stable diffusion 3.5 large turbo gguf

Introduction

The "Stable-Diffusion-3.5-Large-Turbo-GGUF" is a model designed for text-to-image generation. It is a GGUF-converted version of the Stability AI's Stable Diffusion 3.5 Large Turbo model, quantized by city96. This model is suitable for generating images from text prompts, leveraging the capabilities of the Stable Diffusion framework.

Architecture

• Base Model: StabilityAI's Stable Diffusion 3.5 Large Turbo
• Library: GGUF
• Quantized by: city96
• Tags:
  • Text-to-image
  • Image-generation
  • Stable-diffusion
• Language: English

Training

This model is not a fine-tuned version but a quantized one, meaning it maintains the original architecture and training data characteristics but optimized for efficiency in deployment.

Guide: Running Locally

1. Clone the Repository:
   • Obtain the model through the Hugging Face platform.
2. Install Dependencies:
   • Follow the installation instructions provided in the ComfyUI-GGUF GitHub repository.
3. Place Model Files:
   • Download the model files and place them in the ComfyUI/models/unet directory.
4. Run the Model:
   • Execute the model using ComfyUI. Refer to the GitHub readme for detailed instructions on setup and execution.

Cloud GPU Options: Consider using cloud services such as AWS, Google Cloud, or Azure for GPU acceleration to enhance performance when running models locally.

License

The model follows the StabilityAI AI Community license, which maintains the same restrictions and terms as the original model. For detailed license terms, refer to the LICENSE.md file included with the model files.