SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2406.04673 · CVPR · 2024

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

Dinesh Manocha, Balaji Srinivasan, Sanjoy Chowdhury, Sayan Nag, † Joseph

arXiv · PDF · Open in the Atlas

Code that ran

We lifted 12 functions out of this paper's own repositories and ran 12 of them in a sandbox. "Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results.

RepositoryRoleRan
schowdhury671/melfusion canonical 12 of 12
FunctionStatusWhere it lives
Normalize Ran schowdhury671/melfusion/audioldm/variational_autoencoder/modules.py
pointer only (licence: NONE) · get_code("9fcdaa6e423e8aa7")
disabled_train Ran schowdhury671/melfusion/audioldm/ldm.py
pointer only (licence: NONE) · get_code("4cb732f513d69dfd")
exists Ran schowdhury671/melfusion/audioldm/utils.py
pointer only (licence: NONE) · get_code("608e364a9d2376a3")
get_bit_depth Ran schowdhury671/melfusion/audioldm/utils.py
pointer only (licence: NONE) · get_code("33e4f7a8bf80ee3a")
get_duration Ran schowdhury671/melfusion/audioldm/utils.py
pointer only (licence: NONE) · get_code("159fc130dc64d332")
get_image_latents Ran schowdhury671/melfusion/models.py
pointer only (licence: NONE) · get_code("1586badee8c8ddb7")
get_padding Ran schowdhury671/melfusion/audioldm/hifigan/models.py
pointer only (licence: NONE) · get_code("a26f85d7c72ef39a")
get_timestep_embedding Ran schowdhury671/melfusion/audioldm/variational_autoencoder/modules.py
pointer only (licence: NONE) · get_code("cb49209c125de1b4")
load_model Ran schowdhury671/melfusion/models.py
pointer only (licence: NONE) · get_code("bb989094ba0ffe5f")
make_batch_for_text_to_audio Ran schowdhury671/melfusion/audioldm/pipeline.py
pointer only (licence: NONE) · get_code("409a71c470a245cd")
nonlinearity Ran schowdhury671/melfusion/audioldm/variational_autoencoder/modules.py
pointer only (licence: NONE) · get_code("3137073275f8c21a")
round_up_duration Ran schowdhury671/melfusion/audioldm/pipeline.py
pointer only (licence: NONE) · get_code("444fd0303f1aff5a")

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

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.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2406.04673")
get_code_for_paper("2406.04673")
have("2406.04673")

Connect an agent — have() is free.