Stable Diffusion V2 1 GGUF

🚀 Stable-diffusion-GGUF

This project provides Stable Diffusion models quantized to q8_0, q5_0, q5_1, and q4_1, enabling text-to-image generation.

🚀 Quick Start

There are some files quantitated to q8_0, q5_0, q5_1, q4_1. To run these models, follow the steps below:

Step 1: Download the Code

You can go to this page to download the code or run the following command:

git clone --recursive https://github.com/leejet/stable-diffusion.cpp.git

Step 2: Compile the Code

Compile the code according to the instructions on the GitHub page.

Step 3: Run the Model

Finally, run the following command:

./sd -m '/model/stable_diffusion-ema-pruned-v2-1_768.q8_0.gguf'  -p "a lovely cat" -s -1

Then you can see the 'output.png'.

📦 Installation

Prerequisites

• Git
• Compilation tools (e.g., GCC)

Steps

1. Clone the repository:

git clone --recursive https://github.com/leejet/stable-diffusion.cpp.git

2. Compile the code as per the instructions on the GitHub page.

💻 Usage Examples

Basic Usage

./sd -m '/model/stable_diffusion-ema-pruned-v2-1_768.q8_0.gguf'  -p "a lovely cat" -s -1

This command generates an image of a lovely cat using the specified model.

📚 Documentation

Model Tags

• pipeline_tag: text-to-image
• tags: art, stable-diffusion