Skip to content

Commit 9d0cac3

Browse files
mintlify[bot]mintlify[bot]
authored
Add Ovis-Image documentation (#616)
* Update tutorials/image/ovis/ovis-image.mdx * Update zh-CN/tutorials/image/ovis/ovis-image.mdx * Update docs.json * Update docs.json * Update tutorials/image/ovis/ovis-image.mdx * Update zh-CN/tutorials/image/ovis/ovis-image.mdx --------- Co-authored-by: mintlify[bot] <109931778+mintlify[bot]@users.noreply.github.com>
1 parent 1cb690e commit 9d0cac3

File tree

3 files changed

+120
-0
lines changed

3 files changed

+120
-0
lines changed

‎docs.json‎

Lines changed: 12 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -150,6 +150,12 @@
150150
"tutorials/image/z-image/z-image-turbo"
151151
]
152152
},
153+
{
154+
"group": "Ovis",
155+
"pages": [
156+
"tutorials/image/ovis/ovis-image"
157+
]
158+
},
153159
"tutorials/image/cosmos/cosmos-predict2-t2i",
154160
"tutorials/image/omnigen/omnigen2"
155161
]
@@ -773,6 +779,12 @@
773779
"zh-CN/tutorials/image/z-image/z-image-turbo"
774780
]
775781
},
782+
{
783+
"group": "Ovis",
784+
"pages": [
785+
"zh-CN/tutorials/image/ovis/ovis-image"
786+
]
787+
},
776788
"zh-CN/tutorials/image/cosmos/cosmos-predict2-t2i",
777789
"zh-CN/tutorials/image/omnigen/omnigen2"
778790
]

‎tutorials/image/ovis/ovis-image.mdx‎

Lines changed: 54 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,54 @@
1+
---
2+
title: "Ovis-Image ComfyUI Workflow Example"
3+
description: "Ovis-Image is a 7B text-to-image model specifically optimized for high-quality text rendering, designed to operate efficiently under stringent computational constraints."
4+
sidebarTitle: "Ovis-Image"
5+
---
6+
7+
import UpdateReminder from '/snippets/tutorials/update-reminder.mdx'
8+
9+
**Ovis-Image** is a 7B text-to-image model built upon [Ovis-U1](https://github.com/AIDC-AI/Ovis-U1), specifically optimized for high-quality text rendering. It delivers text rendering quality comparable to much larger 20B-class systems while remaining compact enough to run on widely accessible hardware.
10+
11+
**Model Highlights**:
12+
- **Strong Text Rendering at 7B Scale**: Delivers text rendering quality comparable to much larger 20B-class systems like Qwen-Image and competitive with leading closed-source models like GPT4o in text-centric scenarios
13+
- **High Fidelity on Text-Heavy Prompts**: Excels on prompts that demand tight alignment between linguistic content and rendered typography (e.g., posters, banners, logos, UI mockups, infographics)
14+
- **Accurate Bilingual Text Rendering**: Produces legible, correctly spelled, and semantically consistent text in both Chinese and English across diverse fonts, sizes, and aspect ratios
15+
- **Efficiency and Deployability**: Fits on a single high-end GPU with moderate memory, supports low-latency interactive use
16+
17+
**Related Links**:
18+
- [GitHub](https://github.com/AIDC-AI/Ovis-Image)
19+
- [Hugging Face](https://huggingface.co/AIDC-AI/Ovis-Image-7B)
20+
21+
## Ovis-Image text-to-image workflow
22+
23+
<a className="prose" target='_blank' href="https://raw.githubusercontent.com/Comfy-Org/workflow_templates/refs/heads/main/templates/image_ovis_text_to_image.json" style={{ display: 'inline-block', backgroundColor: '#0078D6', color: '#ffffff', padding: '10px 20px', borderRadius: '8px', borderColor: "transparent", textDecoration: 'none', fontWeight: 'bold'}}>
24+
<p className="prose" style={{ margin: 0, fontSize: "0.8rem" }}>Download JSON Workflow File</p>
25+
</a>
26+
27+
<UpdateReminder />
28+
29+
## Model links
30+
31+
**text_encoders**
32+
33+
- [ovis_2.5.safetensors](https://huggingface.co/Comfy-Org/Ovis-Image/resolve/main/split_files/text_encoders/ovis_2.5.safetensors)
34+
35+
**diffusion_models**
36+
37+
- [ovis_image_bf16.safetensors](https://huggingface.co/Comfy-Org/Ovis-Image/resolve/main/split_files/diffusion_models/ovis_image_bf16.safetensors)
38+
39+
**vae**
40+
41+
- [ae.safetensors](https://huggingface.co/Comfy-Org/z_image_turbo/resolve/main/split_files/vae/ae.safetensors)
42+
43+
**Model Storage Location**
44+
45+
```
46+
📂 ComfyUI/
47+
├── 📂 models/
48+
│ ├── 📂 text_encoders/
49+
│ │ └── ovis_2.5.safetensors
50+
│ ├── 📂 diffusion_models/
51+
│ │ └── ovis_image_bf16.safetensors
52+
│ └── 📂 vae/
53+
│ └── ae.safetensors
54+
```

‎zh-CN/tutorials/image/ovis/ovis-image.mdx‎

Lines changed: 54 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,54 @@
1+
---
2+
title: "Ovis-Image ComfyUI 工作流示例"
3+
description: "Ovis-Image 是一个 7B 文生图模型，专门针对高质量文本渲染进行优化，旨在严格的计算约束下高效运行。"
4+
sidebarTitle: "Ovis-Image"
5+
---
6+
7+
import UpdateReminder from '/snippets/zh/tutorials/update-reminder.mdx'
8+
9+
**Ovis-Image** 是一个基于 [Ovis-U1](https://github.com/AIDC-AI/Ovis-U1) 构建的 7B 文生图模型，专门针对高质量文本渲染进行优化。它能够提供与更大的 20B 级别系统相当的文本渲染质量，同时保持足够紧凑，可在常见硬件上运行。
10+
11+
**模型亮点**：
12+
- **7B 规模下的强大文本渲染**：提供与 Qwen-Image 等更大的 20B 级别系统相当的文本渲染质量，在文本场景中与 GPT4o 等领先的闭源模型具有竞争力
13+
- **文本密集型提示词的高保真度**：擅长处理需要语言内容与渲染排版紧密对齐的提示词（如海报、横幅、标志、UI 模型、信息图表）
14+
- **精准的双语文本渲染**：在各种字体、大小和宽高比下，生成清晰、拼写正确且语义一致的中英文文本
15+
- **高效且易于部署**：可在单个高端 GPU 上运行，内存需求适中，支持低延迟交互使用
16+
17+
**相关链接**：
18+
- [GitHub](https://github.com/AIDC-AI/Ovis-Image)
19+
- [Hugging Face](https://huggingface.co/AIDC-AI/Ovis-Image-7B)
20+
21+
## Ovis-Image 文生图工作流
22+
23+
<a className="prose" target='_blank' href="https://raw.githubusercontent.com/Comfy-Org/workflow_templates/refs/heads/main/templates/image_ovis_text_to_image.json" style={{ display: 'inline-block', backgroundColor: '#0078D6', color: '#ffffff', padding: '10px 20px', borderRadius: '8px', borderColor: "transparent", textDecoration: 'none', fontWeight: 'bold'}}>
24+
<p className="prose" style={{ margin: 0, fontSize: "0.8rem" }}>下载 JSON 工作流文件</p>
25+
</a>
26+
27+
<UpdateReminder />
28+
29+
## 模型链接
30+
31+
**text_encoders（文本编码器）**
32+
33+
- [ovis_2.5.safetensors](https://huggingface.co/Comfy-Org/Ovis-Image/resolve/main/split_files/text_encoders/ovis_2.5.safetensors)
34+
35+
**diffusion_models（扩散模型）**
36+
37+
- [ovis_image_bf16.safetensors](https://huggingface.co/Comfy-Org/Ovis-Image/resolve/main/split_files/diffusion_models/ovis_image_bf16.safetensors)
38+
39+
**vae**
40+
41+
- [ae.safetensors](https://huggingface.co/Comfy-Org/z_image_turbo/resolve/main/split_files/vae/ae.safetensors)
42+
43+
**模型存储位置**
44+
45+
```
46+
📂 ComfyUI/
47+
├── 📂 models/
48+
│ ├── 📂 text_encoders/
49+
│ │ └── ovis_2.5.safetensors
50+
│ ├── 📂 diffusion_models/
51+
│ │ └── ovis_image_bf16.safetensors
52+
│ └── 📂 vae/
53+
│ └── ae.safetensors
54+
```

0 commit comments

Comments
 (0)