Skip to content

Commit 2d81fd9

Browse files
mintlify[bot]mintlify[bot]
authored
Add Z-Image tutorial documentation (#594)
* Update tutorials/image/z-image/z-image.mdx * Update zh-CN/tutorials/image/z-image/z-image.mdx * Update docs.json * Update docs.json * Update tutorials/image/z-image/z-image.mdx * Update zh-CN/tutorials/image/z-image/z-image.mdx * Update tutorials/image/z-image/z-image.mdx * Update zh-CN/tutorials/image/z-image/z-image.mdx * Update tutorials/image/z-image/z-image-turbo.mdx * Update zh-CN/tutorials/image/z-image/z-image-turbo.mdx * Delete zh-CN/tutorials/image/z-image/z-image.mdx * Delete tutorials/image/z-image/z-image.mdx * Update docs.json * Update tutorials/image/z-image/z-image-turbo.mdx * Update zh-CN/tutorials/image/z-image/z-image-turbo.mdx * Update tutorials/image/z-image/z-image-turbo.mdx * Update zh-CN/tutorials/image/z-image/z-image-turbo.mdx --------- Co-authored-by: mintlify[bot] <109931778+mintlify[bot]@users.noreply.github.com>
1 parent a7d4520 commit 2d81fd9

File tree

3 files changed

+138
-0
lines changed

3 files changed

+138
-0
lines changed

‎docs.json‎

Lines changed: 12 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -142,6 +142,12 @@
142142
"tutorials/image/hidream/hidream-e1"
143143
]
144144
},
145+
{
146+
"group": "Z-Image",
147+
"pages": [
148+
"tutorials/image/z-image/z-image-turbo"
149+
]
150+
},
145151
"tutorials/image/cosmos/cosmos-predict2-t2i",
146152
"tutorials/image/omnigen/omnigen2"
147153
]
@@ -757,6 +763,12 @@
757763
"zh-CN/tutorials/image/hidream/hidream-e1"
758764
]
759765
},
766+
{
767+
"group": "Z-Image",
768+
"pages": [
769+
"zh-CN/tutorials/image/z-image/z-image-turbo"
770+
]
771+
},
760772
"zh-CN/tutorials/image/cosmos/cosmos-predict2-t2i",
761773
"zh-CN/tutorials/image/omnigen/omnigen2"
762774
]

‎tutorials/image/z-image/z-image-turbo.mdx‎

Lines changed: 63 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,63 @@
1+
---
2+
title: "Z-Image ComfyUI Workflow Example"
3+
description: "Z-Image is a 6B parameter efficient image generation foundation model with single-stream diffusion transformer, offering sub-second inference latency."
4+
sidebarTitle: "Z-Image"
5+
---
6+
7+
import UpdateReminder from '/snippets/tutorials/update-reminder.mdx'
8+
9+
**Z-Image (造相)** is a powerful and highly efficient image generation model with **6B** parameters, developed by Alibaba's Tongyi Lab. It uses a **Scalable Single-Stream DiT** (S3-DiT) architecture where text, visual semantic tokens, and image VAE tokens are concatenated at the sequence level to serve as a unified input stream, maximizing parameter efficiency.
10+
11+
**Model Variants**:
12+
- 🚀 **Z-Image-Turbo** – A distilled version that matches or exceeds leading competitors with only **8 NFEs** (Number of Function Evaluations). It offers **sub-second inference latency** on enterprise-grade H800 GPUs and fits within **16GB VRAM consumer devices**.
13+
- 🧱 **Z-Image-Base** – The non-distilled foundation model for community-driven fine-tuning and custom development.
14+
- ✍️ **Z-Image-Edit** – A variant fine-tuned for image editing tasks with impressive instruction-following capabilities.
15+
16+
**Model Highlights**:
17+
- **Photorealistic Quality**: Delivers strong photorealistic image generation while maintaining excellent aesthetic quality
18+
- **Accurate Bilingual Text Rendering**: Excels at accurately rendering complex Chinese and English text
19+
- **Prompt Enhancing & Reasoning**: Prompt Enhancer empowers the model with reasoning capabilities
20+
- **Sub-second Inference**: Achieves fast generation speed on supported hardware
21+
22+
**Related Links**:
23+
- [GitHub](https://github.com/Tongyi-MAI/Z-Image)
24+
- [Hugging Face](https://huggingface.co/Tongyi-MAI/Z-Image-Turbo)
25+
26+
## Z-Image-Turbo text-to-image workflow
27+
28+
<a className="prose" target='_blank' href="https://raw.githubusercontent.com/Comfy-Org/workflow_templates/refs/heads/main/templates/image_z_image_turbo.json" style={{ display: 'inline-block', backgroundColor: '#0078D6', color: '#ffffff', padding: '10px 20px', borderRadius: '8px', borderColor: "transparent", textDecoration: 'none', fontWeight: 'bold', marginRight: '10px'}}>
29+
<p className="prose" style={{ margin: 0, fontSize: "0.8rem" }}>Download JSON Workflow File</p>
30+
</a>
31+
32+
<a className="prose" target='_blank' href="https://cloud.comfy.org/?template=image_z_image_turbo&utm_source=docs" style={{ display: 'inline-block', backgroundColor: '#28a745', color: '#ffffff', padding: '10px 20px', borderRadius: '8px', borderColor: "transparent", textDecoration: 'none', fontWeight: 'bold'}}>
33+
<p className="prose" style={{ margin: 0, fontSize: "0.8rem" }}>Run on ComfyUI Cloud</p>
34+
</a>
35+
36+
<UpdateReminder />
37+
38+
## Model links
39+
40+
**text_encoders**
41+
42+
- [qwen_3_4b.safetensors](https://huggingface.co/Comfy-Org/z_image_turbo/resolve/main/split_files/text_encoders/qwen_3_4b.safetensors)
43+
44+
**diffusion_models**
45+
46+
- [z_image_turbo_bf16.safetensors](https://huggingface.co/Comfy-Org/z_image_turbo/resolve/main/split_files/diffusion_models/z_image_turbo_bf16.safetensors)
47+
48+
**vae**
49+
50+
- [ae.safetensors](https://huggingface.co/Comfy-Org/z_image_turbo/resolve/main/split_files/vae/ae.safetensors)
51+
52+
**Model Storage Location**
53+
54+
```
55+
📂 ComfyUI/
56+
├── 📂 models/
57+
│ ├── 📂 text_encoders/
58+
│ │ └── qwen_3_4b.safetensors
59+
│ ├── 📂 diffusion_models/
60+
│ │ └── z_image_turbo_bf16.safetensors
61+
│ └── 📂 vae/
62+
│ └── ae.safetensors
63+
```

‎zh-CN/tutorials/image/z-image/z-image-turbo.mdx‎

Lines changed: 63 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,63 @@
1+
---
2+
title: "Z-Image ComfyUI 工作流示例"
3+
description: "Z-Image 是一个拥有 6B 参数的高效图像生成基础模型，采用单流扩散变换器架构，可实现亚秒级推理延迟。"
4+
sidebarTitle: "Z-Image"
5+
---
6+
7+
import UpdateReminder from '/snippets/zh/tutorials/update-reminder.mdx'
8+
9+
**Z-Image（造相）** 是阿里巴巴通义实验室开发的一个强大且高效的图像生成模型，拥有 **6B** 参数。它采用 **可扩展单流 DiT**（S3-DiT）架构，将文本、视觉语义 token 和图像 VAE token 在序列级别进行拼接，作为统一的输入流，最大化参数效率。
10+
11+
**模型变体**：
12+
- 🚀 **Z-Image-Turbo** – 蒸馏版本，仅需 **8 NFEs**（函数评估次数）即可达到或超越领先竞争对手。在企业级 H800 GPU 上可实现**亚秒级推理延迟**，并可在 **16GB 显存的消费级设备**上运行。
13+
- 🧱 **Z-Image-Base** – 非蒸馏基础模型，用于社区驱动的微调和自定义开发。
14+
- ✍️ **Z-Image-Edit** – 针对图像编辑任务微调的变体，具有出色的指令遵循能力。
15+
16+
**模型亮点**：
17+
- **照片级真实质量**：在保持出色美学质量的同时，提供强大的照片级真实图像生成
18+
- **精准的双语文本渲染**：擅长准确渲染复杂的中英文文本
19+
- **提示词增强与推理**：提示词增强器赋予模型推理能力
20+
- **亚秒级推理**：在支持的硬件上实现快速生成
21+
22+
**相关链接**：
23+
- [GitHub](https://github.com/Tongyi-MAI/Z-Image)
24+
- [Hugging Face](https://huggingface.co/Tongyi-MAI/Z-Image-Turbo)
25+
26+
## Z-Image-Turbo 文生图工作流
27+
28+
<a className="prose" target='_blank' href="https://raw.githubusercontent.com/Comfy-Org/workflow_templates/refs/heads/main/templates/image_z_image_turbo.json" style={{ display: 'inline-block', backgroundColor: '#0078D6', color: '#ffffff', padding: '10px 20px', borderRadius: '8px', borderColor: "transparent", textDecoration: 'none', fontWeight: 'bold', marginRight: '10px'}}>
29+
<p className="prose" style={{ margin: 0, fontSize: "0.8rem" }}>下载 JSON 工作流文件</p>
30+
</a>
31+
32+
<a className="prose" target='_blank' href="https://cloud.comfy.org/?template=image_z_image_turbo&utm_source=docs" style={{ display: 'inline-block', backgroundColor: '#28a745', color: '#ffffff', padding: '10px 20px', borderRadius: '8px', borderColor: "transparent", textDecoration: 'none', fontWeight: 'bold'}}>
33+
<p className="prose" style={{ margin: 0, fontSize: "0.8rem" }}>在 ComfyUI Cloud 上运行</p>
34+
</a>
35+
36+
<UpdateReminder />
37+
38+
## 模型链接
39+
40+
**text_encoders（文本编码器）**
41+
42+
- [qwen_3_4b.safetensors](https://huggingface.co/Comfy-Org/z_image_turbo/resolve/main/split_files/text_encoders/qwen_3_4b.safetensors)
43+
44+
**diffusion_models（扩散模型）**
45+
46+
- [z_image_turbo_bf16.safetensors](https://huggingface.co/Comfy-Org/z_image_turbo/resolve/main/split_files/diffusion_models/z_image_turbo_bf16.safetensors)
47+
48+
**vae**
49+
50+
- [ae.safetensors](https://huggingface.co/Comfy-Org/z_image_turbo/resolve/main/split_files/vae/ae.safetensors)
51+
52+
**模型存储位置**
53+
54+
```
55+
📂 ComfyUI/
56+
├── 📂 models/
57+
│ ├── 📂 text_encoders/
58+
│ │ └── qwen_3_4b.safetensors
59+
│ ├── 📂 diffusion_models/
60+
│ │ └── z_image_turbo_bf16.safetensors
61+
│ └── 📂 vae/
62+
│ └── ae.safetensors
63+
```

0 commit comments

Comments
 (0)