Add web interface for VideoGen

Features:
- Modern web UI with all generation modes (T2V, I2V, T2I, I2I, V2V, Dub, Subtitles, Upscale)
- Real-time progress updates via WebSocket
- File upload for input images/videos/audio
- File download for generated content
- Background job processing with progress tracking
- Job management (cancel, retry, delete)
- Gallery for browsing generated files
- REST API for programmatic access
- Responsive design for desktop and mobile

Backend (webapp.py):
- Flask + Flask-SocketIO for real-time updates
- Background job processing with threading
- File upload/download handling
- Job state persistence
- REST API endpoints

Frontend:
- Modern dark theme UI
- Mode selection with visual cards
- Form with all options and settings
- Real-time progress modal with log streaming
- Toast notifications
- Keyboard shortcuts (Ctrl+Enter to submit, Escape to close)

Documentation:
- Updated README.md with web interface section
- Updated EXAMPLES.md with web interface usage
- Updated requirements.txt with web dependencies

EXAMPLES.md

@@ -8,24 +8,25 @@ This document contains comprehensive examples for using the VideoGen toolkit, co
 
 1. [Basic Usage](#basic-usage)
 2. [Auto Mode](#auto-mode)
-3. [Text-to-Video (T2V)](#text-to-video-t2v)
-4. [Image-to-Video (I2V)](#image-to-video-i2v)
-5. [Text-to-Image (T2I)](#text-to-image-t2i)
-6. [Image-to-Image (I2I)](#image-to-image-i2i)
-7. [Video-to-Video (V2V)](#video-to-video-v2v)
-8. [Video-to-Image (V2I)](#video-to-image-v2i)
-9. [2D-to-3D Conversion](#2d-to-3d-conversion)
-10. [Audio Generation](#audio-generation)
-11. [Lip Sync](#lip-sync)
-12. [Video Dubbing & Translation](#video-dubbing--translation)
-13. [Subtitle Generation](#subtitle-generation)
-14. [Character Consistency](#character-consistency)
-15. [Distributed Multi-GPU](#distributed-multi-gpu)
-16. [Model Management](#model-management)
-17. [VRAM Management](#vram-management)
-18. [Upscaling](#upscaling)
-19. [NSFW Content](#nsfw-content)
-20. [Advanced Combinations](#advanced-combinations)
+3. [Web Interface](#web-interface)
+4. [Text-to-Video (T2V)](#text-to-video-t2v)
+5. [Image-to-Video (I2V)](#image-to-video-i2v)
+6. [Text-to-Image (T2I)](#text-to-image-t2i)
+7. [Image-to-Image (I2I)](#image-to-image-i2i)
+8. [Video-to-Video (V2V)](#video-to-video-v2v)
+9. [Video-to-Image (V2I)](#video-to-image-v2i)
+10. [2D-to-3D Conversion](#2d-to-3d-conversion)
+11. [Audio Generation](#audio-generation)
+12. [Lip Sync](#lip-sync)
+13. [Video Dubbing & Translation](#video-dubbing--translation)
+14. [Subtitle Generation](#subtitle-generation)
+15. [Character Consistency](#character-consistency)
+16. [Distributed Multi-GPU](#distributed-multi-gpu)
+17. [Model Management](#model-management)
+18. [VRAM Management](#vram-management)
+19. [Upscaling](#upscaling)
+20. [NSFW Content](#nsfw-content)
+21. [Advanced Combinations](#advanced-combinations)
 
 ---
 
@@ -59,6 +60,145 @@ python3 videogen --auto --prefer-speed --prompt "quick animation test"
 
 ---
 
+## Web Interface
+
+VideoGen includes a modern web interface for easy access to all features without using the command line.
+
+### Starting the Web Server
+
+```bash
+# Start on default port (5000)
+python3 webapp.py
+
+# Start on custom port
+python3 webapp.py --port 8080
+
+# Start accessible from network
+python3 webapp.py --host 0.0.0.0 --port 5000
+
+# Start with debug mode
+python3 webapp.py --debug
+```
+
+### Web Interface Features
+
+The web interface provides access to all VideoGen features:
+
+1. **Generate Tab**
+   - Mode selection (T2V, I2V, T2I, I2I, V2V, Dub, Subtitles, Upscale)
+   - Prompt input with quick hints
+   - Model selection with auto-mode option
+   - File upload for input images/videos/audio
+   - Resolution, FPS, duration settings
+   - Audio options (TTS, music, sync, lip-sync)
+   - Translation/dubbing options
+   - Advanced settings (offloading, VRAM limit, debug)
+
+2. **Jobs Tab**
+   - Real-time job monitoring
+   - Progress bars with status text
+   - Output log streaming
+   - Cancel/retry/delete jobs
+   - Download generated files
+
+3. **Gallery Tab**
+   - Browse all generated files
+   - Preview videos and images
+   - Download files
+   - Delete files
+
+4. **Settings Tab**
+   - Server configuration
+   - Default values
+   - About information
+
+### Using the Web Interface
+
+1. **Start the server:**
+   ```bash
+   python3 webapp.py
+   ```
+
+2. **Open in browser:**
+   Navigate to `http://localhost:5000`
+
+3. **Select a mode:**
+   Click on the desired generation mode (T2V, I2V, etc.)
+
+4. **Enter prompt:**
+   Type your prompt or use the quick hints
+
+5. **Configure settings:**
+   Select model, resolution, duration, etc.
+
+6. **Upload files (if needed):**
+   For I2I, V2V, dubbing - upload input files
+
+7. **Click Generate:**
+   Watch real-time progress in the modal
+
+8. **Download result:**
+   From the modal, jobs list, or gallery
+
+### Web Interface API
+
+The web interface also provides a REST API:
+
+```bash
+# Get model list
+curl http://localhost:5000/api/models
+
+# Get TTS voices
+curl http://localhost:5000/api/tts-voices
+
+# Get languages
+curl http://localhost:5000/api/languages
+
+# Upload a file
+curl -X POST -F "file=@image.png" -F "type=image" http://localhost:5000/api/upload
+
+# Create a job
+curl -X POST -H "Content-Type: application/json" \
+  -d '{"mode":"t2v","prompt":"a cat playing","model":"wan_1.3b_t2v"}' \
+  http://localhost:5000/api/jobs
+
+# Get job status
+curl http://localhost:5000/api/jobs/JOB_ID
+
+# Cancel a job
+curl -X POST http://localhost:5000/api/jobs/JOB_ID/cancel
+
+# List outputs
+curl http://localhost:5000/api/outputs
+
+# Download a file
+curl http://localhost:5000/api/download/filename.mp4 -o output.mp4
+```
+
+### WebSocket Events
+
+For real-time updates, connect via Socket.IO:
+
+```javascript
+const socket = io('http://localhost:5000');
+
+// Subscribe to job updates
+socket.emit('subscribe_job', 'JOB_ID');
+
+// Receive job updates
+socket.on('job_update', (job) => {
+    console.log('Progress:', job.progress);
+    console.log('Status:', job.status);
+});
+
+// Receive log lines
+socket.on('job_log', (data) => {
+    console.log('Log:', data.line);
+});
+```
+
+---
+
 ## Auto Mode
 
 Auto mode analyzes your prompt and automatically:

README.md

@@ -2,7 +2,7 @@
 
 **Copyleft © 2026 Stefy <stefy@nexlab.net>**
 
-A comprehensive, GPU-accelerated video generation toolkit supporting Text-to-Video (T2V), Image-to-Video (I2V), Text-to-Image (T2I), Image-to-Image (I2I), Video-to-Video (V2V), Video-to-Image (V2I), and 2D-to-3D conversion with audio synthesis, synchronization, and lip-sync capabilities.
+A comprehensive, GPU-accelerated video generation toolkit supporting Text-to-Video (T2V), Image-to-Video (I2V), Text-to-Image (T2I), Image-to-Image (I2I), Video-to-Video (V2V), Video-to-Image (V2I), and 2D-to-3D conversion with audio synthesis, synchronization, lip-sync, dubbing, and translation capabilities.
 
 ---
 
@@ -34,6 +34,13 @@ A comprehensive, GPU-accelerated video generation toolkit supporting Text-to-Vid
 - **Audio Sync**: Match audio duration to video (stretch, trim, pad, loop)
 - **Lip Sync**: Wav2Lip and SadTalker integration
 
+### Video Dubbing & Translation
+- **Video Dubbing**: Translate and dub videos while preserving original voice
+- **Voice Cloning**: Preserve speaker's voice in translated video
+- **Automatic Subtitles**: Generate subtitles using Whisper
+- **Subtitle Translation**: Translate subtitles to 20+ languages
+- **Subtitle Burning**: Burn subtitles directly into video
+
 ### Model Support
 - **Small Models** (<16GB VRAM): Wan 1.3B, Zeroscope, ModelScope
 - **Medium Models** (16-30GB VRAM): Wan 14B, CogVideoX, Mochi
@@ -44,12 +51,14 @@ A comprehensive, GPU-accelerated video generation toolkit supporting Text-to-Vid
 - **Auto Mode**: Automatic model selection and configuration
 - **NSFW Detection**: Automatic content classification
 - **Prompt Splitting**: Intelligent I2V prompt separation
-- **Time Estimation**: Predict generation time before starting
+- **Time Estimation**: Hardware-aware generation time prediction
 - **Multi-GPU**: Distributed generation across multiple GPUs
+- **Auto-Disable**: Models that fail 3 times are auto-disabled
 
-### AI Integration
+### User Interfaces
+- **Command Line**: Full-featured CLI with all options
+- **Web Interface**: Modern web UI with real-time progress updates
 - **MCP Server**: Model Context Protocol wrapper for AI agents
-- **Skill Documentation**: Comprehensive AI agent integration guide
 
 ---
 
@@ -77,6 +86,11 @@ pip install opencv-python face-recognition dlib --break-system-packages
 git clone https://github.com/Rudrabha/Wav2Lip.git
 ```
 
+### Web Interface
+```bash
+pip install flask flask-cors flask-socketio eventlet
+```
+
 ### MCP Server (For AI Agents)
 ```bash
 pip install mcp
@@ -187,6 +201,38 @@ See [SKILL.md](SKILL.md) for comprehensive AI agent integration guide including:
 
 ---
 
+## Web Interface
+
+VideoGen includes a modern web interface for easy access to all features:
+
+### Starting the Web Server
+
+```bash
+python3 webapp.py --port 5000 --host 0.0.0.0
+```
+
+Then open `http://localhost:5000` in your browser.
+
+### Web Interface Features
+
+- **All Generation Modes**: T2V, I2V, T2I, I2I, V2V, Upscale, Dubbing, Subtitles
+- **Real-time Progress**: Live progress updates with output log streaming
+- **File Upload/Download**: Upload images, videos, audio; download generated content
+- **Model Selection**: Browse and select from all available models
+- **Job Management**: View, cancel, retry, and track all generation jobs
+- **Gallery**: Browse and download all generated files
+- **Responsive Design**: Works on desktop and mobile devices
+
+### Web Interface Screenshots
+
+The web interface provides:
+1. **Generate Tab**: Main generation form with all options
+2. **Jobs Tab**: Real-time job monitoring with progress bars
+3. **Gallery Tab**: Browse and download generated content
+4. **Settings Tab**: Configuration and about information
+
+---
+
 ## Documentation
 
 - **[EXAMPLES.md](EXAMPLES.md)**: Comprehensive command-line examples for all features
@@ -266,6 +312,12 @@ export CUDA_VISIBLE_DEVICES=0,1        # GPU selection
 ```
 videogen/
 ├── videogen              # Main script
+├── webapp.py             # Web interface server
+├── templates/            # HTML templates
+│   └── index.html        # Main web UI
+├── static/               # Static assets
+│   ├── css/style.css     # Styles
+│   └── js/app.js         # JavaScript
 ├── videogen_mcp_server.py # MCP server for AI agents
 ├── README.md             # This file
 ├── EXAMPLES.md           # Comprehensive examples

requirements.txt

@@ -55,5 +55,16 @@ pydantic>=2.0.0
 # Distributed Processing
 # accelerate  # Already listed above
 
+# Web Interface Dependencies (Optional - for webapp.py)
+flask>=3.0.0
+flask-cors>=4.0.0
+flask-socketio>=5.3.0
+eventlet>=0.33.0
+python-socketio>=5.10.0
+werkzeug>=3.0.0
+
+# MCP Server Dependencies (Optional - for AI agent integration)
+# mcp>=0.9.0  # Install with: pip install mcp
+
 # Optional: NSFW Classification
 # onnxruntime>=1.16.0
\ No newline at end of file