Skip to content

Commit fcd5e5a

Browse files
committed
Add Wan2.2 docs
1 parent b4e2679 commit fcd5e5a

File tree

7 files changed

+325
-0
lines changed

7 files changed

+325
-0
lines changed

docs.json

Lines changed: 2 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -152,6 +152,7 @@
152152
{
153153
"group": "Wan Video",
154154
"pages": [
155+
"tutorials/video/wan/wan2_2",
155156
"tutorials/video/wan/wan-video",
156157
"tutorials/video/wan/vace",
157158
"tutorials/video/wan/wan-ati",
@@ -697,6 +698,7 @@
697698
{
698699
"group": "万相视频",
699700
"pages": [
701+
"zh-CN/tutorials/video/wan/wan2_2",
700702
"zh-CN/tutorials/video/wan/wan-video",
701703
"zh-CN/tutorials/video/wan/vace",
702704
"zh-CN/tutorials/video/wan/wan-ati",
574 KB
Loading
1.03 MB
Loading
917 KB
Loading
797 KB
Loading

tutorials/video/wan/wan2_2.mdx

Lines changed: 157 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,157 @@
1+
---
2+
title: "Wan2.2 Video Generation ComfyUI Official Native Workflow Example"
3+
description: "Official usage guide for Alibaba Cloud Tongyi Wanxiang 2.2 video generation model in ComfyUI"
4+
sidebarTitle: Wan2.2
5+
---
6+
7+
import UpdateReminder from '/snippets/tutorials/update-reminder.mdx'
8+
9+
Wan 2.2 is a new generation multimodal generative model launched by WAN AI. This model adopts an innovative MoE (Mixture of Experts) architecture, consisting of high-noise and low-noise expert models. It can divide expert models according to denoising timesteps, thus generating higher quality video content.
10+
11+
Wan 2.2 has three core features: cinematic-level aesthetic control, deeply integrating professional film industry aesthetic standards, supporting multi-dimensional visual control such as lighting, color, and composition; large-scale complex motion, easily restoring various complex motions and enhancing the smoothness and controllability of motion; precise semantic compliance, excelling in complex scenes and multi-object generation, better restoring users' creative intentions.
12+
The model supports multiple generation modes such as text-to-video and image-to-video, suitable for content creation, artistic creation, education and training, and other application scenarios.
13+
14+
## Model Highlights
15+
16+
- **Cinematic-level Aesthetic Control**: Professional camera language, supports multi-dimensional visual control such as lighting, color, and composition
17+
- **Large-scale Complex Motion**: Smoothly restores various complex motions, enhances motion controllability and naturalness
18+
- **Precise Semantic Compliance**: Complex scene understanding, multi-object generation, better restoring creative intentions
19+
- **Efficient Compression Technology**: 5B version with high compression ratio VAE, memory optimization, supports mixed training
20+
21+
## Wan2.2 Open Source Model Versions
22+
23+
The Wan2.2 series models are based on the Apache 2.0 open source license and support commercial use. The Apache 2.0 license allows you to freely use, modify, and distribute these models, including for commercial purposes, as long as you retain the original copyright notice and license text.
24+
25+
| Model Type | Model Name | Parameters | Main Function | Model Repository |
26+
|------------|------------|------------|---------------|-----------------|
27+
| Hybrid Model | Wan2.2-TI2V-5B | 5B | Hybrid version supporting both text-to-video and image-to-video, a single model meets two core task requirements | 🤗 [Wan2.2-TI2V-5B](https://huggingface.co/Wan-AI/Wan2.2-TI2V-5B) |
28+
| Image-to-Video | Wan2.2-I2V-A14B | 14B | Converts static images into dynamic videos, maintaining content consistency and smooth dynamic process | 🤗 [Wan2.2-I2V-A14B](https://huggingface.co/Wan-AI/Wan2.2-I2V-A14B) |
29+
| Text-to-Video | Wan2.2-T2V-A14B | 14B | Generates high-quality videos from text descriptions, with cinematic-level aesthetic control and precise semantic compliance | 🤗 [Wan2.2-T2V-A14B](https://huggingface.co/Wan-AI/Wan2.2-T2V-A14B) |
30+
31+
This tutorial will use the [🤗 Comfy-Org/Wan_2.2_ComfyUI_Repackaged](https://huggingface.co/Comfy-Org/Wan_2.2_ComfyUI_Repackaged) version.
32+
33+
<UpdateReminder/>
34+
35+
![Wan2.2 template](/images/tutorial/video/wan/wan2_2/template.jpg)
36+
37+
## Wan2.2 TI2V 5B Hybrid Version Workflow Example
38+
39+
### 1. Download Workflow File
40+
41+
Please update your ComfyUI to the latest version, and through the menu `Workflow` -> `Browse Templates` -> `Video`, find "Wan2.2 5B video generation" to load the workflow.
42+
43+
### 2. Manually Download Models
44+
45+
**Diffusion Model**
46+
- [wan2.2_ti2v_5B_fp16.safetensors](https://huggingface.co/Comfy-Org/Wan_2.2_ComfyUI_Repackaged/resolve/main/split_files/diffusion_models/wan2.2_ti2v_5B_fp16.safetensors)
47+
48+
**VAE**
49+
- [wan2.2_vae.safetensors](https://huggingface.co/Comfy-Org/Wan_2.2_ComfyUI_Repackaged/resolve/main/split_files/vae/wan2.2_vae.safetensors)
50+
51+
**Text Encoder**
52+
- [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)
53+
54+
```
55+
ComfyUI/
56+
├───📂 models/
57+
│ ├───📂 diffusion_models/
58+
│ │ └───wan2.2_ti2v_5B_fp16.safetensors
59+
│ ├───📂 text_encoders/
60+
│ │ └─── umt5_xxl_fp8_e4m3fn_scaled.safetensors
61+
│ └───📂 vae/
62+
│ └── wan2.2_vae.safetensors
63+
```
64+
65+
### 3. Follow the Workflow Steps
66+
![Step Diagram](/images/tutorial/video/wan/wan2_2/wan_2.2_5b_t2v.jpg)
67+
68+
1. Ensure the `Load Diffusion Model` node loads the `wan2.2_ti2v_5B_fp16.safetensors` model.
69+
2. Ensure the `Load CLIP` node loads the `umt5_xxl_fp8_e4m3fn_scaled.safetensors` model.
70+
3. Ensure the `Load VAE` node loads the `wan2.2_vae.safetensors` model.
71+
4. (Optional) If you need to perform image-to-video generation, you can use the shortcut Ctrl+B to enable the `Load image` node to upload an image.
72+
5. (Optional) In the `Wan22ImageToVideoLatent` node, you can adjust the size settings and the total number of video frames (`length`).
73+
6. (Optional) If you need to modify the prompts (positive and negative), please do so in the `CLIP Text Encoder` node at step 5.
74+
7. Click the `Run` button, or use the shortcut `Ctrl(cmd) + Enter` to execute video generation.
75+
76+
## Wan2.2 14B T2V Text-to-Video Workflow Example
77+
78+
### 1. Workflow File
79+
80+
Please update your ComfyUI to the latest version, and through the menu `Workflow` -> `Browse Templates` -> `Video`, find "Wan2.2 14B T2V" to load the workflow.
81+
82+
### 2. Manually Download Models
83+
84+
**Diffusion Model**
85+
- [wan2.2_t2v_high_noise_14B_fp8_scaled.safetensors](https://huggingface.co/Comfy-Org/Wan_2.2_ComfyUI_Repackaged/resolve/main/split_files/diffusion_models/wan2.2_t2v_high_noise_14B_fp8_scaled.safetensors)
86+
- [wan2.2_t2v_low_noise_14B_fp8_scaled.safetensors](https://huggingface.co/Comfy-Org/Wan_2.2_ComfyUI_Repackaged/resolve/main/split_files/diffusion_models/wan2.2_t2v_low_noise_14B_fp8_scaled.safetensors)
87+
88+
**VAE**
89+
- [wan_2.1_vae.safetensors](https://huggingface.co/Comfy-Org/Wan_2.2_ComfyUI_Repackaged/resolve/main/split_files/vae/wan_2.1_vae.safetensors)
90+
91+
**Text Encoder**
92+
- [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)
93+
94+
95+
```
96+
ComfyUI/
97+
├───📂 models/
98+
│ ├───📂 diffusion_models/
99+
│ │ ├─── wan2.2_t2v_low_noise_14B_fp8_scaled.safetensors
100+
│ │ └─── wan2.2_t2v_high_noise_14B_fp8_scaled.safetensors
101+
│ ├───📂 text_encoders/
102+
│ │ └─── umt5_xxl_fp8_e4m3fn_scaled.safetensors
103+
│ └───📂 vae/
104+
│ └── wan_2.1_vae.safetensors
105+
```
106+
107+
### 3. Follow the Workflow Steps
108+
![Step Diagram](/images/tutorial/video/wan/wan2_2/wan_2.2_5b_t2v.jpg)
109+
110+
1. Ensure the first `Load Diffusion Model` node loads the `wan2.2_t2v_high_noise_14B_fp8_scaled.safetensors` model.
111+
2. Ensure the second `Load Diffusion Model` node loads the `wan2.2_t2v_low_noise_14B_fp8_scaled.safetensors` model.
112+
3. Ensure the `Load CLIP` node loads the `umt5_xxl_fp8_e4m3fn_scaled.safetensors` model.
113+
4. Ensure the `Load VAE` node loads the `wan_2.1_vae.safetensors` model.
114+
5. (Optional) In the `EmptyHunyuanLatentVideo` node, you can adjust the size settings and the total number of video frames (`length`).
115+
6. (Optional) If you need to modify the prompts (positive and negative), please do so in the `CLIP Text Encoder` node at step 5.
116+
7. Click the `Run` button, or use the shortcut `Ctrl(cmd) + Enter` to execute video generation.
117+
118+
## Wan2.2 14B I2V Image-to-Video Workflow Example
119+
120+
### 1. Workflow File
121+
122+
Please update your ComfyUI to the latest version, and through the menu `Workflow` -> `Browse Templates` -> `Video`, find "Wan2.2 14B I2V" to load the workflow.
123+
124+
### 2. Manually Download Models
125+
126+
**Diffusion Model**
127+
- [wan2.2_i2v_high_noise_14B_fp16.safetensors](https://huggingface.co/Comfy-Org/Wan_2.2_ComfyUI_Repackaged/resolve/main/split_files/diffusion_models/wan2.2_i2v_high_noise_14B_fp16.safetensors)
128+
- [wan2.2_i2v_low_noise_14B_fp16.safetensors](https://huggingface.co/Comfy-Org/Wan_2.2_ComfyUI_Repackaged/resolve/main/split_files/diffusion_models/wan2.2_i2v_low_noise_14B_fp16.safetensors)
129+
130+
**VAE**
131+
- [wan_2.1_vae.safetensors](https://huggingface.co/Comfy-Org/Wan_2.2_ComfyUI_Repackaged/resolve/main/split_files/vae/wan_2.1_vae.safetensors)
132+
133+
**Text Encoder**
134+
- [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)
135+
136+
```
137+
ComfyUI/
138+
├───📂 models/
139+
│ ├───📂 diffusion_models/
140+
│ │ ├─── wan2.2_i2v_low_noise_14B_fp16.safetensors
141+
│ │ └─── wan2.2_i2v_high_noise_14B_fp16.safetensors
142+
│ ├───📂 text_encoders/
143+
│ │ └─── umt5_xxl_fp8_e4m3fn_scaled.safetensors
144+
│ └───📂 vae/
145+
│ └── wan_2.1_vae.safetensors
146+
```
147+
### 3. Follow the Workflow Steps
148+
![Step Diagram](/images/tutorial/video/wan/wan2_2/wan_2.2_5b_t2v.jpg)
149+
150+
1. Make sure the first `Load Diffusion Model` node loads the `wan2.2_t2v_high_noise_14B_fp8_scaled.safetensors` model.
151+
2. Make sure the second `Load Diffusion Model` node loads the `wan2.2_t2v_low_noise_14B_fp8_scaled.safetensors` model.
152+
3. Make sure the `Load CLIP` node loads the `umt5_xxl_fp8_e4m3fn_scaled.safetensors` model.
153+
4. Make sure the `Load VAE` node loads the `wan_2.1_vae.safetensors` model.
154+
5. In the `Load Image` node, upload the image to be used as the initial frame.
155+
6. If you need to modify the prompts (positive and negative), do so in the `CLIP Text Encoder` node at step 6.
156+
7. (Optional) In `EmptyHunyuanLatentVideo`, you can adjust the size settings and the total number of video frames (`length`).
157+
8. Click the `Run` button, or use the shortcut `Ctrl(cmd) + Enter` to execute video generation.
Lines changed: 166 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,166 @@
1+
---
2+
title: "Wan2.2 视频生成ComfyUI 官方原生工作流示例"
3+
description: "阿里云通义万相2.2视频生成模型在ComfyUI中的官方使用指南"
4+
sidebarTitle: Wan2.2
5+
---
6+
7+
import UpdateReminder from '/snippets/zh/tutorials/update-reminder.mdx'
8+
9+
10+
通义万相 2.2(Wan 2.2)是阿里云推出的新一代多模态生成模型。该模型采用创新的 MoE(Mixture of Experts)架构,由高噪专家模型和低噪专家模型组成,能够根据去噪时间步进行专家模型划分,从而生成更高质量的视频内容。
11+
12+
Wan 2.2 具备三大核心特性:影视级美学控制,深度融合专业电影工业的美学标准,支持光影、色彩、构图等多维度视觉控制;大规模复杂运动,轻松还原各类复杂运动并强化运动的流畅度和可控性;精准语义遵循,在复杂场景和多对象生成方面表现卓越,更好还原用户的创意意图。
13+
模型支持文生视频、图生视频等多种生成模式,适用于内容创作、艺术创作、教育培训等多种应用场景。
14+
15+
## 模型亮点
16+
17+
- **影视级美学控制**:专业镜头语言,支持光影、色彩、构图等多维度视觉控制
18+
- **大规模复杂运动**:流畅还原各类复杂运动,强化运动可控性和自然度
19+
- **精准语义遵循**:复杂场景理解,多对象生成,更好还原创意意图
20+
- **高效压缩技术**:5B版本高压缩比VAE,显存优化,支持混合训练
21+
22+
## Wan2.2 开源模型版本
23+
24+
Wan2.2 系列模型基于 Apache2.0 开源协议,支持商业使用。Apache2.0 许可证允许您自由使用、修改和分发这些模型,包括商业用途,只需保留原始版权声明和许可证文本。
25+
26+
| 模型类型 | 模型名称 | 参数量 | 主要功能 | 模型仓库 |
27+
|---------|---------|--------|----------|----------|
28+
| 混合模型 | Wan2.2-TI2V-5B | 5B | 支持文本生成视频和图像生成视频的混合版本,单一模型满足两大核心任务需求 | 🤗 [Wan2.2-TI2V-5B](https://huggingface.co/Wan-AI/Wan2.2-TI2V-5B) |
29+
| 图生视频 | Wan2.2-I2V-A14B | 14B | 将静态图像转换为动态视频,保持内容一致性和流畅的动态过程 | 🤗 [Wan2.2-I2V-A14B](https://huggingface.co/Wan-AI/Wan2.2-I2V-A14B) |
30+
| 文生视频 | Wan2.2-T2V-A14B | 14B | 从文本描述生成高质量视频,具备影视级美学控制和精准语义遵循 | 🤗 [Wan2.2-T2V-A14B](https://huggingface.co/Wan-AI/Wan2.2-T2V-A14B) |
31+
32+
本篇教程将使用 [🤗 Comfy-Org/Wan_2.2_ComfyUI_Repackaged](https://huggingface.co/Comfy-Org/Wan_2.2_ComfyUI_Repackaged)的版本进行
33+
34+
<UpdateReminder/>
35+
36+
![Wan2.2 template](/images/tutorial/video/wan/wan2_2/template.jpg)
37+
38+
## Wan2.2 TI2V 5B 混合版本工作流示例
39+
40+
### 1. 工作流文件下载
41+
42+
请更新你的 ComfyUI 到最新版本,并通过菜单 `工作流` -> `浏览模板` -> `视频` 找到 “Wan2.2 5B video generation” 以加载工作流
43+
44+
<video
45+
controls
46+
className="w-full aspect-video"
47+
src="https://raw.githubusercontent.com/Comfy-Org/example_workflows/refs/heads/main/video/wan/ati/wan_ati.mp4"
48+
></video>
49+
50+
### 2. 手动下载模型
51+
52+
**Diffusion Model**
53+
- [wan2.2_ti2v_5B_fp16.safetensors](https://huggingface.co/Comfy-Org/Wan_2.2_ComfyUI_Repackaged/resolve/main/split_files/diffusion_models/wan2.2_ti2v_5B_fp16.safetensors)
54+
55+
**VAE**
56+
- [wan2.2_vae.safetensors](https://huggingface.co/Comfy-Org/Wan_2.2_ComfyUI_Repackaged/resolve/main/split_files/vae/wan2.2_vae.safetensors)
57+
58+
**Text Encoder**
59+
- [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)
60+
61+
```
62+
ComfyUI/
63+
├───📂 models/
64+
│ ├───📂 diffusion_models/
65+
│ │ └───wan2.2_ti2v_5B_fp16.safetensors
66+
│ ├───📂 text_encoders/
67+
│ │ └─── umt5_xxl_fp8_e4m3fn_scaled.safetensors
68+
│ └───📂 vae/
69+
│ └── wan2.2_vae.safetensors
70+
```
71+
72+
### 3. 按步骤完成工作流
73+
![步骤图](/images/tutorial/video/wan/wan2_2/wan_2.2_5b_t2v.jpg)
74+
75+
1. 确保`Load Diffusion Model`节点加载了 `wan2.2_ti2v_5B_fp16.safetensors` 模型
76+
2. 确保`Load CLIP`节点加载了 `umt5_xxl_fp8_e4m3fn_scaled.safetensors` 模型
77+
3. 确保`Load VAE`节点加载了 `wan2.2_vae.safetensors` 模型
78+
4. (可选)如果你需要进行图生视频,可以使用快捷键 Ctrl+B 来启用 `Load image` 节点来上传图片
79+
5. (可选)在`Wan22ImageToVideoLatent` 你可以进行尺寸的设置调整,和视频总帧数 `length` 调整
80+
6. (可选)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
81+
7. 点击 `Run` 按钮,或者使用快捷键 `Ctrl(cmd) + Enter(回车)` 来执行视频生成
82+
83+
## Wan2.2 14B T2V 文生视频工作流示例
84+
85+
### 1. 工作流文件下载
86+
87+
请更新你的 ComfyUI 到最新版本,并通过菜单 `工作流` -> `浏览模板` -> `视频` 找到 “Wan2.2 14B T2V”
88+
89+
90+
### 2. 手动下载模型
91+
92+
**Diffusion Model**
93+
- [wan2.2_t2v_high_noise_14B_fp8_scaled.safetensors](https://huggingface.co/Comfy-Org/Wan_2.2_ComfyUI_Repackaged/resolve/main/split_files/diffusion_models/wan2.2_t2v_high_noise_14B_fp8_scaled.safetensors)
94+
- [wan2.2_t2v_low_noise_14B_fp8_scaled.safetensors](https://huggingface.co/Comfy-Org/Wan_2.2_ComfyUI_Repackaged/resolve/main/split_files/diffusion_models/wan2.2_t2v_low_noise_14B_fp8_scaled.safetensors)
95+
96+
**VAE**
97+
- [wan_2.1_vae.safetensors](https://huggingface.co/Comfy-Org/Wan_2.2_ComfyUI_Repackaged/resolve/main/split_files/vae/wan_2.1_vae.safetensors)
98+
99+
**Text Encoder**
100+
- [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)
101+
102+
103+
```
104+
ComfyUI/
105+
├───📂 models/
106+
│ ├───📂 diffusion_models/
107+
│ │ ├─── wan2.2_t2v_low_noise_14B_fp8_scaled.safetensors
108+
│ │ └─── wan2.2_t2v_high_noise_14B_fp8_scaled.safetensors
109+
│ ├───📂 text_encoders/
110+
│ │ └─── umt5_xxl_fp8_e4m3fn_scaled.safetensors
111+
│ └───📂 vae/
112+
│ └── wan_2.1_vae.safetensors
113+
```
114+
115+
116+
### 3. 按步骤完成工作流
117+
![步骤图](/images/tutorial/video/wan/wan2_2/wan_2.2_5b_t2v.jpg)
118+
119+
1. 确保第一个 `Load Diffusion Model`节点加载了 `wan2.2_t2v_high_noise_14B_fp8_scaled.safetensors` 模型
120+
2. 确保第二个 `Load Diffusion Model`节点加载了 `wan2.2_t2v_low_noise_14B_fp8_scaled.safetensors` 模型
121+
3. 确保`Load CLIP`节点加载了 `umt5_xxl_fp8_e4m3fn_scaled.safetensors` 模型
122+
4. 确保`Load VAE`节点加载了 `wan_2.1_vae.safetensors` 模型
123+
5. (可选)在`EmptyHunyuanLatentVideo` 你可以进行尺寸的设置调整,和视频总帧数 `length` 调整
124+
6. 如果你需要修改提示词(正向及负向)请在序号`6``CLIP Text Encoder` 节点中进行修改
125+
7. 点击 `Run` 按钮,或者使用快捷键 `Ctrl(cmd) + Enter(回车)` 来执行视频生成
126+
127+
## Wan2.2 14B I2V 图生视频工作流示例
128+
129+
### 1. 工作流文件
130+
131+
请更新你的 ComfyUI 到最新版本,并通过菜单 `工作流` -> `浏览模板` -> `视频` 找到 “Wan2.2 14B I2V” 以加载工作流
132+
133+
### 2. 手动下载模型
134+
135+
**Diffusion Model**
136+
- [wan2.2_i2v_high_noise_14B_fp16.safetensors](https://huggingface.co/Comfy-Org/Wan_2.2_ComfyUI_Repackaged/resolve/main/split_files/diffusion_models/wan2.2_i2v_high_noise_14B_fp16.safetensors)
137+
- [wan2.2_i2v_low_noise_14B_fp16.safetensors](https://huggingface.co/Comfy-Org/Wan_2.2_ComfyUI_Repackaged/resolve/main/split_files/diffusion_models/wan2.2_i2v_low_noise_14B_fp16.safetensors)
138+
139+
**VAE**
140+
- [wan_2.1_vae.safetensors](https://huggingface.co/Comfy-Org/Wan_2.2_ComfyUI_Repackaged/resolve/main/split_files/vae/wan_2.1_vae.safetensors)
141+
142+
**Text Encoder**
143+
- [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)
144+
145+
```
146+
ComfyUI/
147+
├───📂 models/
148+
│ ├───📂 diffusion_models/
149+
│ │ ├─── wan2.2_i2v_low_noise_14B_fp16.safetensors
150+
│ │ └─── wan2.2_i2v_high_noise_14B_fp16.safetensors
151+
│ ├───📂 text_encoders/
152+
│ │ └─── umt5_xxl_fp8_e4m3fn_scaled.safetensors
153+
│ └───📂 vae/
154+
│ └── wan_2.1_vae.safetensors
155+
```
156+
### 3. 按步骤完成工作流
157+
![步骤图](/images/tutorial/video/wan/wan2_2/wan_2.2_5b_t2v.jpg)
158+
159+
1. 确保第一个 `Load Diffusion Model`节点加载了 `wan2.2_t2v_high_noise_14B_fp8_scaled.safetensors` 模型
160+
2. 确保第二个 `Load Diffusion Model`节点加载了 `wan2.2_t2v_low_noise_14B_fp8_scaled.safetensors` 模型
161+
3. 确保`Load CLIP`节点加载了 `umt5_xxl_fp8_e4m3fn_scaled.safetensors` 模型
162+
4. 确保`Load VAE`节点加载了 `wan_2.1_vae.safetensors` 模型
163+
5.`Load Image` 节点上传作为起始帧的图像
164+
6. 如果你需要修改提示词(正向及负向)请在序号`6``CLIP Text Encoder` 节点中进行修改
165+
7. 可选)在`EmptyHunyuanLatentVideo` 你可以进行尺寸的设置调整,和视频总帧数 `length` 调整
166+
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)