<p>note: this model will only be updated when an entirely new node has been released. get incremental updates via comfy manager or git pull.</p><h1 id="comfyui-plaguekind-nodes">ComfyUI-PlagueKind-Nodes</h1><p>A utility node pack for ComfyUI focused on structured LoRA stacking and unified image/mask resizing for consistent workflow behavior across models.</p><hr /><h1 id="included-nodes">Included Nodes</h1><h2 id="ltx-lora-loader-stack">LTX LoRA Loader Stack</h2><p>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.</p><h3 id="features">Features</h3><ul><li><p>10 independent LoRA slots</p></li><li><p>Enable / disable per slot</p></li><li><p>Per-slot strength control</p></li><li><p>Optional split control for LTX models:</p><ul><li><p>Video branch multiplier</p></li><li><p>Audio branch multiplier</p></li></ul></li><li><p>Works as a standard LoRA loader for non-LTX models</p></li><li><p>Searchable LoRA selection menu</p></li><li><p>Folder-aware organization and display</p></li><li><p>Missing file detection warning</p></li><li><p>Drag and drop slot reordering</p></li><li><p>Compact UI designed for mobile and desktop use</p></li></ul><h3 id="behavior">Behavior</h3><p>For non-LTX models, the node functions as a normal LoRA stacker using combined strength values.<br />For LTX workflows, it supports separated audio and video branch weighting when applicable.</p><hr /><h2 id="unified-resize-image-mask">Unified Resize Image / Mask</h2><p>A single consistent resizing node for both images and masks using a unified geometric pipeline.</p><h3 id="features">Features</h3><ul><li><p>Multiple scaling modes:</p><ul><li><p>Dimensions (W × H)</p></li><li><p>Multiplier</p></li><li><p>Longer Side</p></li><li><p>Shorter Side</p></li><li><p>Total Pixels (Megapixels)</p></li></ul></li><li><p>Aspect ratio preservation option</p></li><li><p>Center crop mode</p></li><li><p>Divisible-by constraint (useful for latent-based workflows like LTX / SDXL)</p></li><li><p>Unified image + mask transformation pipeline</p></li><li><p>Stable tensor-based mask resizing (no mismatch between image and mask geometry)</p></li></ul><h3 id="purpose">Purpose</h3><p>Prevents common ComfyUI issues such as:</p><ul><li><p>image and mask misalignment after resizing</p></li><li><p>inconsistent crop behavior between nodes</p></li><li><p>unstable mask scaling in inpainting workflows</p></li></ul><hr /><h1 id="installation">Installation</h1><h2 id="option-1-(recommended)">Option 1 (Recommended)</h2><p>Install via <strong>ComfyUI Manager</strong></p><h2 id="option-2-manual-install">Option 2 Manual Install</h2><pre><code>cd ComfyUI/custom_nodes
git clone https://github.com/PlagueKind/Comfyui-PlagueKind-Nodes.git
</code></pre><p>Restart ComfyUI.</p><hr /><h1 id="requirements">Requirements</h1><p>No external dependencies required beyond standard ComfyUI installation.</p><p>Uses:</p><ul><li><p>torch</p></li><li><p>comfy.utils</p></li></ul><hr /><h1 id="notes">Notes</h1><ul><li><p>LoRA Loader Stack is fully compatible with standard LoRA workflows</p></li><li><p>LTX branch controls only apply when used with compatible models</p></li><li><p>Unified Resize ensures identical transformations for images and masks</p></li></ul><hr /><h1 id="license">License</h1><p>MIT License</p><hr /><h1 id="support">Support</h1><p>If you find this useful, consider supporting development:</p><p>Monero (XMR):<br />865BrcfWLdwELwuq5faV1uVTbh93zVK6AUYLY2c3mX6sFfAGRfS6axe1kBTYYKuM7ccN7zBZDAZvnT7E4NKmUazySdbpc7p</p>

Files with SHA256: f794c53eabab5cc2c3ffca36e5d0637263e719e788f20e2af3e483f6d23703fa