136 datasets found

Diffusion models have achieved great success in image generation. However, when leveraging this idea for video generation, we face significant challenges in maintaining the...

The dataset used in the paper for appearance transfer with semantic correspondence in diffusion models.

Text-to-image dataset with conditional control

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

Protein structure prediction has reached revolutionary levels of accuracy on single structures, yet distributional modeling paradigms are needed to capture the conformational...

Advanced diffusion models perform impressively in image super-resolution, but the high memory and computational costs hinder their deployment. Binarization, an ultra-compression...

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

A custom dataset of approximately 4,000 pattern images from various sources on the internet, compiled for training a fine-tuned diffusion model for textile pattern generation.

Diffusion models have attracted significant attention due to the remarkable ability to create content and generate data for tasks like image classification. However, the usage...

Understanding and identifying different types of single molecules' diffusion that occur in a broad range of systems (including living matter) is extremely important, as it can...

The dataset contains images of subjects and styles, used for training and testing the FreeTuner model.

FreeTuner is a training-free method for compositional personalization that can generate any user-provided subject in any user-provided style.

A large-scale dataset for generating prompts that can be used in diffusion models for text-to-text generation tasks.

The dataset used in the paper is not explicitly described, but it is mentioned that the authors used it for data anonymization, data augmentation, and image perceptual quality...

The dataset used in the paper for text-driven image editing with diffusion models.

A perceptual quality assessment database for AI-generated images (AGIs) named AGIQA-1K, which consists of 1,080 AGIs generated from diffusion models.

Anomalous diffusion dataset, containing trajectories of molecules, cells, or animals.

Anomalous Diffusion Challenge dataset, containing single-particle trajectories of diffusive motion of molecules, cells, or animals.

PIE-Bench is a dataset for single-object editing, featuring a modified subset of the dataset with images from AFHQ, COCO, and Imagen.

The Emu Video Edit model's training dataset, containing 1600 videos with 7 editing instructions each.