Project Overview
This project enables Text-to-Image Generation using Stable Diffusion with ComfyUI and LoRA Checkpoints, integrated seamlessly with a Flask-based API. It allows users to generate high-quality AI-generated images based on text prompts.
✨ Features
🖼 Stable Diffusion for high-quality image synthesis
🎨 ComfyUI Integration for advanced workflow customization
🔗 LoRA Checkpoints support for fine-tuned models
🌐 Flask API for seamless web-based interaction
📸 Sample Image Previews for generated outputs
📷 Sample Images
Below are some AI-generated images using the project:
ComfyUI workflows integrated with Flask
🔧 Installation & Setup
1️⃣ Clone the Repository git clone https://github.com/yourusername/text-to-image-flask.git cd text-to-image-flask
2️⃣ Install Dependencies pip install -r requirements.txt
Ensure you have Python installed, then run:
pip install -r requirements.txt
3️⃣ Download Stable Diffusion Checkpoints & LoRAs
Place Stable Diffusion model files in models/Stable-diffusion/
Place LoRA Checkpoints in models/Lora/
4️⃣ Run the Flask Server
python app.py
The server will be available at http://127.0.0.1:5000/
📡 API Usage
Endpoint: Generate Image
URL: POST /generate
Request Example:
{ "prompt": "A futuristic city at night, cyberpunk style", "steps": 50, "guidance_scale": 7.5 }
Response Example:
{ "image_url": "/static/generated/image_12345.png" }
🛠 Technologies Used
Stable Diffusion - AI Image Generation Model
ComfyUI - Visual workflow for Stable Diffusion
LoRA - Lightweight model finetuning
Flask - Python web framework
Python - Backend scripting
🎯 Future Enhancements
🔹 Implement Web UI for real-time image generation
🔹 Support for different AI models (SDXL, SD 2.1, etc.)
🔹 Cloud deployment for wider accessibility