36 datasets found

The VBCDE-100 dataset is a comprehensive dataset containing 100 sensitive prompts spread across five categories: violence, gore, illegal activities, discrimination, and...

Scaling autoregressive models for content-rich text-to-image generation.

The dataset used for testing the Anonymization Prompt Learning (APL) model, containing names of public figures and their corresponding attribute descriptions.

The dataset used for training the Anonymization Prompt Learning (APL) model, containing names of public figures and their corresponding attribute descriptions.

Text-to-Image Diffusion Models (T2I DMs) have garnered significant attention for their ability to generate high-quality images from textual descriptions. However, these models...

Text-to-Image Diffusion Models (T2I DMs) have garnered significant attention for their ability to generate high-quality images from textual descriptions. However, these models...

The dataset is used to evaluate the proposed MuLan framework for progressive multi-object diffusion. It contains 200 prompts with complex spatial relationships and attribute...

The ENTIGEN dataset is a benchmark for evaluating the change in the diversity of text-to-image generations in the presence of ethical interventions.

A dataset of pre-trained models and their corresponding text prompts used for text-to-image diffusion models.

A dataset of pre-trained models and their corresponding text prompts used for text-to-image generation and editing.

A dataset of pre-trained models and their corresponding text prompts used for text-to-image generation and editing.

A benchmark for open-world compositional text-to-image generation. The dataset consists of 218 prompts with a single object and its number.

A dataset for text-to-image generation with accurate object count. The dataset consists of 200 prompts with various classes, numbers, and scenes.

The dataset used for the text-to-image generation task using diffusion models.

The LAION-Improved-Aesthetics (v1.2) dataset used for training the Stable Diffusion model, which includes images with captions.

The dataset used for training the Stable Diffusion model, which includes images with captions containing various terminology relevant to the field of fluvial geomorphology.

The dataset used in the paper for text-to-image generation and style transfer tasks.

The dataset is created by augmenting a single input image with masks that indicate the presence of target concepts. The masks can be provided by the user or generated...

The Elite dataset contains images with visual concepts encoded into textual embeddings.

The dataset used in this paper is a combined dataset of the TI dataset of 5 concepts, and the dataset from DreamBooth with 20 concepts.