note: this model will only be updated when an entirely new node has been released. get incremental updates via comfy manager or git pull.
ComfyUI-PlagueKind-Nodes
A utility node pack for ComfyUI focused on structured LoRA stacking and unified image/mask resizing for consistent workflow behavior across models.
Included Nodes
LTX LoRA Loader Stack
A 10-slot LoRA stacking system designed for advanced workflows, including LTX models, while remaining fully compatible as a standard LoRA loader for other architectures.
Features
10 independent LoRA slots
Enable / disable per slot
Per-slot strength control
Optional split control for LTX models:
Video branch multiplier
Audio branch multiplier
Works as a standard LoRA loader for non-LTX models
Searchable LoRA selection menu
Folder-aware organization and display
Missing file detection warning
Drag and drop slot reordering
Compact UI designed for mobile and desktop use
Behavior
For non-LTX models, the node functions as a normal LoRA stacker using combined strength values.
For LTX workflows, it supports separated audio and video branch weighting when applicable.
Unified Resize Image / Mask
A single consistent resizing node for both images and masks using a unified geometric pipeline.
Features
Multiple scaling modes:
Dimensions (W × H)
Multiplier
Longer Side
Shorter Side
Total Pixels (Megapixels)
Aspect ratio preservation option
Center crop mode
Divisible-by constraint (useful for latent-based workflows like LTX / SDXL)
Unified image + mask transformation pipeline
Stable tensor-based mask resizing (no mismatch between image and mask geometry)
Purpose
Prevents common ComfyUI issues such as:
image and mask misalignment after resizing
inconsistent crop behavior between nodes
unstable mask scaling in inpainting workflows
Installation
Option 1 (Recommended)
Install via ComfyUI Manager
Option 2 Manual Install
cd ComfyUI/custom_nodes
git clone https://github.com/PlagueKind/Comfyui-PlagueKind-Nodes.git
Restart ComfyUI.
Requirements
No external dependencies required beyond standard ComfyUI installation.
Uses:
torch
comfy.utils
Notes
LoRA Loader Stack is fully compatible with standard LoRA workflows
LTX branch controls only apply when used with compatible models
Unified Resize ensures identical transformations for images and masks
License
MIT License
Support
If you find this useful, consider supporting development:
Monero (XMR):
865BrcfWLdwELwuq5faV1uVTbh93zVK6AUYLY2c3mX6sFfAGRfS6axe1kBTYYKuM7ccN7zBZDAZvnT7E4NKmUazySdbpc7p
Description
Comments (9)
Recommended installation via comfy manager or github, this link will only be updated when a new node is released.
looked very interesting but lora node only allows one decimal, so weird i've never seen something like this, which makes it pretty useless for finetuning a lora, there can be a huge difference between 0.1 - 0.2 with some loras, so pretty useless imho.
So you mean you want to be able to select something like 0.15? If so i can update that tomorrow
it was a quick fix, go ahead and update via comfy manager or git pull.
@Plaguekind I just checked it and it's perfect now, thanks a lot!
@skyrimer3d no problem, thanks for pointing it out, and thanks for the buzz
The users complaint about only accepting single decimals for lora loader has already been fixed.
Resize node also has a display at the bottom for final resolution, so if you were using a get image size node you can safely remove that node and only use mine as a single node now.
update via comfy manager or git pull.
Good eye deer. Advanced weighting is absolutely essential with LTX, ditching the audio data completely is my default. There are a few global LoRAs that can work in a regular stack but anything else, forget about it. My LoRA switching graph of individual advanced loaders has grown to an absurd size, and saving merges bakes in weights, so this is exactly what I need. I'm surprised LoRA Manager hasn't addressed it yet. I was about to write my own, it's such a no-brainer, but of course someone has done it already. Thanks.
Glad you found it useful