Startseite Plattform Dokumentation Neuigkeiten Forschungsarbeiten Tutorials Datensätze Wiki SOTA LLM-Modelle GPU-Rangliste Veranstaltungen

Deutsch

Image Generation On Celeba Hq 256X256

Metriken

FID

Ergebnisse

Leistungsergebnisse verschiedener Modelle zu diesem Benchmark

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

0 of 19 row(s) selected.