Instructions to use saik0s/comfy_backup with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- llama-cpp-python
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
- Pi
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
| // ComfyUI.mxToolkit.Slider v.0.9.92 - Max Smirnov 2025 | |
| import { app } from "../../scripts/app.js"; | |
| class MXSlider | |
| { | |
| constructor(node) | |
| { | |
| this.node = node; | |
| this.node.properties = this.node.properties || {}; | |
| this.node.properties.value=20; | |
| this.node.properties.min=0; | |
| this.node.properties.max=100; | |
| this.node.properties.step=1; | |
| this.node.properties.decimals=0; | |
| this.node.properties.snap=true; | |
| this.node.intpos = { x:0.2 }; | |
| this.node.size = [210, Math.floor(LiteGraph.NODE_SLOT_HEIGHT*1.5)]; | |
| const fontsize = LiteGraph.NODE_SUBTEXT_SIZE; | |
| const shX = (this.node.slot_start_y || 0)+fontsize*1.5; | |
| const shY = LiteGraph.NODE_SLOT_HEIGHT/1.5; | |
| const shiftLeft = 10; | |
| const shiftRight = 60; | |
| for (let i=0; i<3; i++) { this.node.widgets[i].hidden = true; this.node.widgets[i].type = "hidden"; } | |
| this.node.onAdded = function () | |
| { | |
| this.outputs[0].name = this.outputs[0].localized_name = ""; | |
| this.widgets_start_y = -2.4e8*LiteGraph.NODE_SLOT_HEIGHT; | |
| this.intpos.x = Math.max(0, Math.min(1, (this.properties.value-this.properties.min)/(this.properties.max-this.properties.min))); | |
| if (this.size) if (this.size.length) if (this.size[1] > LiteGraph.NODE_SLOT_HEIGHT*1.5) this.size[1] = LiteGraph.NODE_SLOT_HEIGHT*1.5; | |
| this.outputs[0].type = (this.properties.decimals > 0)?"FLOAT":"INT"; | |
| }; | |
| this.node.onConfigure = function () | |
| { | |
| this.outputs[0].type = (this.properties.decimals > 0)?"FLOAT":"INT"; | |
| } | |
| this.node.onGraphConfigured = function () | |
| { | |
| this.configured = true; | |
| this.onPropertyChanged(); | |
| } | |
| this.node.onPropertyChanged = function (propName) | |
| { | |
| if (!this.configured) return; | |
| if (this.properties.step <= 0) this.properties.step = 1; | |
| if ( isNaN(this.properties.value) ) this.properties.value = this.properties.min; | |
| if ( this.properties.min >= this.properties.max ) this.properties.max = this.properties.min+this.properties.step; | |
| if ((propName === "min") && (this.properties.value < this.properties.min)) this.properties.value = this.properties.min; | |
| if ((propName === "max") && (this.properties.value > this.properties.max)) this.properties.value = this.properties.max; | |
| this.properties.decimals = Math.floor(this.properties.decimals); | |
| if (this.properties.decimals>4) this.properties.decimals = 4; | |
| if (this.properties.decimals<0) this.properties.decimals = 0; | |
| this.properties.value = Math.round(Math.pow(10,this.properties.decimals)*this.properties.value)/Math.pow(10,this.properties.decimals); | |
| this.intpos.x = Math.max(0, Math.min(1, (this.properties.value-this.properties.min)/(this.properties.max-this.properties.min))); | |
| if ((this.properties.decimals > 0 && this.outputs[0].type !== "FLOAT") || (this.properties.decimals === 0 && this.outputs[0].type !== "INT")) | |
| if (this.outputs[0].links !== null) | |
| for (let i = this.outputs[0].links.length; i > 0; i--) | |
| { | |
| const tlinkId = this.outputs[0].links[i-1]; | |
| const tlink = app.graph.links[tlinkId]; | |
| app.graph.getNodeById(tlink.target_id).disconnectInput(tlink.target_slot); | |
| } | |
| this.outputs[0].type = (this.properties.decimals > 0)?"FLOAT":"INT"; | |
| this.widgets[2].value = (this.properties.decimals > 0)?1:0; | |
| this.widgets[1].value = this.properties.value; | |
| this.widgets[0].value = Math.floor(this.properties.value); | |
| } | |
| this.node.onDrawForeground = function(ctx) | |
| { | |
| this.configured = true; | |
| if ( this.flags.collapsed ) return false; | |
| if (this.size[1] > LiteGraph.NODE_SLOT_HEIGHT*1.5) this.size[1] = LiteGraph.NODE_SLOT_HEIGHT*1.5; | |
| let dgt = parseInt(this.properties.decimals); | |
| ctx.fillStyle="rgba(20,20,20,0.5)"; | |
| ctx.beginPath(); | |
| ctx.roundRect( shiftLeft, shY-1, this.size[0]-shiftRight-shiftLeft, 4, 2); | |
| ctx.fill(); | |
| ctx.fillStyle=LiteGraph.NODE_TEXT_COLOR; | |
| ctx.beginPath(); | |
| ctx.arc(shiftLeft+(this.size[0]-shiftRight-shiftLeft)*this.intpos.x, shY+1, 7, 0, 2 * Math.PI, false); | |
| ctx.fill(); | |
| ctx.lineWidth = 1.5; | |
| ctx.strokeStyle=node.bgcolor || LiteGraph.NODE_DEFAULT_BGCOLOR; | |
| ctx.beginPath(); | |
| ctx.arc(shiftLeft+(this.size[0]-shiftRight-shiftLeft)*this.intpos.x, shY+1, 5, 0, 2 * Math.PI, false); | |
| ctx.stroke(); | |
| ctx.fillStyle=LiteGraph.NODE_TEXT_COLOR; | |
| ctx.font = (fontsize) + "px Arial"; | |
| ctx.textAlign = "center"; | |
| ctx.fillText(this.properties.value.toFixed(dgt), this.size[0]-shiftRight+24, shX); | |
| } | |
| this.node.onDblClick = function(e, pos, canvas) | |
| { | |
| if ( e.canvasX > this.pos[0]+this.size[0]-shiftRight+10 ) | |
| { | |
| canvas.prompt("value", this.properties.value, function(v) {if (!isNaN(Number(v))) { this.properties.value = Number(v); this.onPropertyChanged("value");}}.bind(this), e); | |
| return true; | |
| } | |
| } | |
| this.node.onMouseDown = function(e) | |
| { | |
| if ( e.canvasY - this.pos[1] < 0 ) return false; | |
| if ( e.canvasX < this.pos[0]+shiftLeft-5 || e.canvasX > this.pos[0]+this.size[0]-shiftRight+5 ) return false; | |
| if ( e.canvasY < this.pos[1]+shiftLeft-5 || e.canvasY > this.pos[1]+this.size[1]-shiftLeft+5 ) return false; | |
| this.capture = true; | |
| this.unlock = false; | |
| this.captureInput(true); | |
| this.valueUpdate(e); | |
| return true; | |
| } | |
| this.node.onMouseMove = function(e, pos, canvas) | |
| { | |
| if (!this.capture) return; | |
| if ( canvas.pointer.isDown === false ) { this.onMouseUp(e); return; } | |
| this.valueUpdate(e); | |
| } | |
| this.node.onMouseUp = function(e) | |
| { | |
| if (!this.capture) return; | |
| this.capture = false; | |
| this.captureInput(false); | |
| this.widgets[0].value = Math.floor(this.properties.value); | |
| this.widgets[1].value = this.properties.value; | |
| } | |
| this.node.valueUpdate = function(e) | |
| { | |
| let prevX = this.properties.value; | |
| let rn = Math.pow(10,this.properties.decimals); | |
| let vX = (e.canvasX - this.pos[0] - shiftLeft)/(this.size[0]-shiftRight-shiftLeft); | |
| if (e.ctrlKey) this.unlock = true; | |
| if (e.shiftKey !== this.properties.snap) | |
| { | |
| let step = this.properties.step/(this.properties.max - this.properties.min); | |
| vX = Math.round(vX/step)*step; | |
| } | |
| this.intpos.x = Math.max(0, Math.min(1, vX)); | |
| this.properties.value = Math.round(rn*(this.properties.min + (this.properties.max - this.properties.min) * ((this.unlock)?vX:this.intpos.x)))/rn; | |
| this.updateThisNodeGraph?.(); | |
| if ( this.properties.value !== prevX ) this.graph.setisChangedFlag(this.id); | |
| } | |
| this.node.onSelected = function(e) { this.onMouseUp(e) } | |
| this.node.computeSize = () => [LiteGraph.NODE_WIDTH,Math.floor(LiteGraph.NODE_SLOT_HEIGHT*1.5)]; | |
| } | |
| } | |
| app.registerExtension( | |
| { | |
| name: "mxSlider", | |
| async beforeRegisterNodeDef(nodeType, nodeData, _app) | |
| { | |
| if (nodeData.name === "mxSlider") | |
| { | |
| const onNodeCreated = nodeType.prototype.onNodeCreated; | |
| nodeType.prototype.onNodeCreated = function () { | |
| if (onNodeCreated) onNodeCreated.apply(this, []); | |
| this.mxSlider = new MXSlider(this); | |
| } | |
| } | |
| } | |
| }); | |