WARNING: this is not a lora its a ref mod!
its realy easy to do ref mod
no training or anything like prompting
im going to say it
no single model can do anime as well as minimax h3 even seedance2.5
i found out minimax h3 is much better in ref mods than loras
i mean very better
super accurate to orginal
download these 2 nodes:
https://github.com/FranckyB/ComfyUI-H3RefModPicker
https://github.com/Luisacaotica/ComfyUI-MiniMaxH3Mod
---
load them like how you load loras
---
version 2.0:
the right eye was fixed (it was invisible)
Description
FAQ
Comments (5)
The new method of reference figures seems to be working well. When actually using it, do we need to describe <subject1> like this, or has Safetensors already included the unique identifier for the figures?
RadomAccessForSep 26, 2026
Can you provide parameter settings for creating refmod? I tried creating it myself, but the effect was not as good as what you provided
Just use the name
In this case "rem"
You dont need a subject
@RadomAccessFor use the nodes that i put in discription
You dont need any tweaks
@to_MacDonalds_and_beyond after test, node "Create H3 RefMod Master" should use mod = "Full Reference" :)