Instructions to use MaxedOut/ComfyUI-Starter-Packs with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use MaxedOut/ComfyUI-Starter-Packs with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="MaxedOut/ComfyUI-Starter-Packs",
	filename="Flux1/clip/GGUF/t5xxl_Q5_K_M.gguf",
)

output = llm(
	"Once upon a time,",
	max_tokens=512,
	echo=True
)
print(output)

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use MaxedOut/ComfyUI-Starter-Packs with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf MaxedOut/ComfyUI-Starter-Packs:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf MaxedOut/ComfyUI-Starter-Packs:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf MaxedOut/ComfyUI-Starter-Packs:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf MaxedOut/ComfyUI-Starter-Packs:Q4_K_M

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 MaxedOut/ComfyUI-Starter-Packs:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf MaxedOut/ComfyUI-Starter-Packs:Q4_K_M

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 MaxedOut/ComfyUI-Starter-Packs:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf MaxedOut/ComfyUI-Starter-Packs:Q4_K_M

Use Docker

docker model run hf.co/MaxedOut/ComfyUI-Starter-Packs:Q4_K_M

LM Studio
Jan
Ollama
How to use MaxedOut/ComfyUI-Starter-Packs with Ollama:
```
ollama run hf.co/MaxedOut/ComfyUI-Starter-Packs:Q4_K_M
```

Unsloth Studio

How to use MaxedOut/ComfyUI-Starter-Packs 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 MaxedOut/ComfyUI-Starter-Packs 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 MaxedOut/ComfyUI-Starter-Packs to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for MaxedOut/ComfyUI-Starter-Packs to start chatting

Docker Model Runner
How to use MaxedOut/ComfyUI-Starter-Packs with Docker Model Runner:
```
docker model run hf.co/MaxedOut/ComfyUI-Starter-Packs:Q4_K_M
```

Lemonade

How to use MaxedOut/ComfyUI-Starter-Packs with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull MaxedOut/ComfyUI-Starter-Packs:Q4_K_M

Run and chat with the model

lemonade run user.ComfyUI-Starter-Packs-Q4_K_M

List all available models

lemonade list

MaxedOut commited on Jun 22, 2025

Commit

0c6ed64

verified ·

1 Parent(s): 7bc718e

Update README.md

Browse files

Files changed (1) hide show

README.md +19 -16

README.md CHANGED Viewed

@@ -131,18 +131,19 @@ If this helped you out, leave a heart or start a discussion on what should be ad
 │   ├── RealESRGAN_x2plus.pth
 </details>
-### `Flux/`
-- UNETs: Dev, Schnell, Depth, Canny, Fill
-- GGUFs: Q3/Q5/Q6 + FP8
-- CLIP + T5XXL encoders
-### `SDXL/`
-- Checkpoints: Inpainting models, Hyper3d (Merged created by Maxed Out) and Sdxl Real Dream 6
-- ControlNets: Depth, Canny, OpenPose, etc.
-### `Extra/`
-- Adetailer
-- Upscalers
 ---
@@ -157,7 +158,7 @@ If this helped you out, leave a heart or start a discussion on what should be ad
 ## 👇 Showcase
-🧠 Depth:
 Flux Depth uses the depth map of an image, letting you prompt for what to fill it with. It's great for keeping the spatial layout while restyling the image however you want.
@@ -168,7 +169,7 @@ Flux Depth uses the depth map of an image, letting you prompt for what to fill i
 ![image/png](https://cdn-uploads.huggingface.co/production/uploads/67074acfd4d3da176ab29e70/yFNCYv-08wut1K87fFv8V.png)
-✏️ Canny:
 Flux Canny uses an edge map and also lets you prompt freely. It’s especially good for repurposing parts of an image like the planet in the first example.
@@ -178,7 +179,7 @@ Flux Canny uses an edge map and also lets you prompt freely. It’s especially g
 ![image/png](https://cdn-uploads.huggingface.co/production/uploads/67074acfd4d3da176ab29e70/0Fk1SQYdIyGlC0E-2HO1Z.png)
-🕺 OpenPose:
 Self-explanatory. It’s great when you don’t want Depth or Canny getting distracted by other elements in the original image.
@@ -189,7 +190,7 @@ Self-explanatory. It’s great when you don’t want Depth or Canny getting dist
 ![image/png](https://cdn-uploads.huggingface.co/production/uploads/67074acfd4d3da176ab29e70/aXSkpKai4SEgO9C3nJm1A.png)
-🫠 Pulid Face Transfer
 Pulid lets you use a face as a reference and prompt as usual. The result will keep a rough match of the reference face. It’s pretty solid without needing any training, though not perfect. As you can see, it struggled with Aloy’s hair.
@@ -199,7 +200,9 @@ Pulid lets you use a face as a reference and prompt as usual. The result will ke
 ![image/png](https://cdn-uploads.huggingface.co/production/uploads/67074acfd4d3da176ab29e70/t-UYkGTPrFNqPSC1N_fdJ.png)
-🔄 Redux
 ![image/png](https://cdn-uploads.huggingface.co/production/uploads/67074acfd4d3da176ab29e70/garxHfPDqbarwGcIebVAo.png)
@@ -207,5 +210,5 @@ Pulid lets you use a face as a reference and prompt as usual. The result will ke
 ![image/png](https://cdn-uploads.huggingface.co/production/uploads/67074acfd4d3da176ab29e70/UAVUwZ7oBppSwxVF-hq_c.png)
-Use the style of one image to influence another.

 │   ├── RealESRGAN_x2plus.pth
 </details>
+## New to ComfyUI or just want clean workflows?
+Flux:
+![image/png](https://cdn-uploads.huggingface.co/production/uploads/67074acfd4d3da176ab29e70/kBL3fpOjto0bIlG28R1AQ.png)
+[Available on the Maxed Out Patreon (free, no paywall)](https://www.patreon.com/posts/flux-level-1-and-131945103?utm_medium=clipboard_copy&utm_source=copyLink&utm_campaign=postshare_creator&utm_content=join_link)
+SDXL:
+![image/png](https://cdn-uploads.huggingface.co/production/uploads/67074acfd4d3da176ab29e70/PEbBMjf8ynE3WBejqUGZE.png)
+[Available on the Maxed Out Patreon (free, no paywall)](https://www.patreon.com/posts/sdxl-v1-5-just-129782694?utm_medium=clipboard_copy&utm_source=copyLink&utm_campaign=postshare_creator&utm_content=join_link)
 ---
 ## 👇 Showcase
+## 🧠 Depth:
 Flux Depth uses the depth map of an image, letting you prompt for what to fill it with. It's great for keeping the spatial layout while restyling the image however you want.
 ![image/png](https://cdn-uploads.huggingface.co/production/uploads/67074acfd4d3da176ab29e70/yFNCYv-08wut1K87fFv8V.png)
+## ✏️ Canny:
 Flux Canny uses an edge map and also lets you prompt freely. It’s especially good for repurposing parts of an image like the planet in the first example.
 ![image/png](https://cdn-uploads.huggingface.co/production/uploads/67074acfd4d3da176ab29e70/0Fk1SQYdIyGlC0E-2HO1Z.png)
+##🕺 OpenPose:
 Self-explanatory. It’s great when you don’t want Depth or Canny getting distracted by other elements in the original image.
 ![image/png](https://cdn-uploads.huggingface.co/production/uploads/67074acfd4d3da176ab29e70/aXSkpKai4SEgO9C3nJm1A.png)
+## 🫠 Pulid Face Transfer
 Pulid lets you use a face as a reference and prompt as usual. The result will keep a rough match of the reference face. It’s pretty solid without needing any training, though not perfect. As you can see, it struggled with Aloy’s hair.
 ![image/png](https://cdn-uploads.huggingface.co/production/uploads/67074acfd4d3da176ab29e70/t-UYkGTPrFNqPSC1N_fdJ.png)
+## 🔄 Redux
+Use the style of one image to influence another.
 ![image/png](https://cdn-uploads.huggingface.co/production/uploads/67074acfd4d3da176ab29e70/garxHfPDqbarwGcIebVAo.png)
 ![image/png](https://cdn-uploads.huggingface.co/production/uploads/67074acfd4d3da176ab29e70/UAVUwZ7oBppSwxVF-hq_c.png)