190 datasets found

DiffuGen generates high-quality labeled image datasets using stable diffusion models.

This dataset contains images generated by various text-to-image models, including Stable Diffusion 1.4, Stable Diffusion 2.1, Stable Diffusion XL, and DeepFloyd IF.

Diffusion models (DMs) have revolutionized image generation, producing high-quality images with applications spanning various fields. However, their ability to create...

CelebAHQ is a dataset of celebrity faces, with 30,000 images of 10,000 celebrities.

The dataset is used for image generation and editing tasks.

The dataset used in the paper is COCO-stuff and Visual Genome. COCO-stuff is a dataset of 164K images with pixel-level stuff annotations, and Visual Genome is a dataset of...

Autoregressive models recently achieved comparable results versus state-of-the-art Generative Adversarial Networks (GANs) with the help of Vector Quantized Variational...

The dataset is a 4-way array of dimensions 4000 × 90 × 90 × 3, where each pixel gives the intensity for colors red, green and blue, resulting in a multiway array of dimensions X...

The dataset used in the paper is not explicitly described, but it is mentioned that the authors used a dataset to train and fine-tune the diffusion model.

The dataset used in the paper is not explicitly described, but it is mentioned that the authors used a dataset to train and fine-tune the diffusion model.

The dataset used in the paper is not explicitly described, but it is mentioned that the authors used a dataset to train and fine-tune the diffusion model.

The dataset used in the paper is not explicitly described, but it is mentioned that the authors used a dataset to train and fine-tune the diffusion model.

The dataset used for training the self-similarity-based super-resolution model for photoacoustic angiography.

The Non-Hair-FFHQ dataset is a high-quality image dataset that contains 6,000 non-hair-FFHQ portraits.

Large-scale text-to-image diffusion models can gener-ate high-fidelity images with powerful compositional ability. However, these models are typically trained on an enormous...

The DeepFashion dataset is a large-scale dataset for person image synthesis, containing 101,966 pairs of images with different poses and clothing.

Sierpinski carpet dataset for image generation via GPA.

The dataset includes 280 real artworks and 350 AI-generated images, covering 7 art styles and 5 AI generators.

Anime Faces is a dataset of 50,000 64x64 RGB images of anime faces.

The EmpatheticDialogues dataset is a text dataset for training empathetic AI chatbots, consisting of 25k conversations grounded in emotional situations with emotion labels.