-
eDiff-I: Text-to-image diffusion models with an ensemble of expert denoisers
Text-to-image diffusion models with an ensemble of expert denoisers. -
Stickers Dataset
The image-only stickers dataset used for testing the kNN-Diffusion model. -
Public Multimodal Dataset
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. -
ABC-6K dataset
The ABC-6K dataset includes prompts with at least two color words modifying different objects. -
DVMP dataset
The DVMP dataset features a diverse set of objects and diverse modifiers including colors, textures, etc. -
AnE dataset
The AnE dataset comprises three benchmarks: Animal-Animal, Animal-Object, and Object-Object. -
HanDiffuser: Text-to-Image Generation With Realistic Hand Appearances
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... -
Benchmark Dataset for Text-Grounded Object Generation in Real Images
A benchmark dataset for text-grounded object generation in real images -
Parti-Prompts
The dataset used in the paper for testing the TextCraftor model. -
OpenPrompt1
The dataset used in the paper for training and testing the TextCraftor model. -
TextCraftor: Your Text Encoder Can be Image Quality Controller
TextCraftor is a stable and powerful framework to fine-tune the pre-trained text encoder to improve the text-to-image generation. -
GreenStableYolo
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... -
Pick-a-Pic
A large dataset of text-to-image prompts for training and evaluation -
LAION-Improved-Aesthetics (v1.2)
The LAION-Improved-Aesthetics (v1.2) dataset used for training the Stable Diffusion model, which includes images with captions. -
Stable Rivers
The dataset used for training the Stable Diffusion model, which includes images with captions containing various terminology relevant to the field of fluvial geomorphology. -
Stable Diffusion Prompts
The dataset used in the paper for text-to-image generation and style transfer tasks. -
Break-A-Scene: Extracting Multiple Concepts from a Single Image
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: Text-to-Image Generation via Masked Generative Transformers
MUSE is a text-to-image generation model that uses masked generative transformers. -
Elite dataset
The Elite dataset contains images with visual concepts encoded into textual embeddings.
