{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/melfusion-synthesizing-music-from-image-and","title":"MeLFusion: Synthesizing Music from Image and Language Cues using Diffusion Models","arxiv_id":"2406.04673","date":"2024-06-07","proceeding":"CVPR 2024 1","authors":["Sanjoy Chowdhury","Sayan Nag","K J Joseph","Balaji Vasan Srinivasan","Dinesh Manocha"],"abstract":"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.","url_abs":"https://arxiv.org/abs/2406.04673v1","url_pdf":"https://arxiv.org/pdf/2406.04673v1.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"melfusion-synthesizing-music-from-image-and","repo_url":"https://github.com/schowdhury671/melfusion","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"jax","reach":{"status":"ok"}}],"tasks":[{"task_slug":"fad","task_name":"FAD"},{"task_slug":"text-to-music-generation","task_name":"Text-to-Music Generation"}],"methods":[{"method_slug":"diffusion","method_name":"Diffusion"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/text-to-music-generation-on-musiccaps","task":"Text-to-Music Generation","dataset":"MusicCaps","model":"MeLFusion (image-conditioned)","rank_in_archive_order":1,"of":21,"metrics":{"FAD":"1.12","FD":"22.65","KL_passt":"0.89"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2406.04673","atlas_url":"https://app.syntology.ai/?focus=2406.04673","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.04673"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-25T09:33:49+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/schowdhury671/melfusion","reach":{"status":"ok"}}],"summary":{"ran_draft_wrong":2,"ran_violates":2,"ran":6,"ran_honours":1,"ran_fixture":1},"by_repo_kind":{"official":{"samples":12,"ran":12,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"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"},"n_pointer_only_for_licence":12,"samples":[{"code_sha256_prefix":"9fcdaa6e423e8aa7","entry":"Normalize","repo":"schowdhury671/melfusion","repo_kind":"official","path":"audioldm/variational_autoencoder/modules.py","file_url":"https://github.com/schowdhury671/melfusion/blob/HEAD/audioldm/variational_autoencoder/modules.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"9fcdaa6e423e8aa7"}},{"code_sha256_prefix":"4cb732f513d69dfd","entry":"disabled_train","repo":"schowdhury671/melfusion","repo_kind":"official","path":"audioldm/ldm.py","file_url":"https://github.com/schowdhury671/melfusion/blob/HEAD/audioldm/ldm.py","link_basis":"harvester_set","language":"python","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"4cb732f513d69dfd"}},{"code_sha256_prefix":"608e364a9d2376a3","entry":"exists","repo":"schowdhury671/melfusion","repo_kind":"official","path":"audioldm/utils.py","file_url":"https://github.com/schowdhury671/melfusion/blob/HEAD/audioldm/utils.py","link_basis":"harvester_set","language":"python","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"608e364a9d2376a3"}},{"code_sha256_prefix":"33e4f7a8bf80ee3a","entry":"get_bit_depth","repo":"schowdhury671/melfusion","repo_kind":"official","path":"audioldm/utils.py","file_url":"https://github.com/schowdhury671/melfusion/blob/HEAD/audioldm/utils.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"33e4f7a8bf80ee3a"}},{"code_sha256_prefix":"159fc130dc64d332","entry":"get_duration","repo":"schowdhury671/melfusion","repo_kind":"official","path":"audioldm/utils.py","file_url":"https://github.com/schowdhury671/melfusion/blob/HEAD/audioldm/utils.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"159fc130dc64d332"}},{"code_sha256_prefix":"1586badee8c8ddb7","entry":"get_image_latents","repo":"schowdhury671/melfusion","repo_kind":"official","path":"models.py","file_url":"https://github.com/schowdhury671/melfusion/blob/HEAD/models.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"1586badee8c8ddb7"}},{"code_sha256_prefix":"a26f85d7c72ef39a","entry":"get_padding","repo":"schowdhury671/melfusion","repo_kind":"official","path":"audioldm/hifigan/models.py","file_url":"https://github.com/schowdhury671/melfusion/blob/HEAD/audioldm/hifigan/models.py","link_basis":"harvester_set","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"a26f85d7c72ef39a"}},{"code_sha256_prefix":"cb49209c125de1b4","entry":"get_timestep_embedding","repo":"schowdhury671/melfusion","repo_kind":"official","path":"audioldm/variational_autoencoder/modules.py","file_url":"https://github.com/schowdhury671/melfusion/blob/HEAD/audioldm/variational_autoencoder/modules.py","link_basis":"harvester_set","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"cb49209c125de1b4"}},{"code_sha256_prefix":"bb989094ba0ffe5f","entry":"load_model","repo":"schowdhury671/melfusion","repo_kind":"official","path":"models.py","file_url":"https://github.com/schowdhury671/melfusion/blob/HEAD/models.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"bb989094ba0ffe5f"}},{"code_sha256_prefix":"409a71c470a245cd","entry":"make_batch_for_text_to_audio","repo":"schowdhury671/melfusion","repo_kind":"official","path":"audioldm/pipeline.py","file_url":"https://github.com/schowdhury671/melfusion/blob/HEAD/audioldm/pipeline.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"409a71c470a245cd"}},{"code_sha256_prefix":"3137073275f8c21a","entry":"nonlinearity","repo":"schowdhury671/melfusion","repo_kind":"official","path":"audioldm/variational_autoencoder/modules.py","file_url":"https://github.com/schowdhury671/melfusion/blob/HEAD/audioldm/variational_autoencoder/modules.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"3137073275f8c21a"}},{"code_sha256_prefix":"444fd0303f1aff5a","entry":"round_up_duration","repo":"schowdhury671/melfusion","repo_kind":"official","path":"audioldm/pipeline.py","file_url":"https://github.com/schowdhury671/melfusion/blob/HEAD/audioldm/pipeline.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"444fd0303f1aff5a"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}