This ComfyUI work flow starts off with a base image made with SD1.5, and carries it through some upscaling and detail steps using SDXL. A lot of it is for fun, but I personally like the look and the creative freedom of SD1.5 as the base image, particularly in certain poses, as well as saving a bunch of VRAM in ControlNet if you choose to go that route.
Make sure you have the ComfyUI Manager installed to easily acquire all the nodes needed for this workflow.
The models I am using are listed in the recommended resources as well as in notes on the workflow.
If you like what I do here, please consider supporting my work via Ko-fi <3
https://ko-fi.com/pixelworldai
Make sure to check out the AIpub Discord and Mastodon!
Description
FAQ
Looks like we don't have an active mirror for this file right now.
CivArchive is a community-maintained index — we catalog mirrors that volunteers upload to HuggingFace, torrents, and other public hosts. Looks like no one has uploaded a copy of this file yet.
Some files do get recovered over time through contributions. If you're looking for this one, feel free to ask in Discord, or help preserve it if you have a copy.