Install this extension via the ComfyUI Manager by searching
for wlsh_nodes
1. Click the Manager button in the main menu
2. Select Custom Nodes Manager button
3. Enter wlsh_nodes in the search bar
After installation, click the Restart button to
restart ComfyUI. Then, manually
refresh your browser to clear the cache and access
the updated list of nodes.
Visit
ComfyUI Online
for ready-to-use ComfyUI environment
The wlsh_nodes extension for ComfyUI includes nodes like Checkpoint Loader with Name, Save Prompt Info, Outpaint to Image, CLIP Positive-Negative, SDXL Quick Empty Latent, and more, enhancing functionality and workflow efficiency.
wlsh_nodes Introduction
The wlsh_nodes extension is a collection of custom nodes designed for use with ComfyUI, a user interface for AI-based image generation. Created by the author to address minor annoyances and implement various features, this extension offers a range of functionalities that can significantly enhance your workflow. Whether you need to read or write metadata to saved images, generate latent images at specific resolutions, or perform advanced image processing tasks, wlsh_nodes has you covered. This extension is particularly useful for AI artists looking to streamline their creative process and achieve more precise control over their outputs.
How wlsh_nodes Works
At its core, wlsh_nodes operates by providing specialized nodes that can be integrated into your ComfyUI workflows. Think of nodes as building blocks that perform specific tasks, such as loading models, generating images, or applying filters. By connecting these nodes in various ways, you can create complex workflows tailored to your specific needs.
For example, if you want to generate an image with specific metadata, you can use the "Image Save with Prompt" node to embed this information directly into the image file. Similarly, if you need to generate a latent image with a particular aspect ratio, you can use the "Empty Latent by Ratio" node to quickly create it. Each node is designed to perform a specific function, and by combining them, you can achieve a wide range of effects and optimizations.
wlsh_nodes Features
Loaders
Checkpoint Loader with Name: This node functions like a regular checkpoint loader but also outputs the name of the loaded model as a string. This is useful for saving filenames that include the model name.
Samplers
KSamplerAdvanced (WLSH): An enhanced version of the advanced KSampler, this node includes a denoising option for experimentation and an INFO output that provides sampler settings for use in other nodes.
Conditioning
CLIP Positive-Negative: A simple CLIP box with positive and negative prompt boxes, available in both standard and SDXL versions.
CLIP Positive-Negative w/Text: Similar to the above but includes two output nodes for positive and negative inputs to other nodes, also available in SDXL.
CLIP +/- w/Text Unified (WLSH): Combines prompt/conditioning for SD1.5 and SDXL, with some feature sacrifices for SDXL.
Latent
Empty Latent by Pixels: Quickly generate an empty latent by selecting an aspect ratio, orientation, and megapixel count.
Empty Latent by Ratio: Generate an empty latent by selecting an aspect ratio, orientation, and the length of the shorter side.
Empty Latent by Size: Similar to the default empty latent node but also provides width and height as integer outputs.
SDXL Quick Empty Latent: Quickly generate an empty latent of a size from a list of ideal SDXL image sizes.
Image
Image Load with Metadata: Extract metadata from Auto1111-sourced images or images saved with this extension's nodes.
Grayscale Image: Converts an input image to grayscale, useful for certain controlnet actions.
Inpainting
Generate Border Mask: Creates a mask with blurred edges for outpainting, useful for smoothing out edges.
Outpaint to Image: Extends an image in a selected direction and outputs the expanded image and a mask of the outpainted region.
VAE Encode for Inpaint Padding: Encodes an image and mask for the sampler, with options for padding/blur to improve inpainting.
Upscaling
Image Scale by Factor: Scales an image by a predefined factor without a model.
Image Scale by Shortside: Scales an image by specifying the shorter side's length, maintaining the aspect ratio.
SDXL Quick Image Scale: Quickly scales an image to one of the ideal SDXL resolutions.
Upscale by Factor with Model: Scales an image using an upscale model, allowing you to define the multiplier factor.
Numbers
Multiply Integer: Multiplies an integer by another integer.
Quick Resolution Multiplier: Multiplies width and height by a specified factor.
Resolutions by Ratio: Returns width and height based on a specified ratio.
Seed to Number: Converts a SEED type to an INT.
Seed and Int: Generates a seed and outputs it as both INT and SEED.
SDXL Steps: Outputs three different integers for use as step counts in SDXL workflows.
SDXL Resolutions: Outputs height and width integers from a list of optimal SDXL resolutions.
Text
Build Filename String: Constructs a filename from various inputs, useful for saving files with specific naming conventions.
Time String: Returns a formatted string of the current time, useful for filenames or debugging.
Simple Pattern Replace: Performs a find/replace operation on an input string.
Simple String Combine: Combines two strings with a selected separator.
Prompt Weight: Adds weight to an input string, useful for prompt adjustments.
IO
Image Save with Prompt: Saves an image with embedded prompt information, similar to Auto1111.
Image Save with Prompt File: Saves an image with embedded metadata and a matching text file.
Save Prompt: Saves prompts to a text file, including model name and seed.
Save Positive Prompt: Saves only the positive prompt to a text file.
Troubleshooting wlsh_nodes
Common Issues and Solutions
Node Compatibility: Some nodes may not be compatible with third-party node suites. Ensure you are using nodes that are known to work well together.
Metadata Extraction: If metadata is not being extracted correctly, make sure you are using a compatible version of ComfyUI (commit d7b3b0f8c11c6261d0d8b859ea98f2d818b7e67d or newer).
Image Scaling: If the image scaling results are not as expected, double-check the input parameters and ensure they match the desired output.
Frequently Asked Questions
Q: How do I save an image with specific metadata?
A: Use the "Image Save with Prompt" node and provide the necessary inputs for model name, seed, and other metadata.
Q: Can I use these nodes with other third-party nodes?
A: While many nodes are compatible, some may have issues. It's best to test compatibility in your specific workflow.
Learn More about wlsh_nodes
For additional resources, tutorials, and community support, consider exploring the following:
ComfyUI Documentation
AI Art Community Forums
Video Tutorials on YouTube
These resources can provide you with more in-depth knowledge and help you get the most out of the wlsh_nodes extension.