Getting Started with ComfyUI: Setup, Models, and Workflows

ComfyUI is a complimentary application that enables local generation of AI-powered images and videos on your personal machine. Designed for users seeking greater control than standard prompt-and-generate tools offer, it provides visibility into and the ability to adjust every stage of the generation process. While this flexibility involves a learning curve, this guide will walk you through the essentials, from installation to executing and customizing your initial workflow.

Prerequisites for Getting Started

To run ComfyUI, your computer must have sufficient GPU resources to handle the specific models and workflows you intend to use. More complex models and demanding workflows typically consume greater amounts of VRAM.

You will also require the specific model files needed for your workflow. Depending on the architecture, this may include checkpoints, diffusion models, VAEs, text encoders, LoRAs, or other components. These files are generally 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-enabled desktop. This approach offloads the generation tasks to the remote hardware while allowing you to access the interface from your standard computer.

Installing ComfyUI

For Windows and macOS users, the ComfyUI team recommends the desktop application for beginners. Other installation options exist, including manual setup and the use of the ComfyUI command-line tool. The best method depends on your specific operating system and environment.

Once ComfyUI is installed, launch the application to open the interface. You will find the workflow canvas along with the tools necessary for creating and managing your workflows.

The Importance of ComfyUI Workflows

A ComfyUI workflow defines the exact process by which an image or video is generated. It governs the models, settings, and processing steps that lead to the final output.

This offers significantly more control than a simple prompt box. You can swap models, integrate LoRAs, use input images, tweak generation parameters, upscale results, or insert additional processing steps.

Furthermore, workflows can be saved and reused. Instead of recreating configurations from scratch, you can retain a workflow that yields preferred results and modify specific settings as needed. You can also download and adapt workflows created by other community members.

Understanding ComfyUI Workflows

Workflows consist of connected nodes. Each node manages a specific aspect of the generation process, while the connections dictate how data flows between them.

A standard text-to-image workflow might include nodes for loading a model, inputting a prompt, initializing image data, generating the image, decoding the result, and saving the file.

• Model loader: Loads the generation model.
• Text encoder: Translates your prompt into a format the model can process.
• Sampler: Executes the generation process based on selected settings.
• VAE: Converts between latent data and visual image data.
• Save Image: Writes the final image to your disk.

There is no need to construct every workflow from the ground up. ComfyUI offers built-in templates, and many community-created workflows are available for direct download and use.

Loading Existing Workflows

Utilizing an existing workflow is often the simplest way to begin. ComfyUI includes example workflows for various models and tasks, and community platforms host many more options.

Many workflow images contain the underlying workflow data within their metadata. You can drag the image directly into ComfyUI or navigate to Workflows → Open to load it. The workflow will appear on the canvas with all nodes and settings pre-configured.

After loading, verify which models the workflow expects. If files are missing, ComfyUI can identify these gaps for supported templates. For other workflows, you may need to locate and install the missing models independently.

Sourcing Models for ComfyUI

Models can be found on repositories like Hugging Face and Civitai, as well as on the specific project page for the model. The key is ensuring the model is compatible with the workflow you intend to use.

Do not assume that any model file will work in any workflow. Different architectures may require specific loaders and supporting files.

Before downloading a model, consider the following:

• The model architecture and version
• The specific ComfyUI workflow required
• The model file format
• Recommended VRAM and hardware requirements
• Necessary VAEs, text encoders, LoRAs, or other supporting files
• The model's license and usage restrictions

ComfyUI supports various model file types, each stored in specific folders. For instance, checkpoints reside in models/checkpoints, LoRAs in models/loras, and VAEs in models/vae. Newer models may use directories such as models/diffusion_models and models/text_encoders.

Installing a Model

Once you have downloaded 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 located in:

ComfyUI/models/checkpoints/

A LoRA might be stored in:

ComfyUI/models/loras/

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

Installing Custom Nodes

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

ComfyUI includes a Manager to facilitate the installation of custom nodes. Alternatively, you can install them manually by placing their repositories in the custom_nodes directory and installing their respective dependencies.

Only install custom nodes from trusted sources. Since custom nodes can contain executable code, they may have unique dependencies and security considerations.

Running and Modifying Workflows

With the necessary models and custom nodes installed, review the key settings in your workflow. Start by checking the model, prompt, image dimensions, and sampling parameters.

Once ready, use the Queue button to execute the workflow. ComfyUI will process each step and produce the output defined by the node graph.

You can then tweak individual components without rebuilding the entire workflow. Add a LoRA, connect an input image, change the sampler, include an upscaler, or adjust other settings to alter the result.

Saving Your Workflows

Save workflows you plan to reuse. Note that a workflow file contains the node graph and settings but not necessarily the model files themselves. Keep track 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.

Experience ComfyUI on DaDesktop

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

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

Learn more about AI image and video generation on DaDesktop. You can also view the available GPUs to choose a configuration suited to your models and workflows.