README.md

---
title: Architecture AI Enhancer
emoji: 🏗️
colorFrom: blue
colorTo: purple
sdk: gradio
sdk_version: 4.20.0
app_file: app.py
pinned: false
license: mit
python_version: "3.10"
---

# Architecture AI Enhancer

Transform your architectural renders with AI-powered enhancement using Stable Diffusion 1.5.

## Features

- 🎨 AI image enhancement with Stable Diffusion
- 📈 2x upscaling with ESRGAN
- 🎭 Photographic post-processing
- ⚙️ Configurable parameters
- 🚀 GPU-accelerated inference
- 🎓 **Custom LoRA training** (local only)

## Usage

1. Upload an architectural render
2. Add custom prompt details (optional)
3. Adjust enhancement settings (optional)
4. Click "Enhance Image"
5. Wait for processing (2-5 minutes on CPU, ~30 seconds on GPU)
6. Download your enhanced result

## 🎓 Custom LoRA Training

Want to train the AI on your specific architectural style? Check out the complete training guide:

**📖 [LoRA Training Guide](./TRAINING_GUIDE.md)**

Learn how to:
- Prepare training image pairs
- Train custom LoRA models locally
- Fine-tune for your specific rendering style
- Deploy your custom model

**Note**: Training requires running the backend locally due to computational requirements.

## Technical Details

- **Model**: runwayml/stable-diffusion-v1-5
- **Framework**: PyTorch + Diffusers
- **Interface**: Gradio 4.44.0
- **Version**: 1.0.0

## Settings Guide

- **Strength** (0.1-0.8): Controls how much the AI modifies the image
  - 0.2-0.3: Subtle enhancements
  - 0.4-0.5: Moderate changes
  - 0.6-0.8: Dramatic transformations

- **Guidance Scale** (1-15): How closely the AI follows the prompt
  - 4-6: Natural, balanced results
  - 7-10: More stylized
  - 11-15: Very strong prompt adherence

## Credits

Built with:
- [Stable Diffusion](https://github.com/CompVis/stable-diffusion)
- [Diffusers](https://github.com/huggingface/diffusers)
- [Gradio](https://gradio.app)
- [PyTorch](https://pytorch.org)