initial commit

.editorconfig

@@ -0,0 +1,12 @@
+root = true
+
+[*]
+indent_style = space
+indent_size = 4
+charset = utf-8
+end_of_line = lf
+insert_final_newline = true
+trim_trailing_whitespace = true
+
+[*.md]
+trim_trailing_whitespace = false

.pre-commit-config.yaml

@@ -0,0 +1,14 @@
+repos:
+  - repo: https://github.com/psf/black
+    rev: 24.4.2
+    hooks:
+      - id: black
+        language_version: python3
+        args: ["--line-length=100"]
+
+  - repo: https://github.com/astral-sh/ruff-pre-commit
+    rev: v0.5.0
+    hooks:
+      - id: ruff
+        args: ["--fix"]
+      - id: ruff-format

.ruff.toml

@@ -0,0 +1,24 @@
+# Ruff Configuration
+
+[lint]
+select = [
+    "E",   # pycodestyle errors
+    "F",   # pyflakes
+    "B",   # bugbear
+    "D",   # pydocstyle
+    "I",   # isort
+]
+ignore = [
+    # Ignore missing docstring for __init__.py only
+    "D104",
+    "B008",
+]
+
+[lint.pydocstyle]
+convention = "google"
+
+[format]
+quote-style = "double"
+indent-style = "space"
+skip-magic-trailing-comma = false
+line-ending = "lf"

README.md

@@ -1,2 +1,226 @@
-# stable-diffusion-image-generator
-AI-powered image generation system built using Stable Diffusion
+# 🎨 Stable Diffusion Image Generator
+
+AI system built using **Stable Diffusion (HuggingFace Diffusers)** and a modern **Gradio UI**.
+This project generates high-quality images from text prompts and includes advanced capabilities such as:
+
+* Style presets
+* Image-to-Image generation
+* Super-resolution upscaling (RealESRGAN)
+* Prompt history & metadata tracking
+* Seed reproducibility
+* LoRA extension support
+
+---
+
+# Feature Details
+
+## 1️⃣ **Text-to-Image Generation**
+
+* Supports prompts & negative prompts
+* Adjustable steps, CFG scale, resolution
+* Seed for reproducibility
+* Preset selection panel
+
+## 2️⃣ **Image-to-Image (Img2Img)**
+
+Transform uploaded images using prompts, e.g.:
+
+* “Make this photo look cyberpunk”
+* “Convert this portrait into anime style”
+* “Turn into oil painting style”
+
+## 3️⃣ **Super-Resolution Upscaling**
+
+Improve output quality significantly:
+
+* 1.5×
+* 2×
+* 4×
+  Powered by **RealESRGAN**.
+
+## 4️⃣ **Style Presets**
+
+One-click artistic styles:
+
+* Anime
+* Realistic photography
+* Pixar / 3D
+* Oil painting
+* Cyberpunk neon
+
+## 5️⃣ **Prompt History & Metadata Tracking**
+
+Every generation stores:
+
+* Prompt
+* Negative prompt
+* Configuration
+* Seed
+* Generated image
+
+## 6️⃣ **LoRA Support**
+
+Load and use custom LoRA fine-tuned models:
+
+* Styles
+* Artists
+* Characters
+* Themes
+
+---
+
+# 🧩 Project Architecture
+
+```
+stable-diffusion-image-generator/
+│
+├── app/
+│   ├── core/
+│   │   └── __init__.py
+│   │
+│   ├── pipeline.py
+│   │   # Loads & initializes Stable Diffusion (FP16, GPU, model configs)
+│   │
+│   ├── generator.py
+│   │   # Text-to-image inference logic
+│   │
+│   ├── img2img.py
+│   │   # Image-to-image transformation logic
+│   │
+│   ├── ui.py
+│   │   # Complete Gradio interface with multiple tabs:
+│   │   # Text2Img, Img2Img, Upscaling, History, About
+│   │
+│   ├── presets/
+│   │   ├── styles.py
+│   │       # Predefined artistic style presets (anime, cyberpunk, etc.)
+│   │
+│   ├── upscaler/
+│   │   ├── realesrgan.py
+│   │       # Super-resolution (1.5x, 2x, 4x)
+│   │
+│   ├── utils/
+│   │   ├── history.py     # Prompt history & metadata saving
+│   │   ├── seed.py        # Seed utilities for reproducibility
+│   │   ├── logger.py      # Central logging
+│   │
+│   ├── models/
+│   │   ├── metadata.py    # Data model for storing history entries
+│
+├── assets/
+│   ├── samples/           # Example generated images
+│   ├── lora/              # Custom LoRA models (optional)
+│
+├── main.py                # Entry point (launches Gradio app)
+├── requirements.txt       # All dependencies (pinned)
+├── LICENSE
+└── README.md
+```
+
+---
+
+# ⚙️ Installation & Setup
+
+### Step 1 — Clone the Repo
+
+```
+git clone https://github.com/sanskarmodi8/stable-diffusion-image-generator
+cd stable-diffusion-image-generator
+```
+
+### Step 2 — Create virtual environment
+
+```
+python -m venv venv
+source venv/bin/activate        # Linux/Mac
+venv\Scripts\activate           # Windows
+```
+
+### Step 3 — Install PyTorch (GPU)
+
+```
+pip install torch torchvision torchaudio --index-url https://download.pytorch.org/whl/cu121
+```
+
+### Step 4 — Install remaining dependencies
+
+```
+pip install -r requirements.txt
+```
+
+### Optional — Login to HuggingFace
+
+```
+huggingface-cli login
+```
+
+---
+
+# ▶️ Running the App
+
+```
+python main.py
+```
+
+App will run at:
+
+```
+http://127.0.0.1:7860
+```
+
+---
+
+# 🤝 Contributing
+
+This project follows **strict formatting and linting standards** to ensure clean, readable, and professional-quality code.
+
+
+#### 1. Install pre-commit hooks
+
+This ensures formatting and linting run **automatically** before every commit.
+
+```
+pre-commit install
+```
+
+#### 2. Format code manually (optional)
+
+```
+black .
+isort .
+ruff check .
+```
+
+#### 3. Create feature branches
+
+Follow standard naming:
+
+```
+feature/<feature-name>
+fix/<bug-name>
+refactor/<module>
+```
+
+#### 4. Commit messages
+
+Use clear, conventional messages:
+
+```
+feat: add anime preset
+fix: resolve img2img prompt issue
+refactor: improve pipeline loading speed
+docs: update readme
+```
+
+---
+
+# 📄 License
+
+Released under the [**MIT License**](LICENSE).
+
+---
+
+# ⭐ Author
+
+**[Sanskar Modi](https://github.com/sanskarmodi8)**
+AI Developer & Machine Learning Engineer

app/__init__.py

@@ -0,0 +1 @@
+"""Package initialization file for Stable Diffusion Image Generator."""

app/core/__init__.py

@@ -0,0 +1 @@
+"""Package initialization file for Stable Diffusion Image Generator."""

app/generator.py

@@ -0,0 +1 @@
+"""Auto-generated placeholder module for Stable Diffusion Image Generator."""

app/img2img.py

@@ -0,0 +1 @@
+"""Auto-generated placeholder module for Stable Diffusion Image Generator."""

app/models/__init__.py

@@ -0,0 +1 @@
+"""Package initialization file for Stable Diffusion Image Generator."""

app/models/metadata.py

@@ -0,0 +1 @@
+"""Auto-generated placeholder module for Stable Diffusion Image Generator."""

app/pipeline.py

@@ -0,0 +1 @@
+"""Auto-generated placeholder module for Stable Diffusion Image Generator."""

app/presets/__init__.py

@@ -0,0 +1 @@
+"""Package initialization file for Stable Diffusion Image Generator."""

app/presets/styles.py

@@ -0,0 +1 @@
+"""Auto-generated placeholder module for Stable Diffusion Image Generator."""

app/ui.py

@@ -0,0 +1 @@
+"""Auto-generated placeholder module for Stable Diffusion Image Generator."""

app/upscaler/__init__.py

@@ -0,0 +1 @@
+"""Package initialization file for Stable Diffusion Image Generator."""

app/upscaler/realesrgan.py

@@ -0,0 +1 @@
+"""Auto-generated placeholder module for Stable Diffusion Image Generator."""

app/utils/__init__.py

@@ -0,0 +1 @@
+"""Package initialization file for Stable Diffusion Image Generator."""

app/utils/history.py

@@ -0,0 +1 @@
+"""Auto-generated placeholder module for Stable Diffusion Image Generator."""

app/utils/logger.py

@@ -0,0 +1 @@
+"""Auto-generated placeholder module for Stable Diffusion Image Generator."""

app/utils/seed.py

@@ -0,0 +1 @@
+"""Auto-generated placeholder module for Stable Diffusion Image Generator."""

assets/__init__.py

@@ -0,0 +1 @@
+"""Package initialization file for Stable Diffusion Image Generator."""

assets/lora/__init__.py

@@ -0,0 +1 @@
+"""Package initialization file for Stable Diffusion Image Generator."""

init_structure.py

@@ -0,0 +1,94 @@
+"""
+Project Structure Generator for Stable Diffusion Image Generator.
+
+Creates all required directories and placeholder files with compliant
+docstrings. Safe for repeated runs — will not overwrite existing files.
+"""
+
+import os
+
+# Placeholder docstrings
+MODULE_PLACEHOLDER = '"""Auto-generated placeholder module for Stable Diffusion Image Generator."""\n'
+INIT_PLACEHOLDER = '"""Package initialization file for Stable Diffusion Image Generator."""\n'
+
+
+# Utility functions
+def create_dir(path: str):
+    """Create directory if it doesn't already exist."""
+    os.makedirs(path, exist_ok=True)
+
+
+def create_file(path: str, content: str = MODULE_PLACEHOLDER):
+    """Create a file only if it does not already exist."""
+    if not os.path.exists(path):
+        with open(path, "w") as f:
+            f.write(content)
+
+
+def init_file(path: str):
+    """Create an __init__.py with a placeholder docstring."""
+    if not os.path.exists(path):
+        with open(path, "w") as f:
+            f.write(INIT_PLACEHOLDER)
+
+
+# Project Directory Structure
+
+directories = [
+    "app",
+    "app/core",
+    "app/models",
+    "app/utils",
+    "app/presets",
+    "app/upscaler",
+    "assets",
+    "assets/samples",
+    "assets/lora",
+]
+
+
+# File Definitions
+
+files = {
+    # Entry
+    "main.py": MODULE_PLACEHOLDER,
+
+    # Core pipeline + generation modules
+    "app/pipeline.py": MODULE_PLACEHOLDER,
+    "app/generator.py": MODULE_PLACEHOLDER,
+    "app/img2img.py": MODULE_PLACEHOLDER,
+
+    # UI
+    "app/ui.py": MODULE_PLACEHOLDER,
+
+    # Presets
+    "app/presets/styles.py": MODULE_PLACEHOLDER,
+
+    # Upscaler
+    "app/upscaler/realesrgan.py": MODULE_PLACEHOLDER,
+
+    # Utils
+    "app/utils/history.py": MODULE_PLACEHOLDER,
+    "app/utils/seed.py": MODULE_PLACEHOLDER,
+    "app/utils/logger.py": MODULE_PLACEHOLDER,
+
+    # Models or reference files
+    "app/models/metadata.py": MODULE_PLACEHOLDER,
+
+    # Root files
+    "requirements.txt": MODULE_PLACEHOLDER,
+    "README.md": MODULE_PLACEHOLDER,
+    "LICENSE": MODULE_PLACEHOLDER,
+}
+
+
+# Build the structure
+
+for d in directories:
+    create_dir(d)
+    init_file(os.path.join(d, "__init__.py"))
+
+for path, content in files.items():
+    create_file(path, content)
+
+print("Stable Diffusion Image Generator project structure created successfully!")

main.py

@@ -0,0 +1 @@
+"""Auto-generated placeholder module for Stable Diffusion Image Generator."""

requirements.txt

@@ -0,0 +1,40 @@
+# CORE GPU LIBRARIES (PyTorch - GPU ONLY)
+# IMPORTANT: Install manually using:
+# pip install torch torchvision torchaudio --index-url https://download.pytorch.org/whl/cu121
+
+torch==2.5.1
+torchvision==0.20.1
+torchaudio==2.5.1
+
+
+# HUGGINGFACE DIFFUSION ECOSYSTEM
+diffusers==0.26.3
+transformers==4.39.3
+accelerate==0.28.0
+safetensors==0.4.2
+
+
+# UI FRAMEWORK
+gradio==4.29.0
+
+
+# IMAGE PROCESSING & UTILITIES
+opencv-python==4.9.0.80
+Pillow==10.2.0
+numpy==1.26.4
+loguru==0.7.2
+tqdm==4.66.2
+python-dotenv==1.0.1
+
+
+# UPSCALING / SUPER-RESOLUTION
+realesrgan==0.3.0
+basicsr==1.4.2
+facexlib==0.3.0
+gfpgan==1.3.8
+
+
+# DEV TOOLS
+black==24.3.0
+ruff==0.3.5
+pre-commit==3.7.0