136 datasets found

The dataset used for training the InstructVid2Vid model, which consists of video-instruction-edited video triplets.

The dataset used in the paper is a diffusion model dataset, where the authors investigate the robustness of Tree-Ring Watermarking in the identification task.

Generating ligand molecules for specific protein targets, known as structure-based drug design, is a fundamental problem in therapeutics development and biological discovery.

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 DPoser dataset is used for human pose prior modeling, leveraging diffusion models.

Crowd counting is a key aspect of crowd analysis and has been typically accomplished by estimating a crowd-density map and summing over the density values.

Large-scale graphs with node attributes are increasingly common in various real-world applications. Creating synthetic, attribute-rich graphs that mirror real-world examples is...

The CATCH dataset is used to test the proposed Style-Extracting Diffusion Models (STEDM) for canine cancer histology image segmentation.

The HER2 dataset is used to test the proposed Style-Extracting Diffusion Models (STEDM) for histopathology image segmentation.

Diffusion-based graph generative models have recently obtained promising results for graph generation. However, existing diffusion-based graph generative models are mostly...

DiffDock: Diffusion steps, twists, and turns for molecular docking.

Coarse-grained (CG) molecular dynamics enables the study of biological processes at temporal and spatial scales that would be intractable at an atomistic resolution.

The dataset used in the paper is not explicitly described, but it is mentioned that the authors collect 3K videos (60-90 seconds long) from the internet to train their model.

Protein structures generated by Genie, a novel DDPM for de novo protein design

The dataset used in the paper is DPM-Solver++

The dataset used in the paper is not explicitly described, but it is mentioned that the authors used a pre-trained model to generate images.

Mix-of-Show: Decentralized low-rank adaptation for multi-concept customization of diffusion models.

Customized generation using diffusion models has made impressive progress in image generation, but remains un-satisfactory in the challenging video generation task, as it...

A text-to-image diffusion model trained on a recaptioned dataset to improve image generation quality and semantic alignment.