Flickr-Faces-HQ (FFHQ) is a high-quality image dataset of human faces, originally created as a benchmark for generative adversarial networks (GAN)

> python download_ffhq.py -h
usage: download_ffhq.py [-h] [-j] [-s] [-i] [-t] [-w] [-r] [-a]
                        [--num_threads NUM] [--status_delay SEC]
                        [--timing_window LEN] [--chunk_size KB]
                        [--num_attempts NUM]

Download Flickr-Face-HQ (FFHQ) dataset to current working directory.

optional arguments:
  -h, --help            show this help message and exit
  -j, --json            download metadata as JSON (254 MB)
  -s, --stats           print statistics about the dataset
  -i, --images          download 1024x1024 images as PNG (89.1 GB)
  -t, --thumbs          download 128x128 thumbnails as PNG (1.95 GB)
  -w, --wilds           download in-the-wild images as PNG (955 GB)
  -r, --tfrecords       download multi-resolution TFRecords (273 GB)
  -a, --align           recreate 1024x1024 images from in-the-wild images
  --num_threads NUM     number of concurrent download threads (default: 32)
  --status_delay SEC    time between download status prints (default: 0.2)
  --timing_window LEN   samples for estimating download eta (default: 50)
  --chunk_size KB       chunk size for each download thread (default: 128)
  --num_attempts NUM    number of download attempts per file (default: 10)
  --random-shift SHIFT  standard deviation of random crop rectangle jitter
  --retry-crops         retry random shift if crop rectangle falls outside image (up to 1000
                        times)
  --no-rotation         keep the original orientation of images
  --no-padding          do not apply blur-padding outside and near the image borders
  --source-dir DIR      where to find already downloaded FFHQ source data

> python ..\download_ffhq.py --json --images
Downloading JSON metadata...
\ 100.00% done  2/2 files  0.25/0.25 GB   43.21 MB/s  ETA: done
Parsing JSON metadata...
Downloading 70000 files...
| 100.00% done  70001/70001 files  89.19 GB/89.19 GB  59.87 MB/s  ETA: done

python download_ffhq.py \
    --source-dir 
   
     \
    --align --no-rotation --random-shift 0.2 --no-padding --retry-crops

   

{
  "0": {                                                 # Image index
    "category": "training",                              # Training or validation
    "metadata": {                                        # Info about the original Flickr photo:
      "photo_url": "https://www.flickr.com/photos/...",  # - Flickr URL
      "photo_title": "DSCF0899.JPG",                     # - File name
      "author": "Jeremy Frumkin",                        # - Author
      "country": "",                                     # - Country where the photo was taken
      "license": "Attribution-NonCommercial License",    # - License name
      "license_url": "https://creativecommons.org/...",  # - License detail URL
      "date_uploaded": "2007-08-16",                     # - Date when the photo was uploaded to Flickr
      "date_crawled": "2018-10-10"                       # - Date when the photo was crawled from Flickr
    },
    "image": {                                           # Info about the aligned 1024x1024 image:
      "file_url": "https://drive.google.com/...",        # - Google Drive URL
      "file_path": "images1024x1024/00000/00000.png",    # - Google Drive path
      "file_size": 1488194,                              # - Size of the PNG file in bytes
      "file_md5": "ddeaeea6ce59569643715759d537fd1b",    # - MD5 checksum of the PNG file
      "pixel_size": [1024, 1024],                        # - Image dimensions
      "pixel_md5": "47238b44dfb87644460cbdcc4607e289",   # - MD5 checksum of the raw pixel data
      "face_landmarks": [...]                            # - 68 face landmarks reported by dlib
    },
    "thumbnail": {                                       # Info about the 128x128 thumbnail:
      "file_url": "https://drive.google.com/...",        # - Google Drive URL
      "file_path": "thumbnails128x128/00000/00000.png",  # - Google Drive path
      "file_size": 29050,                                # - Size of the PNG file in bytes
      "file_md5": "bd3e40b2ba20f76b55dc282907b89cd1",    # - MD5 checksum of the PNG file
      "pixel_size": [128, 128],                          # - Image dimensions
      "pixel_md5": "38d7e93eb9a796d0e65f8c64de8ba161"    # - MD5 checksum of the raw pixel data
    },
    "in_the_wild": {                                     # Info about the in-the-wild image:
      "file_url": "https://drive.google.com/...",        # - Google Drive URL
      "file_path": "in-the-wild-images/00000/00000.png", # - Google Drive path
      "file_size": 3991569,                              # - Size of the PNG file in bytes
      "file_md5": "1dc0287e73e485efb0516a80ce9d42b4",    # - MD5 checksum of the PNG file
      "pixel_size": [2016, 1512],                        # - Image dimensions
      "pixel_md5": "86b3470c42e33235d76b979161fb2327",   # - MD5 checksum of the raw pixel data
      "face_rect": [667, 410, 1438, 1181],               # - Axis-aligned rectangle of the face region
      "face_landmarks": [...],                           # - 68 face landmarks reported by dlib
      "face_quad": [...]                                 # - Aligned quad of the face region
    }
  },
  ...
}