Skip to content

Commit 0acb9c9

Browse files
authored
Remove Kontext dev grouped (#387)
1 parent c8cafe2 commit 0acb9c9

File tree

2 files changed

+2
-87
lines changed

2 files changed

+2
-87
lines changed

tutorials/flux/flux-1-kontext-dev.mdx

Lines changed: 1 addition & 46 deletions
Original file line numberDiff line numberDiff line change
@@ -84,7 +84,7 @@ Model save location
8484
│ └── t5xxl_fp16.safetensors or t5xxl_fp8_e4m3fn_scaled.safetensors
8585
```
8686

87-
## Flux.1 Kontext Dev Basic Workflow
87+
## Flux.1 Kontext Dev Workflow
8888

8989
This workflow is a normal workflow, but it uses the `Load Image(from output)` node to load the image to be edited, making it more convenient for you to access the edited image for multiple rounds of editing.
9090

@@ -110,49 +110,4 @@ You can refer to the numbers in the image to complete the workflow run:
110110
5. In the `CLIP Text Encode` node, modify the prompts, only English is supported
111111
6. Click the `Queue` button, or use the shortcut `Ctrl(cmd) + Enter` to run the workflow
112112

113-
## Flux.1 Kontext Dev Grouped Workflow
114-
115-
This workflow uses the **FLUX.1 Kontext Image Edit** group node, making the interface and workflow reuse simpler.
116-
117-
This example also uses two images as input, using the `Image Stitch` node to combine two images into one, and then using Flux.1 Kontext for editing.
118-
119-
### 1. Workflow and Input Image Download
120-
121-
Download the following files and drag them into ComfyUI to load the corresponding workflow
122-
123-
![ComfyUI Flux Kontext Native Workflow](https://raw.githubusercontent.com/Comfy-Org/example_workflows/main/flux/kontext/dev/flux_1_kontext_dev_grouped.png)
124-
125-
**Input Images**
126-
127-
![ComfyUI Flux Kontext Native Workflow Input](https://raw.githubusercontent.com/Comfy-Org/example_workflows/main/flux/kontext/dev/doll_1.webp)
128-
![ComfyUI Flux Kontext Native Workflow Input](https://raw.githubusercontent.com/Comfy-Org/example_workflows/main/flux/kontext/dev/doll_2.webp)
129-
130-
### 2. Complete the workflow step by step
131-
132-
![Workflow Step Guide](/images/tutorial/flux/flux_1_kontext_dev_grouped_step_guide.jpg)
133-
You can refer to the numbers in the image to complete the workflow run:
134-
135-
1. In the `Load VAE` node, load the `ae.safetensors` model
136-
2. In the `Load Image` node, load the first provided input image
137-
3. In the `Load Image` node, load the second provided input image
138-
4. Since other models and related nodes are packaged in the group node, you need to follow the reference in the step diagram to ensure that the corresponding models are correctly loaded and write prompts
139-
5. Click the `Queue` button, or use the shortcut `Ctrl(cmd) + Enter` to run the workflow
140-
141-
## New Flux.1 Kontext Dev Selection Toolbox Feature
142-
143-
To make it easier for users to edit with Flux.1 Kontext Dev, we have added a selection toolbox feature. This feature allows users to quickly and conveniently add the `FLUX.1 Kontext Image Edit` group node.
144-
You can watch the video demo below. When you select the `Load Image` node, you can find the new edit button in the selection toolbox.
145-
146-
<Tip>
147-
This feature is currently experimental and may be adjusted in future versions.
148-
</Tip>
149-
150-
<iframe
151-
className="w-full aspect-video rounded-xl"
152-
src="https://www.youtube.com/embed/X7ArunILYBw?si=2iNo9ESsyE8zsQV3"
153-
title="ComfyUI Selection Toolbox New Features"
154-
allow="accelerometer; clipboard-write; encrypted-media; gyroscope; picture-in-picture"
155-
allowFullScreen
156-
></iframe>
157-
158113
<PromptTechniques/>

zh-CN/tutorials/flux/flux-1-kontext-dev.mdx

Lines changed: 1 addition & 41 deletions
Original file line numberDiff line numberDiff line change
@@ -85,7 +85,7 @@ FLUX.1 Kontext 是 Black Forest Labs 推出的突破性多模态图像编辑模
8585
│ └── t5xxl_fp16.safetensors 或者 t5xxl_fp8_e4m3fn_scaled.safetensors
8686
```
8787

88-
## Flux.1 Kontext Dev Basic 工作流
88+
## Flux.1 Kontext Dev 工作流
8989

9090
这个工作流是正常的工作流,不过使用了 `Load Image(from output)` 节点来加载需要编辑的图像可以让你更方便地获取到编辑后的图像,从而进行多轮次编辑
9191

@@ -111,44 +111,4 @@ FLUX.1 Kontext 是 Black Forest Labs 推出的突破性多模态图像编辑模
111111
5.`CLIP Text Encode` 节点中修改提示词,仅支持英文
112112
5. 点击 `Queue` 按钮,或者使用快捷键 `Ctrl(cmd) + Enter(回车)` 来运行工作流
113113

114-
## Flux.1 Kontext Dev Grouped 工作流
115-
116-
这个工作流是使用组节点 **FLUX.1 Kontext Image Edit** 的工作流,使得整个界面和工作流复用起来变得简单
117-
118-
同时这个示例也使用了两个图像进行输入通过 `Image Stitch` 节点将两个图像拼接成一个图像,并使用 Flux.1 Kontext 进行编辑。
119-
120-
### 1. 工作流及输入图片下载
121-
122-
下载下面的文件,并拖入 ComfyUI 中加载对应工作流
123-
124-
![ComfyUI Flux Kontext 原生工作流](https://raw.githubusercontent.com/Comfy-Org/example_workflows/main/flux/kontext/dev/flux_1_kontext_dev_grouped.png)
125-
126-
**输入图片**
127-
128-
![ComfyUI Flux Kontext 原生工作流输入](https://raw.githubusercontent.com/Comfy-Org/example_workflows/main/flux/kontext/dev/doll_1.webp)
129-
![ComfyUI Flux Kontext 原生工作流输入](https://raw.githubusercontent.com/Comfy-Org/example_workflows/main/flux/kontext/dev/doll_2.webp)
130-
131-
### 2. 按步骤完成工作流的运行
132-
133-
![工作流步骤图](/images/tutorial/flux/flux_1_kontext_dev_grouped_step_guide.jpg)
134-
你可参考图片中的序号来完成图工作流的运行:
135-
136-
1.`Load VAE` 节点中加载 `ae.safetensors` 模型
137-
2.`Load Image` 节点中加载提供的第一个输入图像
138-
3.`Load Image` 节点中加载提供的第二个输入图像
139-
4. 由于其它模型和相关节点都被组节点打包,你需要按照步骤图中的参考同样确保对应的模型已经正确加载,并书写提示词
140-
5. 点击 `Queue` 按钮,或者使用快捷键 `Ctrl(cmd) + Enter(回车)` 来运行工作流
141-
142-
## 新增的 Flux.1 Kontext Dev 选择工具箱功能
143-
144-
此次为了方便用户使用 Flux.1 Kontext 进行编辑,我们新增了选择工具箱功能,用户可以更加方便地快速添加 `FLUX.1 Kontext Image Edit` 组节点,具体可以查看下面的视频演示,当你选中 `Load Image` 节点时,就可以在选择工具箱中找到新增的编辑按钮
145-
<iframe
146-
className="w-full aspect-video rounded-xl"
147-
src="//player.bilibili.com/player.html?isOutside=true&aid=114758506253384&bvid=BV1tCK1zGENB&cid=30735339422&p=1&autoplay=0"
148-
title="ComfyUI 选择工具箱新增功能"
149-
frameBorder="0"
150-
allow="accelerometer; clipboard-write; encrypted-media; gyroscope; picture-in-picture"
151-
allowFullScreen
152-
></iframe>
153-
154114
<PromptTechniques/>

0 commit comments

Comments
 (0)