A Guide to ComfyUI: Workflows, Models, and Configuration

ComfyUI is a complimentary application that enables you to generate AI images and videos locally on your own machine. Designed for users who seek greater control than what standard prompt-and-generate tools offer, it allows you to visualise and fine-tune every stage of the generation process. While this flexibility does introduce a learning curve, this guide will walk you through the essentials, from installation to executing and customising your first workflow.

Pre-Requisites

To run ComfyUI, your computer requires sufficient GPU resources to handle the models and workflows you intend to use. Generally, larger models and more resource-intensive workflows will demand higher amounts of VRAM.

You will also need the specific model files required by your chosen workflow. Depending on the model type, these files may include checkpoints, diffusion models, VAEs, text encoders, LoRAs, or other components. Typically, these are stored within the ComfyUI/models directory.

If your local hardware lacks a suitable GPU, you have the option to run ComfyUI on a remote GPU-powered desktop. This setup shifts the heavy computational load to the remote GPU while allowing you to access the environment from your standard computer.

Installing ComfyUI

For Windows and macOS users, ComfyUI recommends the desktop application for new users. However, other installation methods are available, such as manual installation or using the ComfyUI command-line tool. The best approach depends on your specific operating system and technical setup.

Once ComfyUI is installed, launch the application to open the interface. Here you will find the workflow canvas along with the tools necessary to create and manage your workflows.

The Importance of ComfyUI Workflows

A ComfyUI workflow defines the precise method for generating an image or video. It governs the models, settings, and processing steps used to achieve the final output.

This offers significantly more control than a simple prompt box. You can swap models, integrate a LoRA, utilise an input image, tweak generation parameters, upscale the result, or incorporate additional processing steps.

Workflows can be saved and reused. Rather than reconstructing the same setup repeatedly, you can retain a workflow that yields satisfactory results and simply adjust individual settings as needed. Additionally, you can download workflows created by other users and adapt them to your own environment.

Understanding ComfyUI Workflows

A workflow consists of interconnected nodes. Each node performs a specific function within the generation process, and the connections between them dictate how data flows through the system.

A basic text-to-image workflow typically includes nodes for loading a model, inputting a prompt, creating initial image data, generating the image, decoding the result, and saving the final file.

• Model loader: Loads the model designated for generation.
• Text encoder: Converts your prompt into data usable by the model.
• Sampler: Executes the generation process using the selected settings.
• VAE: Translates between latent data and a visible image.
• Save Image: Writes the generated image to disk.

You are not required to build every workflow from scratch. ComfyUI offers workflow templates, and many community-created workflows are available for direct download and opening.

Loading an Existing Workflow

Utilising an existing workflow is often the simplest way to begin. ComfyUI provides example workflows for various models and tasks, while community platforms offer an extensive additional selection.

Many workflow images embed the workflow data within their metadata. You can simply drag the image into ComfyUI or use Workflows → Open to load it. The workflow will appear on the canvas with its nodes and settings already configured.

Once the workflow is loaded, verify which models it expects. If required files are missing, ComfyUI can identify these gaps for supported workflow templates. For other workflows, you may need to locate and install the necessary models manually.

Sourcing Models for ComfyUI

Models can be found on repositories such as Hugging Face and Civitai, as well as on the official project pages for the models themselves. The key is to find a model that is compatible with the workflow you wish to use.

It is important not to assume that any model file will work with any workflow. Different model architectures may require specific loaders and supporting files.

Before downloading a model, consider the following:

• The model architecture and version
• The required ComfyUI workflow
• The model file format
• Recommended VRAM and hardware specifications
• Any required VAE, text encoder, LoRA, or other supporting files
• The model's license and usage restrictions

ComfyUI supports various types of model files. The destination folder depends on the model type. For instance, checkpoints are placed in models/checkpoints, LoRAs in models/loras, and VAEs in models/vae. Some newer models utilise folders such as models/diffusion_models and models/text_encoders.

Installing a Model

After downloading a model, place it in the directory expected by the workflow. You can then select it within the corresponding model loader.

For example, a checkpoint might be stored in:

ComfyUI/models/checkpoints/

A LoRA might instead be stored in:

ComfyUI/models/loras/

If the new model does not appear in the model list, refresh the interface or restart ComfyUI.

Installing Custom Nodes

Many advanced ComfyUI workflows rely on custom nodes that are not part of the standard installation. If these dependencies are missing, the workflow may display errors indicating missing nodes.

ComfyUI includes a Manager for installing custom nodes. Alternatively, nodes can be installed manually by placing their repositories in the custom_nodes directory and installing their required dependencies.

Only install custom nodes from trusted sources. Custom nodes can contain executable code and may carry their own dependencies and security implications.

Running and Modifying Your Workflow

Once the required models and custom nodes are installed, review the key settings within the workflow. Begin by checking the model, prompt, image dimensions, and sampling settings.

When everything is prepared, use the Queue button to execute the workflow. ComfyUI will process each step and produce the output defined by the workflow structure.

You can then modify individual components of the workflow without rebuilding it. Add a LoRA, connect an input image, change the sampler, add an upscaler, or adjust other parameters to alter the final result.

Saving Your Workflows

Save workflows that you intend to reuse. While a workflow contains the node graph and its settings, it does not necessarily include the model files themselves. Keep a record of which models and custom nodes the workflow requires.

This is particularly important when transferring a workflow to another computer or cloud desktop. You may need to install the same models and custom nodes before the workflow will function correctly.

Try ComfyUI on DaDesktop

You do not need to purchase a new GPU solely to run ComfyUI. If your current computer lacks sufficient GPU resources, you can run ComfyUI on a cloud desktop instead and use it as needed.

DaDesktop provides cloud desktops equipped with dedicated GPU resources, ideal for workloads such as AI image and video generation. You can install ComfyUI, download your desired models, and build your own workflows without adding a dedicated GPU to your local machine.

Learn more about AI image and video generation on DaDesktop. You can also view the available GPUs and select a configuration based on the models and workflows you plan to run.