🎨 Stable Diffusion Image Generation

This repository contains scripts for text-to-image generation using:

• Stable Diffusion 3.5
• Stable Diffusion 2.1

Both models are implemented using the Diffusers library and optimized for GPU acceleration.

---

📌 Features

🖼️ Stable Diffusion 3.5

• Generates high-quality, detailed images
• Improved prompt adherence and composition
• Optimized for better performance on GPUs

🖌️ Stable Diffusion 2.1

• Generates images with enhanced realism
• Lower VRAM usage compared to SD 3.5
• Supports various customization options

---

🛠️ Installation

Ensure you have Python 3.8+ and a CUDA-enabled GPU. Install dependencies:

pip install torch diffusers accelerate safetensors

🚀 Usage

Both scripts allow you to generate images by providing a text prompt.

Run Stable Diffusion 3.5

python t2i_3_5.py

Run Stable Diffusion 2.1

python t2i_2_1.py

🖼️ Output

The generated images will be saved as:

• image_3.5_0.png, image_3.5_1.png (for SD 3.5)
• image_2.1_0.png, image_2.1_1.png (for SD 2.1)

---

Made with ❤️ by Sanfinity