stable diffusion 3.5 large gguf

Introduction

The Stable Diffusion 3.5 Large GGUF model is a quantized text-to-image model available on Hugging Face, developed by city96. It is a direct GGUF conversion of the StabilityAI's Stable Diffusion 3.5 Large model. The model is designed for generating images from textual descriptions and retains the original license and restrictions of the base model.

Architecture

• Base Model: StabilityAI's Stable Diffusion 3.5 Large
• Library Used: GGUF
• Quantization: Performed by city96
• Tags: text-to-image, image-generation, stable-diffusion
• Language: English

Training

The model is not a fine-tuned version but a quantized form of the original StabilityAI model. As such, it maintains the same functionality and constraints as the base model.

Guide: Running Locally

To run the Stable Diffusion 3.5 Large GGUF model locally:

1. Installation:

   • Clone the ComfyUI-GGUF repository from GitHub: https://github.com/city96/ComfyUI-GGUF.
   • Follow the installation instructions provided in the repository's README.

2. Model Setup:

   • Download the model files and place them in the ComfyUI/models/unet directory.

3. Execution:

   • Use the ComfyUI-GGUF custom node to execute the model.

For enhanced performance, consider using a cloud service with GPU support such as AWS, Google Cloud, or Azure.

License

The model is distributed under the StabilityAI AI Community license. The original license terms and restrictions of the StabilityAI Stable Diffusion 3.5 Large model apply to this GGUF conversion. For detailed license information, refer to the LICENSE.md file included with the model files.