Skip to content

Commit 8683af7

Browse files
mintlify[bot]mintlify[bot]
authored
Add FLUX.2 Dev tutorials in English and Chinese (#596)
* Update tutorials/flux/flux-2-dev.mdx * Update zh-CN/tutorials/flux/flux-2-dev.mdx * Update docs.json * Update docs.json * Update tutorials/flux/flux-2-dev.mdx * Update zh-CN/tutorials/flux/flux-2-dev.mdx * Update tutorials/flux/flux-2-dev.mdx * Update zh-CN/tutorials/flux/flux-2-dev.mdx * Update tutorials/flux/flux-2-dev.mdx * Update zh-CN/tutorials/flux/flux-2-dev.mdx * Update tutorials/flux/flux-2-dev.mdx * Update zh-CN/tutorials/flux/flux-2-dev.mdx * Update tutorials/flux/flux-2-dev.mdx * Update zh-CN/tutorials/flux/flux-2-dev.mdx --------- Co-authored-by: mintlify[bot] <109931778+mintlify[bot]@users.noreply.github.com>
1 parent 2d81fd9 commit 8683af7

File tree

3 files changed

+130
-0
lines changed

3 files changed

+130
-0
lines changed

‎docs.json‎

Lines changed: 2 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -117,6 +117,7 @@
117117
{
118118
"group": "Flux",
119119
"pages": [
120+
"tutorials/flux/flux-2-dev",
120121
"tutorials/flux/flux1-krea-dev",
121122
"tutorials/flux/flux-1-kontext-dev",
122123
"tutorials/flux/flux-1-text-to-image",
@@ -738,6 +739,7 @@
738739
{
739740
"group": "Flux",
740741
"pages": [
742+
"zh-CN/tutorials/flux/flux-2-dev",
741743
"zh-CN/tutorials/flux/flux1-krea-dev",
742744
"zh-CN/tutorials/flux/flux-1-kontext-dev",
743745
"zh-CN/tutorials/flux/flux-1-text-to-image",

‎tutorials/flux/flux-2-dev.mdx‎

Lines changed: 64 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,64 @@
1+
---
2+
title: "ComfyUI Flux.2 Dev Example"
3+
description: "This guide provides a brief introduction to the Flux.2 model and guides you through using the Flux.2 Dev model for text-to-image generation in ComfyUI."
4+
sidebarTitle: "Flux.2 Dev"
5+
---
6+
7+
import UpdateReminder from '/snippets/tutorials/update-reminder.mdx'
8+
9+
## About FLUX.2
10+
11+
[FLUX.2](https://bfl.ai/blog/flux-2) is a next-generation image model from [Black Forest Labs](https://blackforestlabs.ai/), delivering up to 4MP photorealistic output with far better lighting, skin, fabric, and hand detail. It adds reliable multi-reference consistency (up to 10 images), improved editing precision, better visual understanding, and professional-class text rendering.
12+
13+
**Key Features:**
14+
- **Multi-Reference Consistency:** Reliably maintains identity, product geometry, textures, materials, wardrobe, and composition intent across multiple outputs
15+
- **High-Resolution Photorealism:** Generates images up to 4MP with real-world lighting behavior, spatial reasoning, and physics-aware detail
16+
- **Professional-Grade Control:** Exact pose control, hex-code accurate brand colors, any aspect ratio, and structured prompting for programmatic workflows
17+
- **Usable Text Rendering:** Produces clean, legible text across UI screens, infographics, and multi-language content
18+
19+
**Available Models:**
20+
- **FLUX.2 Dev:** Open-source model (used in this tutorial)
21+
- **FLUX.2 Pro:** API version from Black Forest Labs
22+
23+
<Note>
24+
We are using quantized weights in this workflow. The original FLUX.2 repository is available [here](https://huggingface.co/black-forest-labs/FLUX.2-dev/).
25+
</Note>
26+
27+
<UpdateReminder/>
28+
29+
## Flux.2 Dev Workflow
30+
31+
<a className="prose" target='_blank' href="https://raw.githubusercontent.com/Comfy-Org/workflow_templates/refs/heads/main/templates/image_flux2.json" style={{ display: 'inline-block', backgroundColor: '#0078D6', color: '#ffffff', padding: '10px 20px', borderRadius: '8px', borderColor: "transparent", textDecoration: 'none', fontWeight: 'bold', marginRight: '10px'}}>
32+
<p className="prose" style={{ margin: 0, fontSize: "0.8rem" }}>Download JSON Workflow File</p>
33+
</a>
34+
35+
<a className="prose" target='_blank' href="https://cloud.comfy.org/?template=image_flux2&utm_source=docs" style={{ display: 'inline-block', backgroundColor: '#28a745', color: '#ffffff', padding: '10px 20px', borderRadius: '8px', borderColor: "transparent", textDecoration: 'none', fontWeight: 'bold'}}>
36+
<p className="prose" style={{ margin: 0, fontSize: "0.8rem" }}>Run on ComfyUI Cloud</p>
37+
</a>
38+
39+
## Model links
40+
41+
**text_encoders**
42+
43+
- [mistral_3_small_flux2_bf16.safetensors](https://huggingface.co/Comfy-Org/flux2-dev/resolve/main/split_files/text_encoders/mistral_3_small_flux2_bf16.safetensors)
44+
45+
**diffusion_models**
46+
47+
- [flux2_dev_fp8mixed.safetensors](https://huggingface.co/Comfy-Org/flux2-dev/resolve/main/split_files/diffusion_models/flux2_dev_fp8mixed.safetensors)
48+
49+
**vae**
50+
51+
- [flux2-vae.safetensors](https://huggingface.co/Comfy-Org/flux2-dev/resolve/main/split_files/vae/flux2-vae.safetensors)
52+
53+
**Model Storage Location**
54+
55+
```
56+
📂 ComfyUI/
57+
├── 📂 models/
58+
│ ├── 📂 text_encoders/
59+
│ │ └── mistral_3_small_flux2_bf16.safetensors
60+
│ ├── 📂 diffusion_models/
61+
│ │ └── flux2_dev_fp8mixed.safetensors
62+
│ └── 📂 vae/
63+
│ └── flux2-vae.safetensors
64+
```

‎zh-CN/tutorials/flux/flux-2-dev.mdx‎

Lines changed: 64 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,64 @@
1+
---
2+
title: "ComfyUI Flux.2 Dev 示例"
3+
description: "本文将简要介绍 Flux.2 模型，并指导你在 ComfyUI 中使用 Flux.2 Dev 模型进行文生图。"
4+
sidebarTitle: "Flux.2 Dev"
5+
---
6+
7+
import UpdateReminder from '/snippets/zh/tutorials/update-reminder.mdx'
8+
9+
## 关于 FLUX.2
10+
11+
[FLUX.2](https://bfl.ai/blog/flux-2) 是 [Black Forest Labs](https://blackforestlabs.ai/) 推出的下一代图像模型，可生成高达 4MP 的照片级真实输出，在光照、皮肤、织物和手部细节方面有显著提升。它支持可靠的多参考一致性（最多 10 张图像）、改进的编辑精度、更好的视觉理解能力以及专业级的文字渲染。
12+
13+
**主要特点：**
14+
- **多参考一致性：** 在多个输出中可靠地保持身份、产品几何形状、纹理、材质、服装和构图意图
15+
- **高分辨率照片级真实感：** 生成高达 4MP 的图像，具有真实世界的光照行为、空间推理和物理感知细节
16+
- **专业级控制：** 精确的姿势控制、十六进制精确的品牌颜色、任意宽高比以及用于程序化工作流的结构化提示
17+
- **可用的文字渲染：** 在 UI 界面、信息图表和多语言内容中生成清晰、易读的文字
18+
19+
**可用模型：**
20+
- **FLUX.2 Dev：** 开源模型（本教程使用）
21+
- **FLUX.2 Pro：** Black Forest Labs 的 API 版本
22+
23+
<Note>
24+
本工作流使用量化权重。原始 FLUX.2 仓库可在[此处](https://huggingface.co/black-forest-labs/FLUX.2-dev/)获取。
25+
</Note>
26+
27+
<UpdateReminder/>
28+
29+
## Flux.2 Dev 工作流
30+
31+
<a className="prose" target='_blank' href="https://raw.githubusercontent.com/Comfy-Org/workflow_templates/refs/heads/main/templates/image_flux2.json" style={{ display: 'inline-block', backgroundColor: '#0078D6', color: '#ffffff', padding: '10px 20px', borderRadius: '8px', borderColor: "transparent", textDecoration: 'none', fontWeight: 'bold', marginRight: '10px'}}>
32+
<p className="prose" style={{ margin: 0, fontSize: "0.8rem" }}>下载 JSON 工作流文件</p>
33+
</a>
34+
35+
<a className="prose" target='_blank' href="https://cloud.comfy.org/?template=image_flux2&utm_source=docs" style={{ display: 'inline-block', backgroundColor: '#28a745', color: '#ffffff', padding: '10px 20px', borderRadius: '8px', borderColor: "transparent", textDecoration: 'none', fontWeight: 'bold'}}>
36+
<p className="prose" style={{ margin: 0, fontSize: "0.8rem" }}>在 ComfyUI Cloud 上运行</p>
37+
</a>
38+
39+
## 模型链接
40+
41+
**text_encoders**
42+
43+
- [mistral_3_small_flux2_bf16.safetensors](https://huggingface.co/Comfy-Org/flux2-dev/resolve/main/split_files/text_encoders/mistral_3_small_flux2_bf16.safetensors)
44+
45+
**diffusion_models**
46+
47+
- [flux2_dev_fp8mixed.safetensors](https://huggingface.co/Comfy-Org/flux2-dev/resolve/main/split_files/diffusion_models/flux2_dev_fp8mixed.safetensors)
48+
49+
**vae**
50+
51+
- [flux2-vae.safetensors](https://huggingface.co/Comfy-Org/flux2-dev/resolve/main/split_files/vae/flux2-vae.safetensors)
52+
53+
**模型存储位置**
54+
55+
```
56+
📂 ComfyUI/
57+
├── 📂 models/
58+
│ ├── 📂 text_encoders/
59+
│ │ └── mistral_3_small_flux2_bf16.safetensors
60+
│ ├── 📂 diffusion_models/
61+
│ │ └── flux2_dev_fp8mixed.safetensors
62+
│ └── 📂 vae/
63+
│ └── flux2-vae.safetensors
64+
```

0 commit comments

Comments
 (0)