i have a how-to article for this version! find it here.
welcome to my workflow! version 2.5!
i want to thank everyone who has appreciated my images, which were generated using some version of this workflow, and everyone who has downloaded this and earlier versions. please leave a comment if you have any questions, i am happy to help!
if you have any trouble with finding or placing some of the weirder nodes and files, or you're getting errors that are super unhelpful, please please let me know! i am happy to assist if i can.
version 2.6 - new upscaler and detailer from lonecat! reverted the clip encoder because it started getting crashy. separated the detailers into a new area 3 and renumbered 3-5 as 4-6. updated the observer area to be less fancy.
what is this workflow for?
this workflow is for human and human-like character-focused images. it's designed around controlnet preprocessors that can pull randomly from images (poses) you have collected and provides lots and lots and lots of fine-tuning and options. the goal is to make it possible to set up a basic prompt and then generate a bunch of images using the pose templates you have organized.
how is this workflow organized?
there are six bookmarked areas (1 through 6). when you're first getting used to the workflow, go through each bookmarked area one by one and get things set up. later, most of your attention will be spent on bookmarks 4, 5 and 6. area 6 is where you watch everything come together when you start a run.
thanks again!
if you have any questions i will do my best to answer them. this was my first real workflow and it's probably got some issues and it has way too many noodles running all over. but i think it works pretty well and i hope it's easy to understand. thank you!
--sft--
Description
v1.9 - i've removed the flux guidance setting because it really doesn't do anything with any of the models i tested. but in exchange i've added an option to pad (extend) a loaded image to move a pose figure around the frame. instructions are in area 4! i have upgraded the face detailer to use sam3. this means you need to have triton installed as well. brief instructions are in the area.
FAQ
Comments (5)
when I try to run it comfyui give me error "Cannot read properties of undefined (reading 'workflow')" nothing in the terminal to guide me
do you know what version of comfyui you're running? if it's higher than 14.1 (frontend 1.39.2) you might run into some trouble, there are some custom nodes like rgthree that stopped working right and they still haven't gotten a fix out. i haven't seen that specific error before, but here's a bug report about the comfyui front end that references it:
https://github.com/Comfy-Org/ComfyUI_frontend/issues/7486
so it might be a similar thing. you could try the suggestion at the bottom of this thread:
https://github.com/Comfy-Org/ComfyUI_frontend/issues/8986
the commenters on the bug report say that you can update comfyui past 14.1 without causing problems but you need to revert the frontend back to 1.39.2, which you can do from a command line switch when you start comfyui (in the terminal or from a batch file). if this doesn't fix it please let me know and i will hunt around some more.
@SaoirseTeagan Thanks for the replay. Actually am on frontend 1.39.19 but I will give it a try to fix it at least I got the idea.
@xsulai i think the newest update fixes the rgthree issues, 0.17.1 and 1.41.19 - give that a try!