arXivDaily arXiv每日学术速递 周一至周五更新
北美退伍军人节(Veterans Day),12 日无更新
arXiv 2409.00587cs.SDcs.CVeess.AS
收藏

演奏音乐的FLUX

FLUX that Plays Music

Kunlun Inc.(昆仑公司)

Zhengcong Fei, Mingyuan Fan, Changqian Yu, Junshi Huang

AI总结:

本文提出FluxMusic,将基于扩散的整流流Transformer扩展至文本到音乐生成,通过优化架构和双重流处理机制,显著优于已有扩散方法。

摘要:

本文探索了基于扩散的整流流Transformer在文本到音乐生成中的一个简单扩展,称为FluxMusic。通常,伴随先进的Flux模型的设计,我们将其迁移到mel频谱的潜在VAE空间中。它首先对双重文本-音乐流应用一系列独立的注意力,随后堆叠单一音乐流进行去噪补丁预测。我们采用多个预训练文本编码器以充分捕捉标题语义信息及推理灵活性。在此过程中,粗略的文本信息与时间步嵌入结合用于调制机制,而细粒度的文本细节则与音乐补丁序列拼接作为输入。通过深入研究,我们证明采用优化架构的整流流训练在文本到音乐任务上显著优于已有的扩散方法,这由多种自动指标和人类偏好评估所证实。我们的实验数据、代码和模型权重已在以下网址公开:https://github.com/feizc/FluxMusic。

英文摘要:

This paper explores a simple extension of diffusion-based rectified flow Transformers for text-to-music generation, termed as FluxMusic. Generally, along with design in advanced Flux\footnote{https://github.com/black-forest-labs/flux} model, we transfers it into a latent VAE space of mel-spectrum. It involves first applying a sequence of independent attention to the double text-music stream, followed by a stacked single music stream for denoised patch prediction. We employ multiple pre-trained text encoders to sufficiently capture caption semantic information as well as inference flexibility. In between, coarse textual information, in conjunction with time step embeddings, is utilized in a modulation mechanism, while fine-grained textual details are concatenated with the music patch sequence as inputs. Through an in-depth study, we demonstrate that rectified flow training with an optimized architecture significantly outperforms established diffusion methods for the text-to-music task, as evidenced by various automatic metrics and human preference evaluations. Our experimental data, code, and model weights are made publicly available at: \url{https://github.com/feizc/FluxMusic}.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑