Free Reads
Sign in to view your remaining parses.
Tag Filter
Image Generation
Consistency Models
Published:3/3/2023
Consistency ModelsDiffusion ModelsImage GenerationCIFAR-10 DatasetImage Inpainting and Colorization
This paper introduces consistency models to address the slow generation speed of diffusion models, enabling fast onestep generation and multistep sampling. They also support zeroshot data editing, outperforming existing techniques on benchmarks like CIFAR10.
03
Inductive Generative Recommendation via Retrieval-based Speculation
Published:10/4/2024
Generative Recommendation SystemsTraining-Free Acceleration MethodsOnline Recommendation System OptimizationSequential Recommender SystemsImage Generation
The paper introduces , a retrievalbased inductive generative recommendation framework that addresses the limitations of generative models in recommending unseen items by utilizing a drafter model for candidate generation and a generative model for verification, enhancing
06
Scalable Diffusion Models with Transformers
Published:12/20/2022
Diffusion ModelsTransformer architectureImage GenerationScalable Diffusion ModelsClass-Conditional Image Generation
This study introduces Diffusion Transformers (DiTs), which replace UNet with a transformer architecture for image generation. Higher Gflops correlate with better performance (lower FID), with the largest model achieving stateoftheart results on ImageNet benchmarks.
07
Contrastive Test-Time Composition of Multiple LoRA Models for Image
Generation
Published:3/29/2024
Low-Rank Adaptation FinetuningImage GenerationComposition of LoRA ModelsContrastive Test-Time FusionAttention Mechanism Adjustment
CLoRA is a trainingfree testtime method that refines attention maps of multiple LoRA models to fuse semantic features, overcoming attention overlap and concept omission issues, significantly improving multiconcept image generation accuracy and quality.
011