Share your thoughts, 1 month free Claude Pro on usSee more

Conditional Image Generation on ImageNet 256x256 (train/val)

0.27Tok. rFID

LDM-4

Updated 1mo ago

Evaluation Results

Method	Links
LDM-4 2024.12		0.27	157.92	0.37	10.56	103.5	3.6	247.7
MAR-H 2024.12		0.61	67.93	2.08	3.83	211.2	2.54	273.6
DiT-XL 2024.12		0.61	28.81	4.51	5.83	141.3	2.93	268.5
SiT-XL 2024.12		0.61	29.23	5.39	5.35	151.2	1.86	293.6
DiT-XL/2 2024.12		0.62	80.73	0.51	9.62	121.5	2.27	278.2
SiT-XL/2 2024.12		0.62	81.92	0.54	8.3	131.7	2.06	270.3
SiT-XL/2 + REPA 2024.12		0.62	81.92	0.54	5.9	157.8	1.42	305.7
MAR-H 2024.12		0.65	86.55	0.89	2.81	218.3	1.93	289.4
DiT-XL 2024.12		0.65	28.81	4.59	6.53	131.9	3.11	268.3
SiT-XL 2024.12		0.65	29.23	5.42	5.8	143.5	1.88	287.9
DiT-XL 2024.12		0.68	14.52	8.81	9.22	115.8	3.78	266.7
SiT-XL 2024.12		0.68	14.73	10.12	7.67	133.9	2.44	308.8
DiT-XL 2024.12		0.74	14.52	8.74	9.07	117.2	3.69	270.4
SiT-XL 2024.12		0.74	14.73	10.11	7.59	137.4	2.44	310.6
DiT-XL 2024.12		0.88	28.81	4.7	6.62	129.2	3.29	262.5
SiT-XL 2024.12		0.88	29.23	5.51	5.98	138	1.78	279
DiT-XL 2024.12		0.89	14.52	8.94	9.83	113.8	3.91	264.2
SiT-XL 2024.12		0.89	14.73	10.28	7.99	129.3	2.51	301.3
MAR-H 2024.12		1.22	145.08	0.12	2.35	227.8	1.55	303.7
TiTok-S-128 2024.12		1.61	33.03	6.5	-	-	1.97	281.8
LlamaGen-3B 2024.12		2.19	781.56	2.9	-	-	3.06	279.7
MaskGIT 2024.12		2.28	-	-	6.18	182.1	-	-
RQ-Trans. 2024.12		3.2	908.91	7.85	3.8	323.7	-	-
Taming-Trans. 2024.12		7.94	-	-	5.2	290.3	-	-
MAGE 2024.12		-	-	-	6.93	195.8	-	-
U-ViT-H/2 2024.12		-	128.89	0.98	-	-	2.29	263.9
MDTv2-XL/2 2024.12		-	125.43	0.59	5.06	155.6	1.58	314.7