You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Copy file name to clipboardExpand all lines: MyApp/_pages/ai-server/comfy-extension.md
+15-12Lines changed: 15 additions & 12 deletions
Display the source diff
Display the rich diff
Original file line number
Diff line number
Diff line change
@@ -3,20 +3,23 @@ title: ComfyUI Extension
3
3
description: Installing and configuring the ComfyUI extension
4
4
---
5
5
6
-
# ComfyUI Extension
6
+
ComfyUI is a powerful workflow tool for various AI related tasks including the ability to create images from text, images from images, and more. It is a key component of AI Server that provides a wide range of processing capabilities.
7
7
8
-
ComfyUI is a powerful image generation and manipulation tool that can be used to create images from text, images from images, and more. It is a key component of AI Server that provides a wide range of image processing capabilities.
9
-
As a way to leverage the ComfyUI API in a more accessible manner, we have support for ComfyUI as a provider type in AI Server. This allows you to easily integrate ComfyUI into your AI Server instance using it as a remote self-hosted agent capable of processing image requests, and other modalities.
8
+
One issue it has though is that it can be difficult to integrate with other systems. The ComfyUI API consists of converting a JSON workflow definition to an API format with very specific requirements.
9
+
10
+
As a way to leverage the ComfyUI API in a more accessible manner, we have created a [ComfyUI Agent](https://github.com/serviceStack/agent-comfy) repository so you can more easily use ComfyUI workflows and add it to be a provider in AI Server. This allows you to integrate a ComfyUI Agent into your AI Server instance using it as a remote self-hosted agent capable of processing image requests, and other modalities.
11
+
12
+
Since a lot of AI workloads require GPUs or other specialized hardware, the ComfyUI Agent can be run on a separate machine with the necessary hardware, and AI Server can be configured to use it as a provider for these kinds of tasks.
10
13
11
14
## Installing the ComfyUI Extension
12
15
13
-
To install this more easily, [we have put together a Docker image and a Docker Compose file](https://github.com/serviceStack/agent-comfy) that you can use to get started with ComfyUI in AI Server that is already bundled with the ComfyUI extension, and all the necessary dependencies.
16
+
To install this more easily, [we have put together a Docker image and a Docker Compose file](https://github.com/serviceStack/agent-comfy) that you can use to get started with ComfyUI Agent in AI Server that is already bundled with the pretty simple extension, and all the necessary dependencies.
14
17
15
-
### Running the ComfyUI Extension
18
+
### Running the ComfyUI Agent
16
19
17
-
To run the ComfyUI extension, you can use the following steps:
20
+
To run the ComfyUI Agent, you can use the following steps:
18
21
19
-
1.**Clone the Repository**: Clone the ComfyUI extension repository from GitHub.
22
+
1.**Clone the Repository**: Clone the ComfyUI Agent repository from GitHub.
@@ -45,23 +48,23 @@ To run the ComfyUI extension, you can use the following steps:
45
48
46
49
### .env Configuration
47
50
48
-
The `.env` file is used to configure the ComfyUI extension during the initial setup, and is the easiest way to get started.
51
+
The `.env` file is used to configure the ComfyUI Agent during the initial setup, and is the easiest way to get started.
49
52
50
53
The keys available in the `.env` file are:
51
54
52
55
- **DEFAULT_MODELS**: Comma-separated list of models to load on startup. This will be used to automatically download the models and their related dependencies. The full list of options can be found on your AI Server at `/lib/data/media-models.json`.
53
-
- **API_KEY**: This is the API key that will be used by your AI Server to authenticate with the ComfyUI. If not provided, there will be no authentication required to access your ComfyUI instance.
56
+
- **API_KEY**: This is the API key that will be used by your AI Server to authenticate with the ComfyUI. If not provided, there will be no authentication required to access your ComfyUI Agent instance.
54
57
- **HF_TOKEN**: This is the Hugging Face token that will be used to authenticate with the Hugging Face API when trying to download models. If not provided, models requiring Hugging Face authentication like those with user agreements will not be downloaded.
55
58
- **CIVITAI_TOKEN**: This is the Civitai API key that will be used to authenticate with the Civitai API when trying to download models. If not provided, models requiring Civitai authentication like those with user agreements will not be downloaded.
56
59
57
60
::: info
58
61
Models requiring authentication to download are also flagged in the `/lib/data/media-models.json` file.
59
62
:::
60
63
61
-
### Accessing the ComfyUI Extension
64
+
### Accessing the ComfyUI Agent
62
65
63
-
Once the ComfyUI extension is running, you can access the ComfyUI instance at [http://localhost:7860](http://localhost:7860) and can be used as a standard ComfyUI instance.
64
-
The AI Server has pre-defined workflows to interact with your ComfyUI instance to generate images, audio, text, and more.
66
+
Once the ComfyUI Agent is running, you can access the ComfyUI Agent instance at [http://localhost:7860](http://localhost:7860) and can be used as a standard ComfyUI.
67
+
The AI Server has pre-defined workflows to interact with your ComfyUI Agent instance to generate images, audio, text, and more.
65
68
66
69
These workflows are found in the AI Server AppHost project under `workflows`. These are templated JSON versions of workflows you save in the ComfyUI web interface.
0 commit comments