusion Models** 选择 1.3B 或 14B:
30+
- [wan2.1_fun_camera_v1.1_1.3B_bf16.safetensors](https://huggingface.co/Comfy-Org/Wan_2.1_ComfyUI_repackaged/resolve/main/split_files/diffusion_models/wan2.1_fun_camera_v1.1_1.3B_bf16.safetensors)
31+
- [wan2.1_fun_camera_v1.1_14B_bf16.safetensors](https://huggingface.co/Comfy-Org/Wan_2.1_ComfyUI_repackaged/resolve/main/split_files/diffusion_models/wan2.1_fun_camera_v1.1_14B_bf16.safetensors)
32+
33+
下面的模型,如果你使用过 Wan2.1 的相关模型,那么你应该已经有了下面的模型,如果没有,请下载下面的模型:
34+
35+
**Text Encoders** 选择其中一个:
36+
- [umt5_xxl_fp16.safetensors](https://huggingface.co/Comfy-Org/Wan_2.1_ComfyUI_repackaged/resolve/main/split_files/text_encoders/umt5_xxl_fp16.safetensors)
37+
- [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)
38+
39+
**VAE**
40+
- [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)
41+
42+
**CLIP Vision**
43+
- [clip_vision_h.safetensors](https://huggingface.co/Comfy-Org/Wan_2.1_ComfyUI_repackaged/resolve/main/split_files/clip_vision/clip_vision_h.safetensors)
44+
45+
文件保存位置:
46+
47+
```
48+
📂 ComfyUI/
49+
├── 📂 models/
50+
│ ├── 📂 diffusion_models/
51+
│ │ ├── wan2.1_fun_camera_v1.1_1.3B_bf16.safetensors # 1.3B 版本
52+
│ │ └── wan2.1_fun_camera_v1.1_14B_bf16.safetensors # 14B 版本
53+
│ ├── 📂 text_encoders/
54+
│ │ └── umt5_xxl_fp8_e4m3fn_scaled.safetensors
55+
│ ├── 📂 vae/
56+
│ │ └── wan_2.1_vae.safetensors
57+
│ └── 📂 clip_vision/
58+
│ └── clip_vision_h.safetensors
59+
```
60+
61+
## ComfyUI Wan2.1 Fun Camera 1.3B 原生工作流示例
62+
63+
### 1. 工作流相关文件下载
64+
65+
#### 1.1 工作流文件
66+
67+
下载下面的视频,并拖入 ComfyUI 中以加载对应的工作流:
68+
69+
<video
70+
controls
71+
className="w-full aspect-video"
72+
src="https://raw.githubusercontent.com/Comfy-Org/example_workflows/refs/heads/main/video/wan/fun-camera/v1.1/wan2.1_fun_camera_1.3B.mp4"
73+
></video>
74+
75+
<a className="prose" target='_blank' href="https://raw.githubusercontent.com/Comfy-Org/example_workflows/refs/heads/main/video/wan/fun-camera/v1.1/wan2.1_fun_camera_1.3B.json" style={{ display: 'inline-block', backgroundColor: '#0078D6', color: '#ffffff', padding: '10px 20px', borderRadius: '8px', borderColor: "transparent", textDecoration: 'none', fontWeight: 'bold'}}>
76+
<p className="prose" style={{ margin: 0, fontSize: "0.8rem" }}>下载 Json 格式工作流文件</p>
77+
</a>
78+
<Note>
79+
如果你想使用 14B 版本,只需要将模型文件替换为 14B 版本即可,但请注意显存要求。
80+
</Note>
81+
82+
#### 1.2 输入图片下载
83+
84+
85+
请下载下面的图片,我们将作为起始帧:
86+
87+
![输入参考图片](https://raw.githubusercontent.com/Comfy-Org/example_workflows/refs/heads/main/video/wan/fun-camera/v1.1/wan2.1_fun_camera_1.3B_input.jpg)
88+
89+
### 2. 按步骤完成工作流
90+
91+
![Wan2.1 Fun Camera 工作流步骤](/images/tutorial/video/wan/wan2-1-fun-camera-1-3b-step-guide.jpg)
92+
93+
1. 确保加载了正确版本的模型文件:
94+
- 1.3B 版本:`wan2.1_fun_camera_v1.1_1.3B_bf16.safetensors`
95+
- 14B 版本:`wan2.1_fun_camera_v1.1_14B_bf16.safetensors`
96+
2. 确保 `Load CLIP` 节点加载了 `umt5_xxl_fp8_e4m3fn_scaled.safetensors`
97+
3. 确保 `Load VAE` 节点加载了 `wan_2.1_vae.safetensors`
98+
4. 确保 `Load CLIP Vision` 节点加载了 `clip_vision_h.safetensors`
99+
5.`Load Image` 节点上传起始帧
100+
6. 修改 Prompt,如果你使用了你自己的图像输入
101+
7.`WanCameraEmbedding` 节点设置相机动作
102+
8. 点击 `Run` 按钮,或使用快捷键 `Ctrl(cmd) + Enter(回车)` 执行生成
103+
104+
## ComfyUI Wan2.1 Fun Camera 14B 工作流及输入图片
105+
106+
<video
107+
controls
108+
className="w-full aspect-video"
109+
src="https://raw.githubusercontent.com/Comfy-Org/example_workflows/refs/heads/main/video/wan/fun-camera/v1.1/wan2.1_fun_camera_14B.mp4"
110+
></video>
111+
112+
<a className="prose" target='_blank' href="https://raw.githubusercontent.com/Comfy-Org/example_workflows/refs/heads/main/video/wan/fun-camera/v1.1/wan2.1_fun_camera_14B.json" style={{ display: 'inline-block', backgroundColor: '#0078D6', color: '#ffffff', padding: '10px 20px', borderRadius: '8px', borderColor: "transparent", textDecoration: 'none', fontWeight: 'bold'}}>
113+
<p className="prose" style={{ margin: 0, fontSize: "0.8rem" }}>下载 Json 格式工作流文件</p>
114+
</a>
115+
116+
**输入图片**
117+
![输入图片](https://raw.githubusercontent.com/Comfy-Org/example_workflows/refs/heads/main/video/wan/fun-camera/v1.1/wan2.1_fun_camera_14B_input.jpg)
118+
119+
## 性能参考
120+
121+
**1.3B 版本**
122+
- 512×512 RTX 4090 生成 81 帧约需 72 秒
123+
124+
**14B 版本**
125+
- RTX4090 24GB 显存在生成 512×512 分辨率时可能会出现显存不足, 在 A100 上运行尺寸过大时也出现过显存不足的情况

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

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -108,7 +108,7 @@ VACE 14B 是阿里通义万相团队推出的开源视频编辑统一模型。
108108

109109
### 2. 按步骤完成工作流的运行
110110

111-
![](/images/tutorial/video/wan/wan-vace-t2v-step-guide.jpg)
111+
![图像](/images/tutorial/video/wan/wan-vace-t2v-step-guide.jpg)
112112

113113
请参照图片序号进行逐步确认,来保证对应工作流的顺利运行
114114

0 commit comments

Comments
 (0)