Skip to content

Commit 514d2a1

Browse files
authored
Wan ati (#284)
* Update WAN ATI docs * Update navigation
1 parent 71565b5 commit 514d2a1

File tree

4 files changed

+172
-2
lines changed

4 files changed

+172
-2
lines changed

docs.json

Lines changed: 4 additions & 2 deletions
Original file line numberDiff line numberDiff line change
@@ -154,6 +154,7 @@
154154
"pages": [
155155
"tutorials/video/wan/wan-video",
156156
"tutorials/video/wan/vace",
157+
"tutorials/video/wan/wan-ati",
157158
"tutorials/video/wan/fun-control",
158159
"tutorials/video/wan/fun-camera",
159160
"tutorials/video/wan/fun-inp",
@@ -693,11 +694,12 @@
693694
"group": "万相视频",
694695
"pages": [
695696
"zh-CN/tutorials/video/wan/wan-video",
697+
"zh-CN/tutorials/video/wan/vace",
698+
"zh-CN/tutorials/video/wan/wan-ati",
696699
"zh-CN/tutorials/video/wan/fun-control",
697700
"zh-CN/tutorials/video/wan/fun-camera",
698701
"zh-CN/tutorials/video/wan/fun-inp",
699-
"zh-CN/tutorials/video/wan/wan-flf",
700-
"zh-CN/tutorials/video/wan/vace"
702+
"zh-CN/tutorials/video/wan/wan-flf"
701703
]
702704
},
703705
{
1.08 MB
Loading

tutorials/video/wan/wan-ati.mdx

Lines changed: 83 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,83 @@
1+
---
2+
title: "Wan ATI ComfyUI Native Workflow Tutorial"
3+
description: "Using trajectory control for video generation."
4+
sidebarTitle: "WAN ATI"
5+
---
6+
7+
import UpdateReminder from '/snippets/en/tutorials/update-reminder.mdx'
8+
9+
10+
**ATI (Any Trajectory Instruction)** is a controllable video generation framework proposed by the ByteDance team. ATI is implemented based on Wan2.1 and supports unified control of objects, local regions, and camera motion in videos through arbitrary trajectory instructions.
11+
12+
Project URL: [https://github.com/bytedance/ATI](https://github.com/bytedance/ATI)
13+
14+
## Key Features
15+
16+
- **Unified Motion Control**: Supports trajectory control for multiple motion types including objects, local regions, and camera movements.
17+
- **Interactive Trajectory Editor**: Visual tool that allows users to freely draw and edit motion trajectories on images.
18+
- **Wan2.1 Compatible**: Based on the official Wan2.1 implementation, compatible with environments and model structures.
19+
- **Rich Visualization Tools**: Supports visualization of input trajectories, output videos, and trajectory overlays.
20+
21+
22+
## WAN ATI Trajectory Control Workflow Example
23+
24+
<UpdateReminder />
25+
26+
### 1. Workflow Download
27+
28+
Download the video below and drag it into ComfyUI to load the corresponding workflow
29+
<video
30+
controls
31+
className="w-full aspect-video"
32+
src="https://raw.githubusercontent.com/Comfy-Org/example_workflows/refs/heads/main/video/wan/ati/wan_ati.mp4"
33+
></video>
34+
35+
We will use the following image as input:
36+
![v2v-input](https://raw.githubusercontent.com/Comfy-Org/example_workflows/refs/heads/main/video/wan/ati/input.jpg)
37+
38+
### 2. Model Download
39+
40+
If you haven't successfully downloaded the model files from the workflow, you can try downloading them manually using the links below
41+
42+
**Diffusion Model**
43+
- [Wan2_1-I2V-ATI-14B_fp8_e4m3fn.safetensors](https://huggingface.co/Kijai/WanVideo_comfy/resolve/main/Wan2_1-I2V-ATI-14B_fp8_e4m3fn.safetensors)
44+
45+
**VAE**
46+
- [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?download=true)
47+
48+
**Text encoders** Chose one of following model
49+
- [umt5_xxl_fp16.safetensors](https://huggingface.co/Comfy-Org/Wan_2.1_ComfyUI_repackaged/resolve/main/split_files/text_encoders/umt5_xxl_fp16.safetensors?download=true)
50+
- [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?download=true)
51+
52+
**clip_vision**
53+
- [clip_vision_h.safetensors](https://huggingface.co/Comfy-Org/Wan_2.1_ComfyUI_repackaged/resolve/main/split_files/clip_vision/clip_vision_h.safetensors)
54+
55+
File save location
56+
```
57+
ComfyUI/
58+
├───📂 models/
59+
│ ├───📂 diffusion_models/
60+
│ │ └───Wan2_1-I2V-ATI-14B_fp8_e4m3fn.safetensors
61+
│ ├───📂 text_encoders/
62+
│ │ └─── umt5_xxl_fp8_e4m3fn_scaled.safetensors # or other version
63+
│ ├───📂 clip_vision/
64+
│ │ └─── clip_vision_h.safetensors
65+
│ └───📂 vae/
66+
│ └── wan_2.1_vae.safetensors
67+
```
68+
69+
### 3. Complete the workflow execution step by step
70+
71+
![Workflow step diagram](/images/tutorial/video/wan/wan_ati_guide.jpg)
72+
73+
Please follow the numbered steps in the image to ensure smooth execution of the corresponding workflow
74+
75+
1. Ensure the `Load Diffusion Model` node has loaded the `Wan2_1-I2V-ATI-14B_fp8_e4m3fn.safetensors` model
76+
2. Ensure the `Load CLIP` node has loaded the `umt5_xxl_fp8_e4m3fn_scaled.safetensors` model
77+
3. Ensure the `Load VAE` node has loaded the `wan_2.1_vae.safetensors` model
78+
4. Ensure the `Load CLIP Vision` node has loaded the `clip_vision_h.safetensors` model
79+
5. Upload the provided input image in the `Load Image` node
80+
6. Trajectory editing: Currently there is no corresponding trajectory editor in ComfyUI yet, you can use the following link to complete trajectory editing
81+
- [Online Trajectory Editing Tool](https://comfyui-wiki.github.io/Trajectory-Annotation-Tool/)
82+
7. If you need to modify the prompts (positive and negative), please make changes in the `CLIP Text Encoder` node numbered `5`
83+
8. Click the `Run` button, or use the shortcut `Ctrl(cmd) + Enter` to execute video generation
Lines changed: 85 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,85 @@
1+
---
2+
title: "Wan ATI ComfyUI 原生工作流教程"
3+
description: "使用轨迹控制视频生成。"
4+
sidebarTitle: "WAN ATI"
5+
---
6+
7+
import UpdateReminder from '/snippets/zh/tutorials/update-reminder.mdx'
8+
9+
10+
**ATI(Any Trajectory Instruction)** 是由字节跳动团队提出的可控视频生成框架。ATI 基于 Wan2.1 实现,支持通过任意轨迹指令对视频中的物体、局部区域及摄像机运动进行统一控制。
11+
12+
项目地址:[https://github.com/bytedance/ATI](https://github.com/bytedance/ATI)
13+
14+
## 主要特性
15+
16+
- **统一运动控制**:支持物体、局部、摄像机等多种运动类型的轨迹控制。
17+
- **交互式轨迹编辑器**:可视化工具,用户可在图片上自由绘制、编辑运动轨迹。
18+
- **兼容 Wan2.1**:基于 Wan2.1 官方实现,环境和模型结构兼容。
19+
- **丰富的可视化工具**:支持输入轨迹、输出视频及轨迹可视化。
20+
21+
22+
## WAN ATI 轨迹控制工作流示例
23+
24+
<UpdateReminder />
25+
26+
### 1. 工作流下载
27+
28+
下载下面的视频并拖入 ComfyUI 中,以加载对应的工作流
29+
<video
30+
controls
31+
className="w-full aspect-video"
32+
src="https://raw.githubusercontent.com/Comfy-Org/example_workflows/refs/heads/main/video/wan/ati/wan_ati.mp4"
33+
></video>
34+
35+
我们将使用下面的素材作为输入:
36+
![v2v-input](https://raw.githubusercontent.com/Comfy-Org/example_workflows/refs/heads/main/video/wan/ati/input.jpg)
37+
38+
### 2. 模型下载
39+
40+
如果你没有成功下载工作流中的模型文件,可以尝试使用下面的链接手动下载
41+
42+
**Diffusion Model**
43+
- [Wan2_1-I2V-ATI-14B_fp8_e4m3fn.safetensors](https://huggingface.co/Kijai/WanVideo_comfy/resolve/main/Wan2_1-I2V-ATI-14B_fp8_e4m3fn.safetensors)
44+
45+
**VAE**
46+
- [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?download=true)
47+
48+
**Text encoders** Chose one of following model
49+
- [umt5_xxl_fp16.safetensors](https://huggingface.co/Comfy-Org/Wan_2.1_ComfyUI_repackaged/resolve/main/split_files/text_encoders/umt5_xxl_fp16.safetensors?download=true)
50+
- [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?download=true)
51+
52+
**clip_vision**
53+
- [clip_vision_h.safetensors](https://huggingface.co/Comfy-Org/Wan_2.1_ComfyUI_repackaged/resolve/main/split_files/clip_vision/clip_vision_h.safetensors)
54+
55+
File save location
56+
57+
```
58+
ComfyUI/
59+
├───📂 models/
60+
│ ├───📂 diffusion_models/
61+
│ │ └───Wan2_1-I2V-ATI-14B_fp8_e4m3fn.safetensors
62+
│ ├───📂 text_encoders/
63+
│ │ └─── umt5_xxl_fp8_e4m3fn_scaled.safetensors # or other version
64+
│ ├───📂 clip_vision/
65+
│ │ └─── clip_vision_h.safetensors
66+
│ └───📂 vae/
67+
│ └── wan_2.1_vae.safetensors
68+
```
69+
70+
71+
### 3. 按步骤完成工作流的运行
72+
73+
![工作流步骤图](/images/tutorial/video/wan/wan_ati_guide.jpg)
74+
75+
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
76+
77+
1. 确保`Load Diffusion Model`节点加载了 `Wan2_1-I2V-ATI-14B_fp8_e4m3fn.safetensors` 模型
78+
2. 确保`Load CLIP`节点加载了 `umt5_xxl_fp8_e4m3fn_scaled.safetensors` 模型
79+
3. 确保`Load VAE`节点加载了 `wan_2.1_vae.safetensors` 模型
80+
4. 确保`Load CLIP Vision`节点加载了 `clip_vision_h.safetensors` 模型
81+
5.`Load Image` 节点上传提供的输入图片
82+
6. 轨迹编辑: 目前 ComfyUI 中还未有对应的轨迹编辑器,你可以使用下面的链接来完成轨迹编辑
83+
- [在线轨迹编辑工具](https://comfyui-wiki.github.io/Trajectory-Annotation-Tool/)
84+
7. 如果你需要修改提示词(正向及负向)请在序号`5``CLIP Text Encoder` 节点中进行修改
85+
8. 点击 `Run` 按钮,或者使用快捷键 `Ctrl(cmd) + Enter(回车)` 来执行视频生成

0 commit comments

Comments
 (0)