HyperAI초신경

홈 뉴스 최신 연구 논문 튜토리얼 데이터셋 백과사전 SOTA LLM 모델 GPU 랭킹 컨퍼런스

한국어

HyperAI초신경

Image Generation On Celeba Hq 256X256

평가 지표

FID

평가 결과

이 벤치마크에서 각 모델의 성능 결과

모델 이름	FID	Paper Title	Repository
LFM	5.26	Flow Matching in Latent Space
DC-VAE	15.81	Dual Contradistinctive Generative Autoencoder	-
UNCSN++ (RVE) + ST	7.16	Soft Truncation: A Universal Training Technique of Score-based Diffusion Model for High Precision Score Estimation
VAEBM	20.38	VAEBM: A Symbiosis between Variational Autoencoders and Energy-based Models
RDUOT	5.6	A High-Quality Robust Diffusion Framework for Corrupted Dataset
DDGAN	7.64	Tackling the Generative Learning Trilemma with Denoising Diffusion GANs
WaveDiff	5.94	Wavelet Diffusion Models are fast and scalable Image Generators
LDM-4	5.11	High-Resolution Image Synthesis with Latent Diffusion Models
DDMI	8.73	DDMI: Domain-Agnostic Latent Diffusion Models for Synthesizing High-Quality Implicit Neural Representations
VQGAN+Transformer	10.2	Taming Transformers for High-Resolution Image Synthesis
BOSS	-	Bellman Optimal Stepsize Straightening of Flow-Matching Models
RDM	3.15	Relay Diffusion: Unifying diffusion process across resolutions for image synthesis
Dual-MCMC EBM	15.89	Learning Energy-based Model via Dual-MCMC Teaching	-
StyleSwin	3.25	StyleSwin: Transformer-based GAN for High-resolution Image Generation
LSGM	7.22	Score-based Generative Modeling in Latent Space
Joint-EBM	9.89	Learning Joint Latent Space EBM Prior Model for Multi-layer Generator	-
RNODE	-	How to train your neural ODE: the world of Jacobian and kinetic regularization
Diffusion-JEBM	8.78	Learning Latent Space Hierarchical EBM Diffusion Models	-
GLOW	68.93	Glow: Generative Flow with Invertible 1x1 Convolutions

0 of 19 row(s) selected.