127 datasets found

The dataset used for the Text-to-360-Panoramas task, which consists of 360-degree panoramic images generated using diffusion models.

Diffusion by Maximum Entropy IRL (DxMI) is an IRL approach for training a diffusion model and an energy-based model.

StyleAligned is a method for generating style-consistent images using a reference style image.

Score-based generative models (SGMs) show the state-of-the-art sampling quality and diversity. However, their training/sampling complexity is notoriously high due to the highly...

Graph representation learning using directional diffusion models

The proposed method for Multi-View Virtual Try-On (MV-VTON) task, which aims at using the frontal and back clothing to reconstruct the dressing results of a person from multiple...

Diffusion Hyperfeatures: Searching Through Time and Space for Semantic Correspondence

The dataset used in the paper for Bespoke Non-Stationary (BNS) solvers for fast sampling of diffusion and flow models.

The SynthBuster dataset is a collection of images generated by various diffusion models.

Diffusion models have recently emerged as the state-of-the-art of generative modeling, demonstrating remarkable results in image synthesis and across other modalities.

The proposed StableVSR is built upon a pre-trained Latent Diffusion Model (LDM) for single image super-resolution (SISR). We use Stable Diffusion ×4 Upscaler (SD×4Upscaler)2. It...

The proposed StableVSR is built upon a pre-trained Latent Diffusion Model (LDM) for single image super-resolution (SISR). We use Stable Diffusion ×4 Upscaler (SD×4Upscaler)2. It...

Generative Manufacturing Systems (GMS) dataset, using diffusion models and ChatGPT for implicit learning from envisioned futures.

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

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.

LION: Latent Point Diffusion Models for 3D Shape Generation

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

The dataset used in the TextMesh paper, containing 35 text prompts for 3D mesh generation.

The DiffuseStyleGesture+ entry to the GENEA Challenge 2023

Videofusion: Decomposed diffusion models for high-quality video generation.