Once ComfyUI is installed and running, adding workflows is as easy as dragging and dropping images or workflows created by ComfyUI into the empty area of the browser window.
This basic workflow generates an image based on the positive and negative prompts.
* processing starts with the "checkpoint", which is loaded by the Load Checkpoint node on the left.
* Information from the chekcpoint is sent to the two clip boxes, along the node path, and along the model path.
* The clip text encode node attached to the KSampler's _positive_ input in the _Positive Prompt_.
* The clip text encode node attached to the KSampler's _negative_ input in the _Negative Prompt_.
* The Empty Latent Image is the "starting image", is a blank bit of noise. Rather like a painter's canvas.
* The _Model_ is all the raw information _Stable Diffusion_ uses through the Sampler to resolve noise into images.
* I don't know what the fuck VAEs are, but they're important.
* all models contain a VAE, but not all models have a good VAE.
* an external VAE can be added to the workflow through a VAE laoder, see below.
* The _KSampler_ node has a number of options. I won't go over all of them here, but for right now the most important are:
* The _Seed_ is a number used for randomness. All things being equal, a workflow with the same seed will spit out the same image.
* If the seed doesn't change and nothing else changes, ComfyUI won't even process the workflow. The result is the same as last time. If nothing else changes and the seed does, then new images will be generated. They can vary wildly from one to the next.
* This makes it easy to tell if nothing has changed.
* The line under the seed is how new seeds are generated.
* fixed: they aren't. Seed stays the same. Useful for checking othetr parameters and generating the same basic image.
* Increment/Decriment: the seed changes by +/- 1.
* Random: Holdy Changing Numbers, Batman!
* values are changed by clicking the arrows to scroll through the options or clicking directly on a value to see a list.
* a noodle can be pulled from the _VAE Decode_ node's input and dropped to show a Vae Loader in the menu, but that'll be messy. Let's save messy workflows for crazy vixens like comfy and mike.
