Ecosyste.ms: Awesome
An open API service indexing awesome lists of open source software.
https://github.com/anjieyang/VFHQ-downloader
https://github.com/anjieyang/VFHQ-downloader
Last synced: 6 days ago
JSON representation
- Host: GitHub
- URL: https://github.com/anjieyang/VFHQ-downloader
- Owner: anjieyang
- Created: 2024-04-10T03:50:18.000Z (9 months ago)
- Default Branch: main
- Last Pushed: 2024-04-12T18:00:11.000Z (9 months ago)
- Last Synced: 2024-04-13T00:04:10.804Z (9 months ago)
- Language: Python
- Size: 18.6 KB
- Stars: 2
- Watchers: 1
- Forks: 0
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
Awesome Lists containing this project
README
# VFHQ-downloader
VFHQ-downloader is a Python-based utility designed for the easy downloading and processing of videos from the [VFHQ dataset](https://liangbinxie.github.io/projects/vfhq/).
## Warnning
This may cause [temporary IP block](https://github.com/yt-dlp/yt-dlp/issues/7860) by YouTube.
## Setup
1. Clone the repository or download the source code.
2. Install required Python packages: `pip install -r requirements.txt`.
3. Ensure `yt-dlp` and `aria2c` are installed and accessible in your system's PATH.
4. Download and decompress the [meta_info.zip](https://1drv.ms/u/s!Ag1HH_EDGMqqh2i5sgNyHpcVldos?e=8wKFtV) file in the root directory of the project to obtain the metadata files needed for video processing.## Usage
1. Ensure the metadata files are located in the `meta_info/` directory.
2. Run `main.py` to start the downloading and processing pipeline.
3. Processed videos will be available in the `data/outputs/` directory.
4. Make sure you modify `VIDEO_NUM` in `config.py`.## Note
This tool is specifically tailored for the VFHQ dataset and require modifications to work with other datasets or video sources.