FFHQ 70000张png图片 链接：https://pan.baidu.com/s/1XDfTKWOhtwAAQQJ0KBU4RQ 提取码：bowj

  Flickr-Faces-HQ Dataset (FFHQ)

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

A Style-Based Generator Architecture for Generative Adversarial Networks Tero Karras (NVIDIA), Samuli Laine (NVIDIA), Timo Aila (NVIDIA) http://stylegan.xyz/paper

The dataset consists of 70,000 high-quality PNG images… See the full description on the dataset page: https://huggingface.co/datasets/student/FFHQ.

FFHQ-Aging is a Dataset of human faces designed for benchmarking age transformation algorithms as well as many other possible vision tasks. This dataset is an extention of the NVIDIA FFHQ dataset, on top of the 70,000 original FFHQ images, it also contains the following information for each image: * Gender information (male/female with confidence score) * Age group information (10 classes with confidence score) * Head pose (pitch, roll & yaw) * Glasses type (none, normal or dark) * Eye occlusion score (0-100, different score for each eye) * Full semantic map (19 classes, based on CelebAMask-HQ labels)

marcosv/ffhq-dataset dataset hosted on Hugging Face and contributed by the HF Datasets community

Original dataset: https://www.kaggle.com/arnaud58/flickrfaceshq-dataset-ffhq

This dataset contains the same images as the FFHQ dataset, downscaled to 256x256, 128x128, and 64x64 pixels, to make them easier to use in smaller generative models.

The dataset consists of 52,000 high-quality PNG images at 512×512 resolution and contains considerable variation in terms of age, ethnicity and image background. It also has good coverage of accessories such as eyeglasses, sunglasses, hats, etc. The images were crawled from Flickr, thus inheriting all the biases of that website, and automatically aligned and cropped using dlib. Only images under permissive licenses were collected. Various automatic filters were used to prune the set, and finally Amazon Mechanical Turk was used to remove the occasional statues, paintings, or photos of photos.

For business inquiries, please contact researchinquiries@nvidia.com

For press and other inquiries, please contact Hector Marinez at hmarinez@nvidia.com

Dataset

This dataset was created by Youthpe Apps

Contents

Sakamotossss/cluster-ffhq dataset hosted on Hugging Face and contributed by the HF Datasets community

used to training face recognition model

Dataset

This dataset was created by Hưng.341

Released under Database: Open Database, Contents: Database Contents

Contents

Dataset

This dataset was created by misteick

Contents

ssbai/ffhq dataset hosted on Hugging Face and contributed by the HF Datasets community

bitmind/ffhq-256_0-to-8749_mobius dataset hosted on Hugging Face and contributed by the HF Datasets community

The ukiyo-e faces dataset comprises of 5209 images of faces from ukiyo-e prints. The images are 1024x1024 pixels in jpeg format and have been aligned using the procedure used for the FFHQ dataset

bitmind/ffhq-256_46662-to-54438_RealVisXL_V4.0 dataset hosted on Hugging Face and contributed by the HF Datasets community

Dataset

This dataset was created by sw-song

Contents

Animal FacesHQ (AFHQ) is a dataset of animal faces consisting of 15,000 high-quality images at 512 × 512 resolution. The dataset includes three domains of cat, dog, and wildlife, each providing 5000 images. By having multiple (three) domains and diverse images of various breeds (≥ eight) per each domain, AFHQ sets a more challenging image-to-image translation problem. All images are vertically and horizontally aligned to have the eyes at the center. The low-quality images were discarded by human effort.

bitmind/ffhq-256_0-to-9_FLUX.1-dev dataset hosted on Hugging Face and contributed by the HF Datasets community

Dataset

This dataset was created by Le Dang Khoa

Contents

FFHQ Dataset (pravsels/FFHQ_1024) encoded using the dc-ae-f32c32-mix-1.0 auto encoder. Example usage import sys sys.path.append('../dcae') # https://github.com/vladmandic/dcae from dcae import DCAE

from datasets import load_dataset import torch import torchvision

dataset = load_dataset("SwayStar123/FFHQ_1024_DC-AE_f32", split="train") dc_ae = DCAE("dc-ae-f32c32-mix-1.0", device="cuda", dtype=torch.bfloat16).eval() # Must be bfloat. with float16 it produces terrible outputs.

def denorm(x):… See the full description on the dataset page: https://huggingface.co/datasets/SwayStar123/FFHQ_1024_DC-AE_f32.

abcd10987/ffhq-256_stable-diffusion-xl-base-1.0 dataset hosted on Hugging Face and contributed by the HF Datasets community