Basic Nodes and using Comfy UI

 What you see when you start Comfy UI are the basic building blocks of the interface. There are more complicated, more diverse, more niche case options, but we will come to those later. Lets take a look at what we have now. This is the basic screen that you will see when you click the load default button.

 

 

What does all this mean? Lets start from the left hand side:

 

Load Checkpoint:

 

This is the node that loads the Checkpoint, or model, that the ComfyUI engine will use to genereate images.  The three coloured dots on the left hand side are the outputs that this node uses. Model goes to KSampler, Clip goes in to the conditioning prompts, and the VAE is used to decode things. The colours will all match the corresponding inputs. Click the right arrow will pull up a menu with all the Checkpoints that you have installed.

Clip Text Encode (Prompt):

These nodes are the basic building blocks of ComfyUI. You tell the engine here what you want, in the top box, and what you dont want in the bottom box. Simple right? It is to start, but later on we will find out that things can get much more complicated, but easy to understand. Clip inputs come from the left, and conditioning inputs leave the right hand side. Each prompt is also a individual node.

 

KSampler:

 

KSampler is what makes the images. There are lots of options on here, what we are not going to talk about just yet. Inputs on the right hand side, model from the Checkpoint Loader, Positive and negative from the Clip text encode, and latent image from the next node.

Empty latent Image:

This creates a empty space for the image to appear in. Width and height are in pixels, and mostly determined by how powerful your computer is, but 512x512 is a good starting point, however I prefer 512x768 or 768x512. Batch size is how many images it will do at once, again dependent on your computer. The right side output connects to the latent image input on the KSampler.

VAE Decode:

This decodes what comes from the KSampler, and puts it to a viewable form that can be displayed and saved. Samples id from KSampler, VAE is (usually) from the model on Load Checkpoint, and the Image output moves it to a displayable file.

Save image:

Does exactly what it says it does. It saves the image into the output folder in your ComfyUI install folder. The filename prefix can be changed to whatever you want.

Menu:

Lots to see here but the main button is the Queue Promt button at the top. That starts the generation of the image.

 

Have a play around with some prompts, next time we will be talking about prompting and getting some different images.