### Setup Development Environment

Source: https://github.com/tencent-hunyuan/hunyuanvideo-foley/blob/main/INSTALL.md

Clone the project, install the development version with dependencies, set up pre-commit hooks, and run tests. Includes commands for code formatting and type checking.

```bash
# Clone the project
git clone https://github.com/Tencent-Hunyuan/HunyuanVideo-Foley
cd HunyuanVideo-Foley

# Install development version
pip install -e .[dev]

# Install pre-commit hooks
pre-commit install

# Run tests
python -m pytest

# Code formatting
black --line-length 120 .
isort --profile black .

# Type checking
mypy --ignore-missing-imports .
```

--------------------------------

### Setup Development Environment

Source: https://github.com/tencent-hunyuan/hunyuanvideo-foley/blob/main/DEVELOPMENT.md

Steps to set up a Python virtual environment, activate it, and install project dependencies including the project in editable mode.

```bash
python -m venv venv
source venv/bin/activate  # Linux/Mac
# or
venv\Scripts\activate     # Windows

pip install -r requirements.txt
pip install -e .
```

--------------------------------

### Install and Install Pre-commit Hooks

Source: https://github.com/tencent-hunyuan/hunyuanvideo-foley/blob/main/DEVELOPMENT.md

Install the pre-commit package and set up the hooks to automatically format code before each commit.

```bash
pip install pre-commit
pre-commit install
```

--------------------------------

### Build and Install Wheel Package

Source: https://github.com/tencent-hunyuan/hunyuanvideo-foley/blob/main/INSTALL.md

Build a wheel package from the source and then install it using pip.

```bash
# In the project root directory
python setup.py bdist_wheel
pip install dist/hunyuanvideo_foley-1.0.0-py3-none-any.whl
```

--------------------------------

### Install from Source (Recommended)

Source: https://github.com/tencent-hunyuan/hunyuanvideo-foley/blob/main/INSTALL.md

Clone the repository and install the package in development mode. Use '[all]' to include all optional dependencies.

```bash
# Clone the repository
git clone https://github.com/Tencent-Hunyuan/HunyuanVideo-Foley
cd HunyuanVideo-Foley

# Install the package (development mode)
pip install -e .

# Or install with all optional dependencies
pip install -e .[all]
```

--------------------------------

### Install Directly from GitHub

Source: https://github.com/tencent-hunyuan/hunyuanvideo-foley/blob/main/INSTALL.md

Install the package directly using pip from its GitHub repository.

```bash
pip install git+https://github.com/Tencent-Hunyuan/HunyuanVideo-Foley.git
```

--------------------------------

### Verify Installation

Source: https://github.com/tencent-hunyuan/hunyuanvideo-foley/blob/main/INSTALL.md

Check if the package is installed correctly by importing it and checking the command-line tool help.

```bash
# Check if the package is installed correctly
python -c "import hunyuanvideo_foley; print(hunyuanvideo_foley.__version__)"

# Check the command-line tool
hunyuanvideo-foley --help
```

--------------------------------

### Install Special Dependencies

Source: https://github.com/tencent-hunyuan/hunyuanvideo-foley/blob/main/INSTALL.md

Install 'audiotools' and a specific version of 'transformers' that supports SigLIP2, as these are not on PyPI.

```bash
# Install audiotools (required)
pip install git+https://github.com/descriptinc/audiotools

# Install specific version of transformers (SigLIP2 support)
pip install git+https://github.com/huggingface/transformers@v4.49.0-SigLIP-2
```

--------------------------------

### Install Optional Dependencies

Source: https://github.com/tencent-hunyuan/hunyuanvideo-foley/blob/main/INSTALL.md

Install optional dependencies for development, testing, Gradio interface, or all available optional packages.

```bash
# Install development dependencies
pip install hunyuanvideo-foley[dev]

# Install testing dependencies
pip install hunyuanvideo-foley[test]

# Install Gradio interface dependencies
pip install hunyuanvideo-foley[gradio]

# Install all optional dependencies
pip install hunyuanvideo-foley[all]
```

--------------------------------

### Example Function with Type Hints and Docstrings

Source: https://github.com/tencent-hunyuan/hunyuanvideo-foley/blob/main/DEVELOPMENT.md

A Python function demonstrating type hints for parameters and return values, along with Google-style docstrings including Args, Returns, and Raises sections.

```python
import os
from typing import Optional, Tuple

import numpy as np

def process_video(
    video_path: str,
    max_duration: Optional[float] = None
) -> Tuple[np.ndarray, float]:
    """
    Process video file and extract frames.    
    Args:
        video_path: Path to input video file
        max_duration: Maximum duration in seconds (optional)
        
    Returns:
        Tuple of (frames array, duration in seconds)
        
    Raises:
        FileNotFoundError: If video file doesn't exist
        VideoProcessingError: If video processing fails
    """
    if not os.path.exists(video_path):
        raise FileNotFoundError(f"Video file not found: {video_path}")
    
    # Implementation here...
```

--------------------------------

### Download Pretrained Models from Huggingface (git-lfs)

Source: https://github.com/tencent-hunyuan/hunyuanvideo-foley/blob/main/README.md

Download the pretrained model weights from Huggingface using git-lfs. Ensure git-lfs is installed and configured.

```bash
# using git-lfs
git clone https://huggingface.co/tencent/HunyuanVideo-Foley
```

--------------------------------

### Clone HunyuanVideo-Foley Repository

Source: https://github.com/tencent-hunyuan/hunyuanvideo-foley/blob/main/README.md

Clone the official repository to your local machine and navigate into the project directory. This is the first step to begin setup.

```bash
# \ud83d\udce6 Clone the repository
git clone https://github.com/Tencent-Hunyuan/HunyuanVideo-Foley
cd HunyuanVideo-Foley
```

--------------------------------

### Install Project Dependencies

Source: https://github.com/tencent-hunyuan/hunyuanvideo-foley/blob/main/README.md

Install all necessary Python dependencies listed in the requirements.txt file. It is recommended to use a Conda environment for managing dependencies.

```bash
# \u2699\ufe0f Install dependencies
pip install -r requirements.txt
```

--------------------------------

### Troubleshoot Transformers Version

Source: https://github.com/tencent-hunyuan/hunyuanvideo-foley/blob/main/INSTALL.md

If you face issues related to the 'transformers' library, install the specific version that supports SigLIP2.

```bash
pip install git+https://github.com/huggingface/transformers@v4.49.0-SigLIP-2
```

--------------------------------

### Troubleshoot ImportError for audiotools

Source: https://github.com/tencent-hunyuan/hunyuanvideo-foley/blob/main/INSTALL.md

If you encounter an 'ImportError: No module named 'audiotools'', install it using the provided pip command.

```bash
pip install git+https://github.com/descriptinc/audiotools
```

--------------------------------

### Use Command-Line Tool

Source: https://github.com/tencent-hunyuan/hunyuanvideo-foley/blob/main/INSTALL.md

Process single videos, batch videos from a CSV, or launch the Gradio interface using the command-line tool.

```bash
# Single video processing
hunyuanvideo-foley \
    --model_path ./pretrained_models \
    --single_video video.mp4 \
    --single_prompt "footsteps on gravel" \
    --output_dir ./outputs

# Batch processing
hunyuanvideo-foley \
    --model_path ./pretrained_models \
    --csv_path batch_videos.csv \
    --output_dir ./outputs

# Launch Gradio interface
hunyuanvideo-foley --gradio --model_path ./pretrained_models
```

--------------------------------

### Launch Gradio Web Interface (XL Model)

Source: https://github.com/tencent-hunyuan/hunyuanvideo-foley/blob/main/README.md

Launch the interactive Gradio web interface with the memory-friendly XL model. Set the HIFI_FOLEY_MODEL_PATH environment variable and specify MODEL_SIZE=xl.

```bash
export HIFI_FOLEY_MODEL_PATH=PRETRAINED_MODEL_PATH_DIR
MODEL_SIZE=xl python3 gradio_app.py
```

--------------------------------

### Launch Gradio Web Interface with Offload Enabled

Source: https://github.com/tencent-hunyuan/hunyuanvideo-foley/blob/main/README.md

Launch the Gradio web interface with optional offload enabled to reduce memory usage. Set the HIFI_FOLEY_MODEL_PATH environment variable and ENABLE_OFFLOAD=true.

```bash
export HIFI_FOLEY_MODEL_PATH=PRETRAINED_MODEL_PATH_DIR
ENABLE_OFFLOAD=true python3 gradio_app.py
```

--------------------------------

### Download Pretrained Models from Huggingface (huggingface-cli)

Source: https://github.com/tencent-hunyuan/hunyuanvideo-foley/blob/main/README.md

Download the pretrained model weights from Huggingface using the huggingface-cli tool. This is an alternative method to git-lfs.

```bash
# using huggingface-cli
huggingface-cli download tencent/HunyuanVideo-Foley
```

--------------------------------

### Download Test Videos

Source: https://github.com/tencent-hunyuan/hunyuanvideo-foley/blob/main/README.md

Download sample test videos required for batch processing. This script should be run before executing batch processing commands.

```bash
bash ./download_test_videos.sh
```

--------------------------------

### Download Model using HuggingFace Hub

Source: https://github.com/tencent-hunyuan/hunyuanvideo-foley/blob/main/INSTALL.md

Download the pre-trained model from HuggingFace Hub using git clone or the huggingface-cli.

```bash
# Using HuggingFace Hub
git clone https://huggingface.co/tencent/HunyuanVideo-Foley

# Or using huggingface-cli
huggingface-cli download tencent/HunyuanVideo-Foley
```

--------------------------------

### Launch Gradio Web Interface (XXL Model)

Source: https://github.com/tencent-hunyuan/hunyuanvideo-foley/blob/main/README.md

Launch the interactive Gradio web interface using the default XXL model. Set the HIFI_FOLEY_MODEL_PATH environment variable to your model directory.

```bash
export HIFI_FOLEY_MODEL_PATH=PRETRAINED_MODEL_PATH_DIR
python3 gradio_app.py
```

--------------------------------

### Use Original Scripts (Backward Compatibility)

Source: https://github.com/tencent-hunyuan/hunyuanvideo-foley/blob/main/INSTALL.md

Run inference using the original 'infer.py' script or launch the Gradio application by setting the model path environment variable.

```bash
# Use the original infer.py script
python infer.py --model_path ./pretrained_models --single_video video.mp4 --single_prompt "audio description"

# Launch Gradio application
export HIFI_FOLEY_MODEL_PATH=./pretrained_models
python gradio_app.py
```

--------------------------------

### Batch Process Videos with CSV

Source: https://github.com/tencent-hunyuan/hunyuanvideo-foley/blob/main/README.md

Process multiple videos by providing a CSV file containing video paths and descriptions. This command requires the model path, CSV file path, and output directory.

```bash
python3 infer.py \
    --model_path PRETRAINED_MODEL_PATH_DIR \
    --csv_path assets/test.csv \
    --output_dir OUTPUT_DIR \
    # --enable_offload
```

--------------------------------

### Generate Foley Audio for Single Video (XXL Model)

Source: https://github.com/tencent-hunyuan/hunyuanvideo-foley/blob/main/README.md

Use this command to generate Foley audio for a single video file using the default XXL model. Specify the model path, video path, audio description prompt, and output directory.

```bash
python3 infer.py \
    --model_path PRETRAINED_MODEL_PATH_DIR \
    --single_video video_path \
    --single_prompt "audio description" \
    --output_dir OUTPUT_DIR \
    # --enable_offload
```

--------------------------------

### Generate Foley Audio for Single Video (XL Model)

Source: https://github.com/tencent-hunyuan/hunyuanvideo-foley/blob/main/README.md

Use this command for generating Foley audio with the memory-friendly XL model. Ensure to set the model size to 'xl' and specify the model path, video path, prompt, and output directory.

```bash
python3 infer.py \
    --model_path PRETRAINED_MODEL_PATH_DIR \
    --model_size xl \
    --single_video video_path \
    --single_prompt "audio description" \
    --output_dir OUTPUT_DIR \
    # --enable_offload
```

--------------------------------

### Use as Python Package

Source: https://github.com/tencent-hunyuan/hunyuanvideo-foley/blob/main/INSTALL.md

Load the model and process features using the HunyuanVideo-Foley Python package. This involves loading models and then processing visual, text, and audio data.

```python
import hunyuanvideo_foley as hvf

# Load the model
model_dict, cfg = hvf.load_model(
    model_path="path/to/model",
    config_path="configs/hunyuanvideo-foley-xxl.yaml"
)

# Process features
visual_feats, text_feats, audio_len = hvf.feature_process(
    video_path="video.mp4",
    prompt="footsteps on gravel",
    model_dict=model_dict,
    cfg=cfg
)

# Generate audio
audio, sample_rate = hvf.denoise_process(
    visual_feats, text_feats, audio_len,
    model_dict, cfg
)
```

--------------------------------

### Run Quality Checks

Source: https://github.com/tencent-hunyuan/hunyuanvideo-foley/blob/main/DEVELOPMENT.md

Execute the automated quality checks for code formatting, import sorting, linting, type checking, and running tests.

```bash
black --check --line-length 120 .
isort --check-only --profile black .
flake8 --max-line-length 120
mypy --ignore-missing-imports .
pytest
```

--------------------------------

### Run Pytest Tests

Source: https://github.com/tencent-hunyuan/hunyuanvideo-foley/blob/main/DEVELOPMENT.md

Commands to execute tests using pytest, including running all tests, targeting a specific file, and running tests with code coverage.

```bash
# Run all tests
python -m pytest

# Run specific test file
python -m pytest tests/test_feature_utils.py

# Run with coverage
python -m pytest --cov=hunyuanvideo_foley
```

--------------------------------

### Manually Format and Lint Code

Source: https://github.com/tencent-hunyuan/hunyuanvideo-foley/blob/main/DEVELOPMENT.md

Commands to manually format Python code using Black, sort imports with isort, check style with flake8, and perform static type checking with mypy.

```bash
# Format all Python files
black --line-length 120 .

# Sort imports
isort --profile black --line-length 120 .

# Check code style
flake8 --max-line-length 120

# Type checking
mypy --ignore-missing-imports .
```

=== COMPLETE CONTENT === This response contains all available snippets from this library. No additional content exists. Do not make further requests.