This is an unmodified mirror hosted for reliable download by the LocalMusic app. Original files, checksums untouched; mirrored 2026-08-25.

All credit belongs to the original authors. If you are an author and want this mirror changed or removed, open a discussion on this repo.

language:

We propose SongBloom, a novel framework for full-length song generation that leverages an interleaved paradigm of autoregressive sketching and diffusion-based refinement. SongBloom employs an autoregressive diffusion model that combines the high fidelity of diffusion models with the scalability of language models. Specifically, it gradually extends a musical sketch from short to long and refines the details from coarse to fine-grained. The interleaved generation paradigm effectively integrates prior semantic and acoustic context to guide the generation process. Experimental results demonstrate that SongBloom outperforms existing methods across both subjective and objective metrics and achieves performance comparable to the state-of-the-art commercial music generation platforms.

A .jsonl file, where each line is a json object:

One example can be refered to as: example/test.jsonl

The prompt wav should be a 10-second, 48kHz audio clip.

The details about lyric format can be found in docs/lyric_format.md.

@article{yang2025songbloom,
title={SongBloom: Coherent Song Generation via Interleaved Autoregressive Sketching and Diffusion Refinement},
author={Yang, Chenyu and Wang, Shuai and Chen, Hangting and Tan, Wei and Yu, Jianwei and Li, Haizhou},
journal={arXiv preprint arXiv:2506.07634},
year={2025}
}