模板概述
工作流结构
节点流程图(Mermaid)
graph TD
A[CheckpointLoaderSimple] -->|MODEL| B[KSampler]
A -->|CLIP| C[CLIPTextEncode]
A -->|CLIP| D[CLIPTextEncode]
A -->|VAE| E[VAEDecode]
C -->|CONDITIONING| B
D -->|CONDITIONING| B
F[EmptyLatentImage] -->|LATENT| B
B -->|LATENT| E
E -->|IMAGE| G[SaveImage]
style A fill:#e1f5ff
style B fill:#fff4e1
style C fill:#ffe1f5
style D fill:#ffe1f5
style E fill:#e1ffe1
style F fill:#e1ffe1
style G fill:#ffe1e1
节点连接详解
graph LR
A[模型加载] --> B[提示词编码]
B --> C[采样]
C --> D[解码]
D --> E[保存]
style A fill:#e1ffe1
style B fill:#fff4e1
style C fill:#fff4e1
style D fill:#fff4e1
style E fill:#fff4e1
节点配置
1. CheckpointLoaderSimple
{
"inputs": {
"ckpt_name": "v1-5-pruned-emaonly.ckpt"
},
"class_type": "CheckpointLoaderSimple"
}
2. CLIPTextEncode (正向)
{
"inputs": {
"text": "beautiful landscape, mountains, sunset, 4k, detailed",
"clip": ["1", 1]
},
"class_type": "CLIPTextEncode"
}
3. CLIPTextEncode (负向)
{
"inputs": {
"text": "ugly, blurry, low quality",
"clip": ["1", 1]
},
"class_type": "CLIPTextEncode"
}
4. EmptyLatentImage
{
"inputs": {
"width": 512,
"height": 512,
"batch_size": 1
},
"class_type": "EmptyLatentImage"
}
5. KSampler
{
"inputs": {
"seed": 123456789,
"steps": 20,
"cfg": 7.5,
"sampler_name": "euler",
"scheduler": "normal",
"denoise": 1.0,
"model": ["1", 0],
"positive": ["2", 0],
"negative": ["3", 0],
"latent_image": ["4", 0]
},
"class_type": "KSampler"
}
6. VAEDecode
{
"inputs": {
"samples": ["5", 0],
"vae": ["1", 2]
},
"class_type": "VAEDecode"
}
7. SaveImage
{
"inputs": {
"filename_prefix": "txt2img_",
"images": ["6", 0]
},
"class_type": "SaveImage"
}
完整工作流JSON
{
"1": {
"inputs": {
"ckpt_name": "v1-5-pruned-emaonly.ckpt"
},
"class_type": "CheckpointLoaderSimple"
},
"2": {
"inputs": {
"text": "beautiful landscape, mountains, sunset, 4k, detailed",
"clip": ["1", 1]
},
"class_type": "CLIPTextEncode"
},
"3": {
"inputs": {
"text": "ugly, blurry, low quality",
"clip": ["1", 1]
},
"class_type": "CLIPTextEncode"
},
"4": {
"inputs": {
"width": 512,
"height": 512,
"batch_size": 1
},
"class_type": "EmptyLatentImage"
},
"5": {
"inputs": {
"seed": 123456789,
"steps": 20,
"cfg": 7.5,
"sampler_name": "euler",
"scheduler": "normal",
"denoise": 1.0,
"model": ["1", 0],
"positive": ["2", 0],
"negative": ["3", 0],
"latent_image": ["4", 0]
},
"class_type": "KSampler"
},
"6": {
"inputs": {
"samples": ["5", 0],
"vae": ["1", 2]
},
"class_type": "VAEDecode"
},
"7": {
"inputs": {
"filename_prefix": "txt2img_",
"images": ["6", 0]
},
"class_type": "SaveImage"
}
}
参数说明
关键参数
graph TD
A[关键参数] --> B[seed]
A --> C[steps]
A --> D[cfg]
A --> E[分辨率]
B --> B1[随机种子]
C --> C1[采样步数]
D --> D1[提示词相关性]
E --> E1[图像尺寸]
style A fill:#e1f5ff
style B fill:#fff4e1
style C fill:#ffe1f5
style D fill:#e1ffe1
style E fill:#ffe1e1
参数推荐值
- seed: 随机或固定
- steps: 15-25
- cfg: 6-9
- width: 512
- height: 512
使用步骤
步骤流程图
graph LR
A[加载模型] --> B[设置提示词]
B --> C[创建潜在空间]
C --> D[采样生成]
D --> E[解码图像]
E --> F[保存图像]
style A fill:#e1ffe1
style B fill:#fff4e1
style C fill:#fff4e1
style D fill:#fff4e1
style E fill:#fff4e1
style F fill:#fff4e1
示例结果
示例1: 风景生成
- 提示词: beautiful landscape, mountains, sunset, 4k, detailed
- 负向: ugly, blurry, low quality
- 参数: steps=20, cfg=7.5
- 结果: 高质量风景图像
示例2: 人物生成
- 提示词: portrait of beautiful woman, detailed, 4k
- 负向: ugly, blurry, bad anatomy
- 参数: steps=25, cfg=8.0
- 结果: 高质量人物肖像
常见问题
Q1: 如何修改提示词?
A: 修改CLIPTextEncode节点的text参数。
Q2: 如何调整图像大小?
A: 修改EmptyLatentImage的width和height参数。
Q3: 如何提高质量?
A: 增加steps,调整cfg,改进提示词。
Q4: 如何批量生成?
A: 增加batch_size参数。
Q5: 如何保存工作流?
A: 点击"Save"按钮,保存为JSON文件。
扩展建议
扩展方向
graph TD
A[基础模板] --> B[添加LoRA]
A --> C[添加ControlNet]
A --> D[添加后处理]
A --> E[批量处理]
B --> B1[LoraLoader]
C --> C1[ControlNetApply]
D --> D1[ImageScale]
E --> E1[增加batch_size]
style A fill:#e1f5ff
style B fill:#fff4e1
style C fill:#ffe1f5
style D fill:#e1ffe1
style E fill:#ffe1e1
相关模板
更新日志
- 2026-01-26: 初始版本创建