Manage ComfyUI using ComfyUI Launcher

ComfyUI Launcher is the core management tool of ComfyUI for administrator users. You can use it to control the running status of the ComfyUI service within the cluster, while easily managing models, plugins, runtime environment, and network configurations.

This guide walks you through using ComfyUI Launcher for service management and routine maintenance.

Learning objectives

By the end of this tutorial, you will learn how to:

• Start and stop the ComfyUI service for all users in the cluster.
• Verify and adjust network settings so GitHub, PyPI, and Hugging Face are accessible.
• Install essential models and additional models, and understand where models are stored in Files.
• Manage plugins registered in ComfyUI Launcher as well as from GitHub.
• Manage Python dependencies by installing, updating, removing packages, and analyzing missing dependencies for plugins.
• Troubleshoot common issues using logs and safely reset ComfyUI to its initial state when necessary.

Start and stop the service

As the administrator, you must start the ComfyUI service before you or other members can access it via the client interface.

• Start ComfyUI service

  Go to Home and click the START button in the upper-right corner.

  Notes on first run

  • Initial startup of ComfyUI Launcher typically takes 10-20 seconds for environment initialization.
  • If the system prompts that essential models are missing, you can click START ANYWAY. However, workflows may fail without these base models. We recommend downloading the essential model package before starting the service.

• Stop ComfyUI service

  Go to Home and click the STOP button when ComfyUI is not in use. This releases VRAM and memory resources for other applications.

Configure network

ComfyUI relies heavily on external resources such as GitHub (plugins), PyPI (Python packages), and Hugging Face (models). Before installing components, verify the connection status in Network Config.

1. Go to Network Config.
2. Check the connectivity to GitHub, PyPI, and Hugging Face.
3. If any service shows Inaccessible, fix your network or proxy settings, and then click SAVE & CHECK to test again.
4. Repeat until the status of each service becomes Accessible.

Manage files and directories

ComfyUI Launcher provides quick access to key directories and uses a shared model folder so models can be reused across ComfyUI and SD Web UI.

Access file locations

On the Home tab, the File Type section provides direct access to the main directories used by ComfyUI:

Entry	Location in Files	Description
Root	/Files/External/olares/ai/ comfyui/ComfyUI	Root directory of the ComfyUI installation.
Plugin	/Files/External/olares/ai/ comfyui/ComfyUI/custom_nodes	Stores installed plugins (custom nodes and extensions).
Model	/Files/External/olares/ai/model	Centralized storage for AI models shared by ComfyUI and other AI apps.
Output	/Files/External/olares/ai/ output/comfyui	Default destination for images and other assets generated by ComfyUI.
Input	/Files/External/olares/ai/ comfyui/ComfyUI/input	Folder for source images used in image-to-image or in-painting workflows.

Clicking any of these entries opens the Files app directly in the corresponding directory.

Understand the model directory structure

ComfyUI in Olares uses a file structure that differs from the standard installation. This change allows models to be shared between ComfyUI and SD Web UI.

When uploading external models manually or selecting a destination in Custom Download, it is important to place files into the correct subfolder.

TIP

Make sure the model type matches the target folder so that ComfyUI can detect and use the files correctly.

Directory in Files	Standard ComfyUI directory	Model type
main/	checkpoints/	Base checkpoints (SD 1.5, SDXL, Flux)
lora/	loras/	LoRA weights
vae/	vae/	VAE models
controlnet/	controlnet/	ControlNet models
ipadapter/	ipadapter/	IP-Adapter models
upscale_models/	upscale_models/	Upscalers (ESRGAN, SwinIR)
clip_vision/	clip_vision/	CLIP Vision models (used for IP-Adapter)
unet/	unet/	Standalone UNet weights
text_encoders/	text_encoders/	Text encoder models (T5, CLIP-L/G)
clip/	clip/	CLIP models
embeddings/	embeddings/	Textual Inversion embeddings
hypernetworks/	hypernetworks/	Hypernetwork weights
facerestore_models/	facerestore_models/	Face restoration (GFPGAN, CodeFormer)
inpaint/	inpaint/	Inpainting-specific models
style_models/	style_models/	Style or effect models
diffusion_models/	diffusion_models/	Other diffusion models

Manage models

ComfyUI Launcher provides flexible ways to manage models: install the essential package with one click, download from the built-in library or a Hugging Face link, upload directly to Files, and delete models when needed.

Install essential models

Essential models are basic resources required for ComfyUI to run, including SD large models, VAE, preview decoders, and auxiliary tool models. We recommend installing them on the first run.

1. Open the package page in either of the following ways:

   • In the Missing essential models prompt window that appears on first start, click INSTALL MODELS.
   • Go to Home, scroll to the Package installation section, find Stable Diffusion base package, and click VIEW. This package provides the necessary foundation for ComfyUI, including VAEs, utility models, and preview decoders.

2. On the Package Details page, click GET ALL to start the automatic installation. You can track the progress in the status bar.

   

Install additional models

In addition to the essential models, ComfyUI Launcher supports installing additional models from the built-in library, via a Hugging Face link, or by uploading files manually.

Download from built-in library

Follow these steps to download a model from the built-in Hugging Face library:

1. Go to Model management.

2. Scroll down to the Available models section, and find the desired model by category or keyword.

3. Click the download button to install the model.

   

Download via link

If you can't find a specific model in the built-in library, you can install it via the model URL on Hugging Face:

1. Go to Model management > Custom Download.

2. Fill in the model URL and select the destination path based on the model type.

3. Click DOWNLOAD MODEL.

   

Upload external models

If you can't find the desired model on Hugging Face, you can upload external models via Files.

1. Open Files from the launchpad.
2. Go to External > olares > ai > model.
3. Find the folder that your downloaded model belongs to and upload the file directly inside the target folder. See Understand the model directory structure for reference.

Delete models

To delete a model:

1. Go to Model management > Model library.
2. Under the Installed models section, find the model you want to delete, and click the delete button on the right to delete it.

Manage plugins

ComfyUI Launcher provides flexible ways to manage plugins in Plugin management.

Manage available plugins

To manage available plugins registered in ComfyUI Launcher:

1. Go to Plugin management > Plugin library.
2. Under Available Plugins, find the target plugin.

For any plugin, you can:

• Click the visibility button to view plugin details.
• Visit the GitHub repository if it is available.

Depending on the plugin status, different actions are available:

• Not installed: Click Install to get the latest version, or Switch version to choose a specific one.
• Installed: You can Disable, Uninstall, or Switch version.
• Disabled: Click Enable to reactivate it, or Uninstall to remove it.

At the top of the section, you can also:

• Click UPDATE ALL PLUGINS to update all installed plugins.
• Click REFRESH to refresh the plugin list.

Install plugins from GitHub

To install plugins directly from GitHub repositories:

1. Go to Plugin management > Custom Install.
2. Enter the GitHub repository URL of the plugin.
3. (Optional) Specify the branch. If you are not sure, keep the default value.
4. Click INSTALL PLUGIN.

Manage Python environment

ComfyUI's operation relies on a set of Python dependency libraries. You can manage these libraries easily on the Python dependency management page.

Install dependency libraries

1. Go to Python dependencies > INSTALL NEW PACKAGE.
2. In the pop-up window, enter the library name and version number (optional), and then click INSTALL.

Manage installed dependency libraries

1. Go to Python dependencies.
2. Under the Installed Python packages tab, find the Python library you want to manage.
3. Click the arrow_upward button on the right to update the library, or the delete button to remove it.

Analyze dependency installation status

1. Go to Python dependencies > Dependency analysis.
2. Click ANALYZE NOW to start analyzing.
3. From the plugins list on the left, find the problematic plugin highlighted in red, and click on it.
4. From Dependency list, find the missing library for the plugin, and click the Install button on the right. You can also click FIX ALL to automatically install all missing libraries.

Troubleshoot and maintain ComfyUI

ComfyUI Launcher provides tools to help diagnose and maintain the ComfyUI service.

Export ComfyUI logs

You can export logs to diagnose the current running status of ComfyUI:

1. Go to Home and click more_vert in the upper-right corner, then click View logs to view the current running log.
2. Click the refresh button to refresh the log, and the download button to download the log.

Reset ComfyUI configuration

Perform with caution

Restoring ComfyUI is an irreversible operation. Please operate carefully.

To reset ComfyUI to its initial state:

1. Go to Home and click more_vert in the upper-right corner, then click Wipe and restore.
2. In the prompt window, click WIPE AND RESTORE.
3. Enter CONFIRM, then click CONFIRM.

After the restoration operation is complete, restart ComfyUI for the changes to take effect.