-
Emu: Enhancing Image Generation Models Using Photogenic Needles in a Haystack
Training text-to-image models with web scale image-text pairs enables the generation of a wide range of visual concepts from text. However, these pre-trained models often face... -
ODIN: On-demand Data Formulation to Mitigate Dataset Lock-in
ODIN is an innovative approach that addresses the problem of dataset constraints by integrating generative AI models. -
Directly Denosing Diffusion Models
Directly Denoising Diffusion Models: a simple and generic approach for generating realistic images with few-step sampling, while multistep sampling is still preserved for better... -
SD-DiT: Unleashing the Power of Self-supervised Discrimination in Diffusion T...
Diffusion Transformer (DiT) has emerged as the new trend of generative diffusion models on image generation. In view of extremely slow convergence in typical DiT, recent... -
Stable Diffusion safety filter dataset
The dataset used in the paper is the Stable Diffusion safety filter dataset, which contains images that are generated using the Stable Diffusion model and are classified as safe... -
CelebA-HQ-FI and CelebA-25000
The dataset used in the paper is the CelebA-HQ-FI and CelebA-25000 datasets. -
Unsupervised Image-to-Image Translation Networks
Unsupervised image-to-image translation networks. -
Portrait Diffusion: Training-free Face Stylization with Chain-of-Painting
Face stylization refers to the transformation of a face into a specific portrait style. However, current methods require the use of example-based adaptation approaches to... -
SD architecture
A dataset used for experiments with LoRA-enhanced distillation on guided diffusion models -
LAION-Aesthetic
The dataset used in the paper is LAION-Aesthetic, a large-scale image dataset. -
Diffusion by Maximum Entropy IRL
Diffusion by Maximum Entropy IRL (DxMI) is an IRL approach for training a diffusion model and an energy-based model. -
Style Aligned Image Generation
StyleAligned is a method for generating style-consistent images using a reference style image. -
Concept Sliders Test Dataset
The dataset used for testing the Concept Sliders, consisting of paired image data and text prompts. -
Concept Sliders Dataset
The dataset used for training the Concept Sliders, consisting of paired image data and text prompts. -
Photorealistic text-to-image diffusion models with deep language understanding
The authors present a photorealistic text-to-image diffusion model with deep language understanding. -
GIU-GANs:Global Information Utilization for Generative Adversarial Networks
Recently, with the rapid development of artificial intelligence, image generation based on deep learning has advanced significantly. Image generation based on Generative... -
SynthBuster dataset
The SynthBuster dataset is a collection of images generated by various diffusion models. -
SC-VAE: Sparse Coding-based Variational Autoencoder with Learned ISTA
Learning rich data representations from unlabeled data is a key challenge towards applying deep learning algorithms in downstream tasks. The proposed method learns sparse data...
