Image Generation On Imagenet 512X512

评估指标

FID

Inception score

评测结果

各个模型在此基准测试上的表现结果

			Paper Title	Repository
ADM-G	7.72	172.71	Diffusion Models Beat GANs on Image Synthesis
MaskGIT	7.32	156.0	MaskGIT: Masked Generative Image Transformer
simple diffusion (U-ViT, L)	4.53	205.3	Simple diffusion: End-to-end diffusion for high resolution images
MaskGIT (a=0.05)	4.46	342.0	MaskGIT: Masked Generative Image Transformer
simple diffusion (U-Net)	4.28	171	Simple diffusion: End-to-end diffusion for high resolution images
ADM-G, ADM-U	3.85	221.72	Diffusion Models Beat GANs on Image Synthesis
Poly-INR	3.81	-	Polynomial Implicit Neural Representations For Large Diverse Datasets
Latent Diffusion (LDM-4-G)	3.60	247.67	High-Resolution Image Synthesis with Latent Diffusion Models
DPC-U	3.54	350.2	Discrete Predictor-Corrector Diffusion Models for Image Synthesis	-
SiD-EDM2-XS (125M)	3.353	-	Adversarial Score identity Distillation: Rapidly Surpassing the Teacher in One Step
MAGVIT-v2 (w/o guidance)	3.07	213.1	Language Model Beats Diffusion -- Tokenizer is Key to Visual Generation
DiT-XL/2	3.04	240.82	Scalable Diffusion Models with Transformers
GIVT-Causal-L+A	2.92	-	GIVT: Generative Infinite-Vocabulary Transformers
EDM2-XS	2.91	-	Analyzing and Improving the Training Dynamics of Diffusion Models
DiMR-XL/3R	2.89	-	Alleviating Distortion in Image Generation via Multi-Resolution Diffusion Models
DiT-XL/2 with SA-Solver	2.80	-	SA-Solver: Stochastic Adams Solver for Fast Sampling of Diffusion Models
SiD-EDM2-S (280M)	2.707	-	Adversarial Score identity Distillation: Rapidly Surpassing the Teacher in One Step
DiffiT	2.67	252.12	DiffiT: Diffusion Vision Transformers for Image Generation
TiTok-L-64	2.49	-	An Image is Worth 32 Tokens for Reconstruction and Generation
StyleGAN-XL	2.40	-	StyleGAN-XL: Scaling StyleGAN to Large Diverse Datasets

0 of 48 row(s) selected.