This is my most recent workflow that I am currently using. I am mostly active elsewhere under the username Gladas. I can be found at civitai if you need to contact me.

I am not interested in posting the workflow elsewhere or make any money from it. This is just a hobby for me. If you wish to post it somewhere else, feel free to do so.

I'm just someone who uses comfyUI and am not a developer. If you have technical questions, I probably can't help you. I make heavy use of Google when I don't know why something breaks or want to know what something does. However, I will try to help you within the best of my abilities for any non-technical questions.

This workflow does involve the use of several custom nodes. I will provide a list toward the end of the description.

I have notes in various places throughout the workflow to help provide information or at least guide on where to look for information.

The workflow works as follows:

1. Initial Image Generation
2. Second KSampler Pass
3. Watermark Detection and Removal
4. Ultimate SD Upscale
5. Second Ultimate SD Upscale pass
6. Face Detailer (Face)
7. Face Detailer (Eyes)
8. Color Correction
9. Save Image

Note: there are two Load Image nodes in the workflow. One is for IMG2IMG and the other is for ControlNet. AFAIK, you have to have an image in these nodes or the workflow will break. (Even if you are not using those portions of the workflow).

Most of the workflow has the ability to be bypassed. Anything that cannot be bypassed will have DNB in the group name.

The workflow has been tested on various Illustrious and Pony models. It should work with SDXL.

Here is a list of the custom nodes in use with this workflow. If I missed any, then my bad.

ComfyUI-Manager

ComfyUI-Impact-Pack

ComfyUI-Impact-Subpack (the Ultralytics Provider node was moved to here)

ComfyUI-Crystools

ComfyUI_Comfyroll_CustomNodes

ComfyUI-Custom-Scripts

ComfyUI-Detail-Daemon

comfyui-lama-remover

rgthree-comfy

comfyui-art-venture

ComfyUI_UltimateSDUpscale

ComfyUI_JPS-Nodes

ComfyUI-KJNodes

ComfyUI_essentials

ComfyLiterals

was-node-suite-comfyui

ComfyUI-Image-Saver

ComfyUI-ppm

sd-perturbed-attention

comfyui_controlnet_aux

Upscale Model:

You should be able to use whatever upscale model you like best. I primarily use 4xNomosWebPhoto_RealPLKSR now.

FaceDetailer Models:

If I recall, Impact Pack includes the needed models to get you started, but if you want something else, you can find more by using ComfyUI Manager's "Model Manager" option. The two types of models needed will be "Ultralytics" and "sam".

I use Anzhc's Face Seg Detection model for the ultralytics face detection model. It's still around on Huggingface, but no longer on civitai when I checked today. You'll have to Google it if you want the same model.

Watermark Detection Model:

I use this one.

VAE Model:

I usually use the normal SDXL VAE or whatever is baked into the checkpoint models.