Instructions to use saik0s/comfy_backup with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use saik0s/comfy_backup with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="saik0s/comfy_backup",
	filename="ComfyUI/models/text_encoders/gemma-3-12b-it-q2_k.gguf",
)

llm.create_chat_completion(
	messages = "No input example has been defined for this model task."
)

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use saik0s/comfy_backup with llama.cpp:

Install (macOS, Linux)

curl -LsSf https://llama.app/install.sh | sh
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf saik0s/comfy_backup:Q4_K_S
# Run inference directly in the terminal:
llama cli -hf saik0s/comfy_backup:Q4_K_S

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf saik0s/comfy_backup:Q4_K_S
# Run inference directly in the terminal:
llama cli -hf saik0s/comfy_backup:Q4_K_S

Use pre-built binary

# Download pre-built binary from:
# https://github.com/ggerganov/llama.cpp/releases
# Start a local OpenAI-compatible server with a web UI:
./llama-server -hf saik0s/comfy_backup:Q4_K_S
# Run inference directly in the terminal:
./llama-cli -hf saik0s/comfy_backup:Q4_K_S

Build from source code

git clone https://github.com/ggerganov/llama.cpp.git
cd llama.cpp
cmake -B build
cmake --build build -j --target llama-server llama-cli
# Start a local OpenAI-compatible server with a web UI:
./build/bin/llama-server -hf saik0s/comfy_backup:Q4_K_S
# Run inference directly in the terminal:
./build/bin/llama-cli -hf saik0s/comfy_backup:Q4_K_S

Use Docker

docker model run hf.co/saik0s/comfy_backup:Q4_K_S

LM Studio
Jan
Ollama
How to use saik0s/comfy_backup with Ollama:
```
ollama run hf.co/saik0s/comfy_backup:Q4_K_S
```

Unsloth Studio

How to use saik0s/comfy_backup with Unsloth Studio:

Install Unsloth Studio (macOS, Linux, WSL)

curl -fsSL https://unsloth.ai/install.sh | sh
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for saik0s/comfy_backup to start chatting

Install Unsloth Studio (Windows)

irm https://unsloth.ai/install.ps1 | iex
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for saik0s/comfy_backup to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for saik0s/comfy_backup to start chatting

How to use saik0s/comfy_backup with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf saik0s/comfy_backup:Q4_K_S

Configure the model in Pi

# Install Pi:
npm install -g @mariozechner/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "llama-cpp": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "saik0s/comfy_backup:Q4_K_S"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use saik0s/comfy_backup with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf saik0s/comfy_backup:Q4_K_S

Configure Hermes

# Install Hermes:
curl -fsSL https://hermes-agent.nousresearch.com/install.sh | bash
hermes setup
# Point Hermes at the local server:
hermes config set model.provider custom
hermes config set model.base_url http://127.0.0.1:8080/v1
hermes config set model.default saik0s/comfy_backup:Q4_K_S

Run Hermes

hermes

Atomic Chat new

OpenClaw new

How to use saik0s/comfy_backup with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf saik0s/comfy_backup:Q4_K_S

Configure OpenClaw

# Install OpenClaw:
npm install -g openclaw@latest
# Register the local server and set it as the default model:
openclaw onboard --non-interactive --mode local \
  --auth-choice custom-api-key \
  --custom-base-url http://127.0.0.1:8080/v1 \
  --custom-model-id "saik0s/comfy_backup:Q4_K_S" \
  --custom-provider-id llama-cpp \
  --custom-compatibility openai \
  --custom-text-input \
  --accept-risk \
  --skip-health

Run OpenClaw

openclaw agent --local --agent main --message "Hello from Hugging Face"

Docker Model Runner
How to use saik0s/comfy_backup with Docker Model Runner:
```
docker model run hf.co/saik0s/comfy_backup:Q4_K_S
```

Lemonade

How to use saik0s/comfy_backup with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull saik0s/comfy_backup:Q4_K_S

Run and chat with the model

lemonade run user.comfy_backup-Q4_K_S

List all available models

lemonade list

comfy_backup / custom_nodes /comfyui-custom-scripts /README.md

saik0s

Add files using upload-large-folder tool

8d5e143 verified 22 days ago

preview code

Raw

History Blame Contribute Delete

10.4 kB

ComfyUI-Custom-Scripts

⚠️ While these extensions work for the most part, i'm very busy at the moment and so unable to keep on top of everything here, thanks for your patience!

Installation

Clone the repository: git clone https://github.com/pythongosssss/ComfyUI-Custom-Scripts.git
to your ComfyUI custom_nodes directory

The script will then automatically install all custom scripts and nodes.
It will attempt to use symlinks and junctions to prevent having to copy files and keep them up to date.

For uninstallation:
- Delete the cloned repo in custom_nodes
- Ensure web/extensions/pysssss/CustomScripts has also been removed

Update

Navigate to the cloned repo e.g. custom_nodes/ComfyUI-Custom-Scripts
git pull

Features

Autocomplete

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.

Auto Arrange Graph

Adds a menu option to auto arrange the graph in order of execution, this makes very wide graphs!

Always Snap to Grid

Adds a setting to make moving nodes always snap to grid.

[Testing] "Better" Loader Lists

Adds custom Lora and Checkpoint loader nodes, these have the ability to show preview images, just place a png or jpg next to the file and it'll display in the list on hover (e.g. sdxl.safetensors and sdxl.png).
Optionally enable subfolders via the settings:

Adds an "examples" widget to load sample prompts, triggerwords, etc:

These should be stored in a folder matching the name of the model, e.g. if it is loras/add_detail.safetensors put your files in as loras/add_detail/*.txt
To quickly save a generated image as the preview to use for the model, you can right click on an image on a node, and select Save as Preview and choose the model to save the preview for:

Checkpoint/LoRA/Embedding Info

Adds "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.

Constrain Image

Adds a node for resizing an image to a max & min size optionally cropping if required.

Custom Colors

Adds a custom color picker to nodes & groups

Favicon Status

Adds a favicon and title to the window, favicon changes color while generating and the window title includes the number of prompts in the queue

Image Feed

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 and the size of the panel and the images via the sliders at the top of the panel.

KSampler (Advanced) denoise helper

Provides a simple method to set custom denoise on the advanced sampler

Math Expression

Allows for evaluating complex expressions using values from the graph. You can input INT, FLOAT, IMAGE and LATENT values.

Other nodes values can be referenced via the Node name for S&R via the Properties menu item on a node, or the node title.
Supported operators: + - * / (basic ops) // (floor division) ** (power) ^ (xor) % (mod)
Supported functions floor(num, dp?) floor(num) ceil(num) randomint(min,max)
If using a LATENT or IMAGE you can get the dimensions using a.width or a.height where a is the input name.

Node Finder

Adds a menu item for following/jumping to the executing node, and a menu to quickly go to a node of a specific type.

Preset Text

Adds a node that lets you save and use text presets (e.g. for your 'normal' negatives)

Quick Nodes

Adds various menu items to some nodes for quickly setting up common parts of graphs

Play Sound

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 ComfyUI/custom_nodes/ComfyUI-Custom-Scripts/web/js/assets/notify.mp3

System Notification

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.

[WIP] Repeater

Node 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 (e.g. a Checkpoint Loader would want to be re-used, but a random number would want to be unique) TODO: Type safety on the wildcard outputs to require match with input

Show Text

Takes input from a node that produces a string and displays it, useful for things like interrogator, prompt generators, etc.

Show Image on Menu

Shows the current generating image on the menu at the bottom, you can disable this via the settings menu.

String Function

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 e.g. \1

Touch Support

Provides basic support for touch screen devices, its not perfect but better than nothing

Widget Defaults

Allows you to specify default values for widgets when adding new nodes, the values are configured via the settings menu

Workflows

Adds options to the menu for saving + loading workflows:

Workflow Images

Adds menu options for importing/exporting the graph as SVG and PNG showing a view of the nodes

(Testing) Reroute Primitive

Provides a node that allows rerouting primitives.
The node can also be collapsed to a single point that you can drag around.

Warning: Don't use normal reroutes or primitives with these nodes, it isn't tested and this node replaces their functionality.

WD14 Tagger

Moved to: https://github.com/pythongosssss/ComfyUI-WD14-Tagger

Lock Nodes & Groups

This is now a standard feature of ComfyUI
~~Adds a lock option to nodes & groups that prevents you from moving them until unlocked~~