Dataset - LDM

Extended MusicCaps

Extended MusicCaps is a music caption dataset that is extended to include images.
- Dataset
- JSON
MeLBench

MeLBench is a new dataset containing 11,250 manually annotated triplets of ⟨Image, Text, Music⟩.
- Dataset
- JSON
MELFUSION: Synthesizing Music from Image and Language Cues using Diffusion Mo...

MELFUSION is a text-to-music diffusion model that can synthesize music conditioned on both visual and textual modality.
- Dataset
- JSON

You can also access this registry using the API (see API Docs).

3 datasets found