Papers › MeLFusion: Synthesizing Music from Image and Language Cues using Diffusion Models

MeLFusion: Synthesizing Music from Image and Language Cues using Diffusion Models

7 Jun 2024CVPR 2024 1arXiv:2406.04673archive 2025-07-28

Sanjoy Chowdhury, Sayan Nag, K J Joseph, Balaji Vasan Srinivasan, Dinesh Manocha

Music is a universal language that can communicate emotions and feelings. It forms an essential part of the whole spectrum of creative media, ranging from movies to social media posts. Machine learning models that can synthesize music are predominantly conditioned on textual descriptions of it. Inspired by how musicians compose music not just from a movie script, but also through visualizations, we propose MeLFusion, a model that can effectively use cues from a textual description and the corresponding image to synthesize music. MeLFusion is a text-to-music diffusion model with a novel "visual synapse", which effectively infuses the semantics from the visual modality into the generated music. To facilitate research in this area, we introduce a new dataset MeLBench, and propose a new evaluation metric IMSM. Our exhaustive experimental evaluation suggests that adding visual information to the music synthesis pipeline significantly improves the quality of generated music, measured both objectively and subjectively, with a relative gain of up to 67.98% on the FAD score. We hope that our work will gather attention to this pragmatic, yet relatively under-explored research area.

PaperPDFConference PDFCodeCode Syntology ran

In Syntology View this paper on Syntology: its repositories, every harvested function with whether it ran, its licence and the call to fetch it.

Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

For agents, Syntology's MCP tool lists every function and class Syntology harvested from this paper and whether it ran (how to connect): get_harvested_code_for_paper(arxiv_id="2406.04673")

Code

Syntology Ran 12 of 12 code samples harvested from 1 repository linked to this paper; 0 have no recorded run. Of those that ran: 1 ran · honoured contract; 2 ran · violated contract; 2 ran · our draft was wrong; 1 ran · fixture could not drive it; 6 ran with no contract checked.

By repository: official repository: 12 samples from 1 repository, 12 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

12 samples harvested; 12 ran; 1 honoured the contract we drafted; 0 have no recorded run. Read from Syntology's graph 2026-09-25; that is when this build read the record, not when the samples ran.

1ran · honoured contract
2ran · violated contract
2ran · our draft was wrong
1ran · fixture could not drive it
6ran

Licence: 12 of the 12 samples are pointer only, meaning Syntology does not serve that copy's text. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from schowdhury671/melfusion. “Ran” means the sample executed on a synthesized input. It does not mean the output is correct, and nothing here reproduces the paper's results. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself; “our draft was wrong” and “fixture could not drive it” are failures of Syntology's instrument, not of the code.

Each sample ends with its code_sha256, Syntology's identity for that exact code. An agent fetches the stored sample with Syntology's MCP tool get_code(code_sha256="…") (how to connect); click an identity to copy that call.

Repository labels, per sample. official repository: The archive marks this repository official for the paper. named in the paper: The archive records that the paper mentions this repository; it is not marked official. community (archive-listed): In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper. found in paper text by Syntology: Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted. community: Not in the archive's code links for this paper; a community repository Syntology harvested. Samples from a repository marked official are listed first. Licence labels name the repository's licence as recorded at harvest. “Pointer only” means Syntology does not serve that copy's text, for one of four reasons: no licence file was found; the licence was not identified; the licence is recorded as permissive but that copy's record is not marked cleared; or the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar). Some licences outside that list permit redistribution, such as WTFPL, and GPL-3.0 under its conditions; they are simply not on the list. Hover a licence label for the reason. File links open the file on GitHub at the default branch, which may have changed since the harvest.

Normalize schowdhury671/melfusion/audioldm/variational_autoencoder/modules.py official repository ran · our draft was wrong no licence file found · pointer only · 9fcdaa6e423e8aa7 · report
disabled_train schowdhury671/melfusion/audioldm/ldm.py official repository ran · violated contract no licence file found · pointer only · 4cb732f513d69dfd · report
exists schowdhury671/melfusion/audioldm/utils.py official repository ran · violated contract fingerprinted no licence file found · pointer only · 608e364a9d2376a3 · report
get_bit_depth schowdhury671/melfusion/audioldm/utils.py official repository ran no licence file found · pointer only · 33e4f7a8bf80ee3a · report
get_duration schowdhury671/melfusion/audioldm/utils.py official repository ran no licence file found · pointer only · 159fc130dc64d332 · report
get_image_latents schowdhury671/melfusion/models.py official repository ran no licence file found · pointer only · 1586badee8c8ddb7 · report
get_padding schowdhury671/melfusion/audioldm/hifigan/models.py official repository ran · honoured contract fingerprinted no licence file found · pointer only · a26f85d7c72ef39a · report
get_timestep_embedding schowdhury671/melfusion/audioldm/variational_autoencoder/modules.py official repository ran · fixture could not drive it no licence file found · pointer only · cb49209c125de1b4 · report
load_model schowdhury671/melfusion/models.py official repository ran no licence file found · pointer only · bb989094ba0ffe5f · report
make_batch_for_text_to_audio schowdhury671/melfusion/audioldm/pipeline.py official repository ran no licence file found · pointer only · 409a71c470a245cd · report
nonlinearity schowdhury671/melfusion/audioldm/variational_autoencoder/modules.py official repository ran · our draft was wrong fingerprinted no licence file found · pointer only · 3137073275f8c21a · report
round_up_duration schowdhury671/melfusion/audioldm/pipeline.py official repository ran fingerprinted no licence file found · pointer only · 444fd0303f1aff5a · report

Tasks

FADText-to-Music Generation

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Text-to-Music Generation MusicCaps MeLFusion (image-conditioned) FAD 1.12 #1 of 21 Archive leaderboard report
Text-to-Music Generation MusicCaps MeLFusion (image-conditioned) FD 22.65 #1 of 21 Archive leaderboard report
Text-to-Music Generation MusicCaps MeLFusion (image-conditioned) KL_passt 0.89 #1 of 21 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Methods

Diffusion

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections