KO | EN

GitLite

Minimalist Open Source Repository Search Engine

gitlite — search

#dsh #ai-agents #dsh-plugin #codex #developer-tools #claude-code #windows #desktop-app #typescript #rust #ai-agent #cli

AI-video-Generation

★ 1 Open GitHub ↗

A text to Video generation engine built using Hugging Face Inference API (Wan AI)

// repository documentation

Was this content helpful?

★ 0 (0 ratings)

# AI Video Generator

A web application that generates short videos from text prompts using open-source models from Hugging Face.

## Features

- Text-to-video generation using AI
- Simple and intuitive user interface
- FastAPI backend with React frontend
- **Prompt Enhancement:** Automatically enhances user prompts with cinematic descriptors for better video generation results.

## DEMO - 
https://www.loom.com/share/a556a7f9d1c14afda8311a25cdb00b23?sid=a1b477b1-8f74-4553-bcb4-e31f54131085 
and I have added few videos generated by the model in the dir

## Prerequisites

- Python 3.8+
- Node.js 16+
- A Hugging Face API token (optional, if using mock mode or providing via frontend).

## Setup

1.  **Clone the repository:**
    ```bash
    git clone <repository-url>
    cd ai-video-generator
    ```

2.  **Set up the backend:**
    ```bash
    cd backend
    python -m venv venv
    # On Windows
    .\venv\Scripts\activate
    # On macOS/Linux
    source venv/bin/activate
    pip install -r requirements.txt
    ```

3.  **Set up the frontend:**
    ```bash
    cd ../frontend
    npm install
    ```

4.  **Configure environment variables:**

Create a file named `.env` in the `backend` directory and add your Hugging Face API token and mock setting like this:

```
    HF_TOKEN=your_hugging_face_token
    MOCK_VIDEO_GENERATION=false
    ```
    *   **HF_TOKEN:** Set this to your Hugging Face API token. This is the recommended and most secure way to provide the token. If provided here, the frontend input field can be left empty.
    *   **MOCK_VIDEO_GENERATION:** Set to `true` to enable mock video generation (useful for development without consuming API credits). Set to `false` for actual generation.

## Running the Application Locally

**SECURITY WARNING:**
Providing your Hugging Face API token directly through the frontend input field is **NOT recommended for production environments** due to security risks. The token could be exposed if the frontend is compromised or if the connection is not secure. For production, always manage API keys securely using environment variables or dedicated secret management services on your server.

1.  **Start the backend server:**
    ```bash
    cd backend
    uvicorn main:app --host 0.0.0.0 --port 8000
    ```

2.  **Start the frontend development server (in a new terminal):**
    ```bash
    cd frontend
    npm start
    ```

3.  Open your browser and navigate to `http://localhost:3001`.

You can now enter your Hugging Face Token directly in the provided input field on the frontend, or rely on the `HF_TOKEN` set in your `backend/.env` file.

## Production Considerations

When deploying this application to a production environment, consider the following:

*   **API Key Management:** Never hardcode API keys. Use environment variables or a secure secret management service provided by your cloud platform. **Avoid taking API keys directly from the frontend in production.**
*   **Scalability:** For the AI model, consider using dedicated GPU-enabled services (e.g., AWS SageMaker, Google Cloud AI Platform, specialized inference providers) that can scale to handle demand. Running large AI models on general-purpose CPU servers is not efficient or cost-effective.
*   **Error Handling & Logging:** Implement robust error handling and logging to monitor the health and performance of your application in production.
*   **Performance:** Optimize your frontend assets and backend code for faster load times and responsiveness.
*   **Cost Management:** Monitor your API usage and set up alerts to manage costs, especially for paid AI services.
*   **Video Streaming:** For large video files, consider implementing video streaming optimizations (e.g., using a CDN, adaptive bitrate streaming) to ensure smooth playback for users.
*   **Prompt Engineering:** For better video generation results, explore advanced prompt engineering techniques or integrate RAG (Retrieval Augmented Generation) to provide more context to the AI model.

## Deployment

For deployment, you will need to build the frontend and serve the static files. You can then deploy the backend and the frontend to your preferred cloud provider.

### Backend

Deploy the FastAPI application to a service like Render, Railway, or Heroku.

### Frontend

Deploy the React application to a service like Vercel, Netlify, or any static site hosting service.

Make sure to set the `REACT_APP_API_URL` environment variable in your frontend deployment to the URL of your deployed backend.

AI-video-Generation

Explore Similar Repositories

Was this content helpful?

Recent Feedback

Download README