-
MNIST and FashionMNIST
The MNIST and FashionMNIST datasets are used to test the performance of the proposed generative autoencoders. -
Laion-400M
Text-to-image Latent Diffusion model, CLIP model, Blended Diffusion model, GLIDE model, GLIDE-filtered model -
CLIP-GLaSS
The dataset used for the text-to-image task consists of 20 context tokens, to which three fixed tokens have been concatenated, representing the static context "the picture of". -
Pixart Alpha
Diffusion Models (DMs) represent a powerful class of generative models that have gained significant attention in recent years. -
FFHQ, AFHQ, and LSUN
The proposed method uses the FFHQ, AFHQ, and LSUN datasets for image generation tasks. -
Large Logo Dataset (LLD)
The Large Logo Dataset (LLD) is a large-scale logo dataset crawled from the web, containing 486,377 logos in 32x32 pixel resolution. -
LatentGAN Autoencoder: Learning Disentangled Latent Distribution
LatentGAN Autoencoder: Learning Disentangled Latent Distribution -
No Token Left Behind: Explainability-Aided Image Classification and Generation
The dataset used in the paper is not explicitly described, but it is mentioned that the authors used the ImageNet, ImageNetV2, ImageNet-Sketch, ImageNet-A, and Imagenet-R datasets. -
MD30 (Manually-annotated Dataset)
MD30 (Manually-annotated Dataset) comprises 30 images chosen from the 807 images. For those images, we discard sn by BLIP2 and attach a more accurate text as sn by a human... -
BD807 (BLIP2-guided Dataset with 807 images)
NoiseCollage generates an image with N objects from the following conditions, L, S, and s∗: L = {l1,..., lN } is the N layout conditions to control the layout of individual... -
FashionMNIST dataset
The dataset used in this paper is the FashionMNIST dataset, which consists of 60,000 images of clothing items from 10 different classes. -
CIFAR10 dataset
The dataset used in this paper is the CIFAR10 dataset, which contains 60,000 32x32 color images in 10 classes, with 6,000 images per class. -
Entropy-driven Sampling and Training Scheme for Conditional Diffusion Generation
Conditional image generation using denoising diffusion probabilistic model with entropy-driven sampling and training scheme -
MOA: Mixture-of-Attention for Subject-Context Disentanglement in Personalized...
A synthetic dataset of over 65,000 identities, each associated with multiple images of that person. -
weights2weights (w2w) Space
A dataset of over 60,000 customized diffusion model weights, each fine-tuned to insert a different person's visual identity. -
AFHQ Dog and Cat
AFHQ Dog and Cat dataset for unconditional image generation -
FFHQ, AFHQ-Cat, and LSUN-Church
The dataset used in the paper is a large dataset of images, including FFHQ, AFHQ-Cat, and LSUN-Church.
