Text-to-Image Generation on COCO (Common Objects in Context)

Metric: Inception score (higher is better)

LeaderboardDataset

Loading chart...

Results

Hide extra data

#	Model↕	Inception score▼	Extra Data	Paper	Date↕	Code
1	FuseDream (k=10, 256)	34.67	No	FuseDream: Training-Free Text-to-Image Generatio...	2021-12-02	Code
2	FuseDream (few-shot, k=5)	34.26	No	FuseDream: Training-Free Text-to-Image Generatio...	2021-12-02	Code
3	FuseDream (k=5, 256)	34.26	No	FuseDream: Training-Free Text-to-Image Generatio...	2021-12-02	Code
4	DM-GAN+CL	33.34	No	Improving Text-to-Image Synthesis Using Contrast...	2021-07-06	Code
5	DM-GAN + VICTR	32.37	No	VICTR: Visual Information Captured Text Represen...	2020-10-07	Code
6	Lafite	32.34	No	LAFITE: Towards Language-Free Training for Text-...	2021-11-27	Code
7	DM-GAN (256 x 256)	32.2	No	NÜWA: Visual Synthesis Pre-training for Neural v...	2021-11-24	Code
8	Swinv2-Imagen	31.46	Yes	Swinv2-Imagen: Hierarchical Vision Transformer D...	2022-10-18	-
9	XMC-GAN (256 x 256)	30.5	No	NÜWA: Visual Synthesis Pre-training for Neural v...	2021-11-24	Code
10	DM-GAN	30.49	No	DM-GAN: Dynamic Memory Generative Adversarial Ne...	2019-04-02	Code
11	AttnGAN + VICTR	28.18	No	VICTR: Visual Information Captured Text Represen...	2020-10-07	Code
12	OP-GAN	27.88	No	Semantic Object Accuracy for Generative Text-to-...	2019-10-29	Code
13	NÜWA (256 x 256)	27.2	No	NÜWA: Visual Synthesis Pre-training for Neural v...	2021-11-24	Code
14	Lafite (zero-shot)	26.02	No	LAFITE: Towards Language-Free Training for Text-...	2021-11-27	Code
15	AttnGAN+CL	25.7	No	Improving Text-to-Image Synthesis Using Contrast...	2021-07-06	Code
16	AttnGAN + OP	24.76	No	Generating Multiple Objects at Spatially Distinc...	2019-01-03	Code
17	AttnGAN (256 x 256)	23.3	No	NÜWA: Visual Synthesis Pre-training for Neural v...	2021-11-24	Code
18	DF-GAN (256 x 256)	18.7	No	NÜWA: Visual Synthesis Pre-training for Neural v...	2021-11-24	Code
19	CogView	18.2	Yes	CogView: Mastering Text-to-Image Generation via ...	2021-05-26	Code
20	CogView (256 x 256)	18.2	No	NÜWA: Visual Synthesis Pre-training for Neural v...	2021-11-24	Code
21	DALL-E (256 x 256)	17.9	No	NÜWA: Visual Synthesis Pre-training for Neural v...	2021-11-24	Code
22	StackGAN + OP	12.12	No	Generating Multiple Objects at Spatially Distinc...	2019-01-03	Code
23	StackGAN + VICTR	10.38	No	VICTR: Visual Information Captured Text Represen...	2020-10-07	Code
24	ChatPainter	9.74	No	ChatPainter: Improving Text to Image Generation ...	2018-02-22	-
25	StackGAN-v1	8.45	No	StackGAN++: Realistic Image Synthesis with Stack...	2017-10-19	Code