76 datasets found

Text-to-image diffusion models with an ensemble of expert denoisers.

The dataset used for training the diffusion model, containing 2M images.

The image-only stickers dataset used for testing the kNN-Diffusion model.

The dataset used for training the kNN-Diffusion model, which consists of a large-scale retrieval method for training a text-to-image model without any text data.

The ABC-6K dataset includes prompts with at least two color words modifying different objects.

The DVMP dataset features a diverse set of objects and diverse modifiers including colors, textures, etc.

The AnE dataset comprises three benchmarks: Animal-Animal, Animal-Object, and Object-Object.

Text-to-image generative models can generate high-quality humans, but realism is lost when generating hands. Common artifacts include irregular hand poses, shapes, in-correct...

A benchmark dataset for text-grounded object generation in real images

The dataset used in the paper for testing the TextCraftor model.

The dataset used in the paper for training and testing the TextCraftor model.

TextCraftor is a stable and powerful framework to fine-tune the pre-trained text encoder to improve the text-to-image generation.

The dataset used in the paper is not explicitly described, but it is mentioned that the authors used Stable Diffusion and Yolo to optimize the parameters and prompts for...

A large dataset of text-to-image prompts for training and evaluation

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...

MUSE is a text-to-image generation model that uses masked generative transformers.

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