76ee9a7d43ed41b3f90c36ed145dc65f1ef133b4
sn0w-scripts
A collection of nodes and improvements created mainly for testing loras and general ease
Get Started
Install
- Install ComfyUi.
- Clone this repo into
custom_nodes:cd ComfyUI/custom_nodes git clone https://github.com/sn0w12/ComfyUI-Sn0w-Scripts - Start up ComfyUI.
Important Note
Many of the nodes require these paths to be in your extra_model_paths.yaml (with your real directories of course).
- loras_xl: C:/path/XL
- loras_15: C:/path/1.5
Nodes
Find Resolution
An easy way to select a width and height.
Lora Selector
Automatically selects X amount of loras between two numbers.
ℹ️ See More Information
- Loras have to be formatted like the default kohya_ss outputs. (lora_name-000001)
- Select the first lora.
- Select the number of the highest lora you want to test.
- Select the amount of loras you want to test.
- Outputs list of loras like this: <lora:name:strength>
- Add default generation adds an extra "nothing" at the end of the list, used in Lora Tester to generate an image without the lora.
Lora Tester (XL)
Automatically generates X amount of images with provided loras.
Character Selector
Outputs a character name and prompt.
Prompt Combine
Combines 4 string to a single string.
Lora Stacker
Outputs a list of loras for Lora Tester.
Load Lora XL/1.5
Normal load lora but from another folder.
Load Lora Character
Finds and applies the closest matching Lora model to a character based on name similarity.
ℹ️ See More Information
- The process begins by cleaning the input character string for comparison. It then searches a JSON file for a matching character name. If a match is found, it proceeds to select the appropriate folder based on the
xlboolean flag.- To find the closest Lora model, it calculates the Levenshtein distance between the character name (in full and in parts) and the filenames of available Lora models. This ensures a case-insensitive match with the best possible model.
- If no lora is found it just returns the input model and the workflow can continue.
Example Workflows
Languages
Python
68.6%
HTML
17.5%
JavaScript
13.9%








