Visit ComfyUI Online for ready-to-use ComfyUI environment
pythongosssss/ComfyUI-Custom-Scripts enhances ComfyUI with features like Auto Arrange Graph, Workflow SVG, Favicon Status, Image Feed, Latent Upscale, Lock Nodes & Groups, Lora Subfolders, Preset Text, Touch Support, and Workflow Management.
ComfyUI-Custom-Scripts is an extension designed to enhance the functionality of ComfyUI, a user interface for AI art generation. This extension provides a variety of custom scripts and nodes that can help streamline your workflow, improve the organization of your projects, and add new features to your AI art creation process. Whether you're looking to automate repetitive tasks, manage your projects more efficiently, or add new capabilities to your AI art tools, ComfyUI-Custom-Scripts has something to offer.
ComfyUI-Custom-Scripts works by adding custom nodes and scripts to your ComfyUI environment. These nodes and scripts can be used to automate tasks, manage your workflow, and add new features to your projects. For example, you can use the autocomplete feature to quickly insert commonly used words or phrases, or use the auto arrange graph feature to organize your project graph in a logical order. The extension also includes tools for managing images, customizing the appearance of your nodes, and more.
The autocomplete feature provides embedding and custom word autocomplete. You can view embedding details by clicking on the info icon on the list. Define your list of custom words via the settings. You can quickly default to danbooru tags using the Load button, or load/manage other custom word lists.
This feature adds a menu option to auto arrange the graph in order of execution, making very wide graphs more manageable.
Adds a setting to make moving nodes always snap to the grid, ensuring a neat and organized layout.
Adds custom Lora and Checkpoint loader nodes with the ability to show preview images. You can enable subfolders via the settings and add an "examples" widget to load sample prompts, trigger words, etc.
Adds a "View Info" menu option to view details about the selected LoRA or Checkpoint. To view embedding details, click the info button when using embedding autocomplete.
Checkpoint/LoRA/Embedding Info
Adds a node for resizing an image to a max & min size, optionally cropping if required.
Adds a custom color picker to nodes and groups, allowing you to personalize the appearance of your project.
Adds a favicon and title to the window. The favicon changes color while generating, and the window title includes the number of prompts in the queue.
Favicon Status (https://user-images.githubusercontent.com/125205205/230171227-31f061a6-6324-4976-bed9-723a87500cf3.png)
Adds a panel showing images that have been generated in the current session. You can control the direction that images are added and the position of the panel via the ComfyUI settings screen.
Provides a simple method to set custom denoise on the advanced sampler.
Adds a lock option to nodes and groups that prevents you from moving them until unlocked.
Lock Nodes & Groups (https://user-images.githubusercontent.com/125205205/230172868-5c5a943c-ade1-4799-bf80-cc931da5d4b2.png)
Allows for evaluating complex expressions using values from the graph. You can input INT
, FLOAT
, IMAGE
, and LATENT
values.
Adds a menu item for following/jumping to the executing node and a menu to quickly go to a node of a specific type.
Adds a node that lets you save and use text presets, such as for your 'normal' negatives.
Preset Text (https://user-images.githubusercontent.com/125205205/230173939-08459efc-785b-46da-93d1-b02f0300c6f4.png)
Adds various menu items to some nodes for quickly setting up common parts of graphs.
Quick Nodes (https://user-images.githubusercontent.com/125205205/230174266-5232831a-a03b-4bf7-bc8b-c45466a0bc64.png)
Plays a sound when the node is executed, either after each prompt or only when the queue is empty for queuing multiple prompts. You can customize the sound by replacing the mp3 file.
Sends a system notification via the browser when the node is executed, either after each prompt or only when the queue is empty for queuing multiple prompts.
Allows you to either create a list of N repeats of the input node or create N outputs from the input node. You can optionally decide if you want to reuse the input node or create a new instance each time.
Takes input from a node that produces a string and displays it, useful for things like interrogator, prompt generators, etc.
Show Text (https://user-images.githubusercontent.com/125205205/230174888-c004fd48-da78-4de9-81c2-93a866fcfcd1.png)
Shows the current generating image on the menu at the bottom. You can disable this via the settings menu.
Supports appending and replacing text. tidy_tags
will add commas between parts when in append
mode. replace
mode supports regex replace by using /your regex here/
and you can reference capturing groups using \number
.
Provides basic support for touch screen devices, making it easier to use ComfyUI on tablets and other touch-enabled devices.
Allows you to specify default values for widgets when adding new nodes. The values are configured via the settings menu.
Adds options to the menu for saving and loading workflows, making it easier to manage and reuse your project setups.
Adds menu options for importing/exporting the graph as SVG and PNG, showing a view of the nodes.
Allows you to control the rendering of the links between nodes, choosing between straight, linear, and spline.
sdxl.safetensors
should have a preview image named sdxl.png
.How do I update ComfyUI-Custom-Scripts?
Navigate to the cloned repository in your custom_nodes
directory and run git pull
to fetch the latest updates.
Can I customize the sound for the Play Sound node?
Yes, you can replace the notify.mp3
file in the web/extensions/pysssss/CustomScripts/assets
directory with your own sound file.
How do I save a generated image as a preview for a model? Right-click on the generated image in the node and select "Save as Preview," then choose the model to save the preview for.
For more information, tutorials, and community support, you can visit the following resources:
© Copyright 2024 RunComfy. All Rights Reserved.