76 datasets found

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.

The FFHQ dataset is a large dataset of high-quality face images with 1024 × 1024 resolution with variations in age, gender, and glasses.

The authors present a photorealistic text-to-image diffusion model with deep language understanding.

The dataset used in this paper for text-to-image generation tasks.

The dataset used in the paper is a text-to-image diffusion model, which is a type of generative model that can generate images from text prompts.

Key-locked rank one editing for text-to-image personalization.

The dataset used in this paper for testing the effectiveness of the disguise generation algorithm.

Textual Inversion: An image is worth one word: Personalizing text-to-image generation using textual inversion.

CatVersion allows users to learn the personalized concept through a handful of examples and then utilize text prompts to generate images that embody the personalized concept.

FlashEval: Towards Fast and Accurate Evaluation of Text-to-image Diffusion Generative Models

The dataset used in the paper is LAION-2B, which is a large-scale image-text dataset. The authors fine-tune a pre-trained diffusion model with a subset of LAION-2B with 10k...

The ImageReward dataset is a large-scale dataset for evaluating human preferences in text-to-image generation.

The Multi-dimensional Human Preference (MHP) dataset is a large-scale dataset for evaluating text-to-image models from multi-dimensional human preferences.

The CustomConcept101 dataset is a dataset of 101 concepts across 16 broader categories, used for evaluating personalization approaches in text-to-image diffusion models.

The dataset used in this paper is DreamBench, which contains 30 different subject images including backpacks, sneakers, boots, cats, dogs, and toy, etc.

Text-to-image generative models have recently attracted considerable interest, enabling the synthesis of high-quality images from textual prompts. However, these models often...

Learning from human feedback has been shown to improve text-to-image models. These techniques first learn a reward function that captures what humans care about in the task and...

The Caltech-256 object category dataset is used for the feature extraction step, and the Omniglot dataset is used for the evaluation.

ConceptLab: Creative Concept Generation using VLM-Guided Diffusion Prior Constraints

The dataset used in this study consists of a large language model (LLM) enabled platform - ChatGPT.