How to create consistent character with Stable Diffusion in ComfyUI

A walk-through on how to create a consistent character with Stable Diffusion in ComfyUI.

Download links for this ComfyUI workflow, SDXL model, controlnet model, and ip adapter model.

Tutorial of this workflow in A1111

Stable Diffusion guided course

[MarDos]

Awesome workflow! The best I tried so far! And it works perfect on my silicon M1! Thank you so much for the tutorial!🍄

[maxsj]

Thanks for the example. If it's not difficult, it would be interesting to see your own examples and experiments in ComfyUI

[PaulRoneClarke]

But what do you do with those images? How do you create a consistent character with those head shots? Am I missing something? As I was watching I thought you were then going to use those images to train a LoRA or something? Which I was hoping you would show as the next step. Am I missing something?

[GenevieveSinclair]

It's just a character sheet. By itself, it doesn't mean, you can generate multiple different images with the same character. Even the sheet not consistent, just similar.

[slotsmaster]

how do i download the control net model? do you have the link for it?

[grobknoblin]

This was awsome! all the resources ready for us, explained clearly! you are amazing I had a ton of issues getting the ipadapter working lmao but thats my fault (had wrong version of python installed lmao) I got amazing results you are the best! I cant wait to watch all your videos! You earned a sub from me! Can wait to see what else you make! one question say if the mask isnt exactly getting the face how do you change that so the mask better fits the faces im getting some cut off on the sides of the image?

[behrampatel]

Hi can this also be done for entire characters?
For example a sprite sheet for a game character running ? Or is it only suitable for faces.
Thanks

[check]

Unfortunately I don't have enough gpu vram to do this many faces on a character sheet. I am using an amd 6900xt on windows with directml, and even after decreasing the resolution to 664x664 it stops on the face detailer node.

[nevzatist]

Why am I getting this error?

Error occurred when executing

ClipVision model not found.

File "C:\Users\nevzatt\Downloads\Yapaylar\ComfyUI_windows_portable\ComfyUI\execution.py", line 151, in recursive_execute
output_data, output_ui = get_output_data(obj, input_data_all)

File "C:\Users\nevzatt\Downloads\Yapaylar\ComfyUI_windows_portable\ComfyUI\execution.py", line 81, in get_output_data
return_values = map_node_over_list(obj, input_data_all, obj.FUNCTION, allow_interrupt=True)

File "C:\Users\nevzatt\Downloads\Yapaylar\ComfyUI_windows_portable\ComfyUI\execution.py", line 74, in map_node_over_list
results.append(getattr(obj, func)(**slice_dict(input_data_all, i)))

File "C:\Users\nevzatt\Downloads\Yapaylar\ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyUI_IPAdapter_plus\IPAdapterPlus.py", line 511, in load_models
raise Exception("ClipVision model not found.")

[RubenTainoAI]

1. Where are the results? 2. Where did you get the original 9 images? 3. What happens if the characters of my story are animals? — Please understand why people need consistent characters. They are needed for AI Videos, like Pika, Haiper, Genmo. Not everyone can make videos locally, since the minimum requirements are 12gb to 16gb of GPU. So must people depend on WebUI for the videos. Others need them for Children books. I know how to make a children book, but I need consistent characters. So I need the 9 image for every animal in the story. Where do I get the first 9 images? I just want an answer, because everybody is talking about consistent characters, a no one is showing a real solution. Apparently we will need to wait for the Spatial AI to be available to the public.