Text-to-Music Generation on MusicCaps

Metric: KL_passt (higher is better)

LeaderboardDataset

Loading chart...

Results

Sort:

#	Model↕	KL_passt▼	Extra Data	Paper	Date↕	Code
1	UniAudio	1.87	No	-	-	Code
2	AudioLDM2-music	1.53	No	AudioLDM 2: Learning Holistic Audio Generation w...	2023-08-10	Code
3	Stable Audio Open	1.32	No	Stable Audio Open	2024-07-19	Code
4	OpenMusic (QA-MDT)	1.31	No	Quality-aware Masked Diffusion Transformer for E...	2024-05-24	Code
5	MusicGen w/o melody (3.3B)	1.31	No	Simple and Controllable Music Generation	2023-06-08	Code
6	MusicGen w/ random melody (1.5B)	1.31	No	Simple and Controllable Music Generation	2023-06-08	Code
7	JEN-1	1.29	No	JEN-1: Text-Guided Universal Music Generation wi...	2023-08-09	Code
8	FLUXMusic	1.25	No	FLUX that Plays Music	2024-09-01	Code
9	MusicGen w/o melody (1.5B)	1.23	No	Simple and Controllable Music Generation	2023-06-08	Code
10	AudioLDM 2-Full	1.2	No	AudioLDM 2: Learning Holistic Audio Generation w...	2023-08-10	Code
11	AudioLDM2-large	1	No	AudioLDM 2: Learning Holistic Audio Generation w...	2023-08-10	Code
12	TANGO-AF	0.94	No	Improving Text-To-Audio Models with Synthetic Ca...	2024-06-18	Code
13	MeLFusion (image-conditioned)	0.89	No	MeLFusion: Synthesizing Music from Image and Lan...	2024-06-07	Code
14	ETTA	0.84	No	ETTA: Elucidating the Design Space of Text-to-Au...	2024-12-26	Code
15	Stable Audio	0.8	No	Fast Timing-Conditioned Latent Audio Diffusion	2024-02-07	Code

#1UniAudio
1.87
KL_passt
No paperCode
#2AudioLDM2-musicSOTA
1.53
KL_passt· 2023-08-10
AudioLDM 2: Learning Holistic Audio Generation with Self-supervised Pretraining Code
#3Stable Audio Open
1.32
KL_passt· 2024-07-19
Stable Audio Open Code
#4OpenMusic (QA-MDT)
1.31
KL_passt· 2024-05-24
Quality-aware Masked Diffusion Transformer for Enhanced Music Generation Code
#5MusicGen w/o melody (3.3B)SOTA
1.31
KL_passt· 2023-06-08
Simple and Controllable Music Generation Code
#6MusicGen w/ random melody (1.5B)
1.31
KL_passt· 2023-06-08
Simple and Controllable Music Generation Code
#7JEN-1
1.29
KL_passt· 2023-08-09
JEN-1: Text-Guided Universal Music Generation with Omnidirectional Diffusion Models Code
#8FLUXMusic
1.25
KL_passt· 2024-09-01
FLUX that Plays Music Code
#9MusicGen w/o melody (1.5B)
1.23
KL_passt· 2023-06-08
Simple and Controllable Music Generation Code
#10AudioLDM 2-Full
1.2
KL_passt· 2023-08-10
AudioLDM 2: Learning Holistic Audio Generation with Self-supervised Pretraining Code
#11AudioLDM2-large
1
KL_passt· 2023-08-10
AudioLDM 2: Learning Holistic Audio Generation with Self-supervised Pretraining Code
#12TANGO-AF
0.94
KL_passt· 2024-06-18
Improving Text-To-Audio Models with Synthetic Captions Code
#13MeLFusion (image-conditioned)
0.89
KL_passt· 2024-06-07
MeLFusion: Synthesizing Music from Image and Language Cues using Diffusion Models Code
#14ETTA
0.84
KL_passt· 2024-12-26
ETTA: Elucidating the Design Space of Text-to-Audio Models Code
#15Stable Audio
0.8
KL_passt· 2024-02-07
Fast Timing-Conditioned Latent Audio Diffusion Code