Instructions to use ND911/SD35_Blur_Canny_Depth with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use ND911/SD35_Blur_Canny_Depth with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="ND911/SD35_Blur_Canny_Depth",
	filename="SD3.5 Clips/converted-flan-t5-xxl-Q8_0.gguf",
)

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

Notebooks
Google Colab
Kaggle
Local Apps

llama.cpp

How to use ND911/SD35_Blur_Canny_Depth with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf ND911/SD35_Blur_Canny_Depth:Q8_0
# Run inference directly in the terminal:
llama-cli -hf ND911/SD35_Blur_Canny_Depth:Q8_0

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf ND911/SD35_Blur_Canny_Depth:Q8_0
# Run inference directly in the terminal:
llama-cli -hf ND911/SD35_Blur_Canny_Depth:Q8_0

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 ND911/SD35_Blur_Canny_Depth:Q8_0
# Run inference directly in the terminal:
./llama-cli -hf ND911/SD35_Blur_Canny_Depth:Q8_0

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 ND911/SD35_Blur_Canny_Depth:Q8_0
# Run inference directly in the terminal:
./build/bin/llama-cli -hf ND911/SD35_Blur_Canny_Depth:Q8_0

Use Docker

docker model run hf.co/ND911/SD35_Blur_Canny_Depth:Q8_0

LM Studio
Jan
Ollama
How to use ND911/SD35_Blur_Canny_Depth with Ollama:
```
ollama run hf.co/ND911/SD35_Blur_Canny_Depth:Q8_0
```

Unsloth Studio new

How to use ND911/SD35_Blur_Canny_Depth 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 ND911/SD35_Blur_Canny_Depth 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 ND911/SD35_Blur_Canny_Depth to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for ND911/SD35_Blur_Canny_Depth to start chatting

Docker Model Runner
How to use ND911/SD35_Blur_Canny_Depth with Docker Model Runner:
```
docker model run hf.co/ND911/SD35_Blur_Canny_Depth:Q8_0
```

Lemonade

How to use ND911/SD35_Blur_Canny_Depth with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull ND911/SD35_Blur_Canny_Depth:Q8_0

Run and chat with the model

lemonade run user.SD35_Blur_Canny_Depth-Q8_0

List all available models

lemonade list

GGUF Workflow

The workflow combines all controlnet models into one and controlled by switches. Also include Ksampler and Custom Sampler with Demon Details, simply use the switch to choose your sampler. The SD 3.5 model I used in the workflow is the SD 3.5 SLG_Weighted Merge

Example Images of SD 3.5 SLG_Weighted Merge on Civitai

SD3.5-SLG-Weighted-Merge-Q8_0.gguf

Clip models for GGUF uploaded and go into the ComfyUI\models\clip

Other Clip models uploaded that are used in the workflow also

Controlnet models go into the ComfyUI\models\controlnet