Before you download: This workflow is not meant for fast generation. If you want speed, then this workflow is not what you want. If you're looking for a basic workflow, the comfyUI devs provided a bunch here. There's also other (possibly better) workflows here on civitai as well.
Updating ComfyUI, installing custom nodes, etc., can break your Comfy install. Do these at your own risk. I am not responsible for your install breaking. These are all built and tested on the "portable" version of ComfyUI. Desktop app users may have to jump through some hoops to get things working.
Please be aware my workflows are not a one-size-fits-all solution for all comfyUI users, nor are they intended to be. They were designed for my personal use. This workflow can be heavy to use for some folks since it does everything in one go.
The general idea behind my workflows is to plug in whatever settings and prompts, queue it up, and let it go from start to finish. The workflows that are marked "Simple" are (by my standards) simple.
You can add or remove whatever you want from the workflow, since you're the one using it. Just understand that you are responsible for troubleshooting if something breaks.
My recommendation for anyone having questions on what certain nodes do and what settings to use: look it up. I'm not saying that to be a dick, I am saying it because there are smarter people than me who have posted videos and walkthroughs on how to use just about everything ComfyUI related. Various custom node github project pages also have good (and accurate) information. You can also gamble and try asking your preferred AI chat. I am definitely no sort of authority on all things comfyUI.
If you have RES4LYF (or other custom samplers or schedulers) installed: v13* and lower will probably not work. v14+ should work with RES4LYF in a limited capacity.
I don't guarantee that this workflow will work for you. Your comfyui install is 99.999% likely to have something different from my comfyui install.
Nodes 2.0: I do not recommend using Nodes 2.0, but you do you. Expect weird issues if you enable this feature. I am not providing support for any Nodes 2.0 issues.
Each version has notes on what changed under "about this version" to the right.
I've disabled DMs since I am getting spammed way too much for the same questions repeatedly. Check the discussions below, because chances are someone asked already.
Random people have also been soliciting me in a roundabout way to make them a workflow. I'll just say it flat out: I'm not interested and chances are you don't want to pay me for my time. Post a bounty instead. There's plenty of talented people on this platform.
IMG2IMG (on the workflows that have it)
YMMV on denoise settings and may depend on the source image. I have no control over how comfy does this.
Sample run at 0.5 denoise:
Original:
Resulting Image:

Description
Added a very basic ControlNet & IMG2IMG group (same as 13e)
If you don't know how to use ControlNet or IMG2IMG, there's plenty of info out there.
ControlNet:
I basically don't use it and when I do, it's just as a more complicated version of IMG2IMG.
TL;DR for Image 2 Image in this workflow:
Put your source image into the Load Image node.
Adjust the denoise to something below 1.0.
Change the toggle on the Latent Switch to 2.
Click Run.
As previously mentioned:
The Global Seed and Global Sampler nodes will override any of the settings related to them across the workflow.
Using a sampler or scheduler not compatible with any of the nodes will result in an error.
You can bypass or delete these two nodes if you want to do these settings manually on each node.
CFG is tied to the “CFG” node to the left of the KSampler.
Delete this node if you want to set CFG manually on each node.
The detailers can be used for whatever you want as long as you have the detections models.
The detailer nodes used in this workflow take all detected items and do them at the same time.
You can use whatever detection model you want. You don't have to use what I use.
If you’re using the Nodes 2.0 feature: you are on your own.
Custom nodes used in this workflow: