TE
科技回声
首页24小时热榜最新最佳问答展示工作
GitHubTwitter
首页

科技回声

基于 Next.js 构建的科技新闻平台,提供全球科技新闻和讨论内容。

GitHubTwitter

首页

首页最新最佳问答展示工作

资源链接

HackerNews API原版 HackerNewsNext.js

© 2025 科技回声. 版权所有。

Diffusion Radio – A 24/7 Livestream of AI-Generated Music

3 点作者 carlgreene超过 2 年前

2 条评论

LunarAurora超过 2 年前
&gt; <i>These outputs are from text-conditioned latent audio diffusion models on raw audio, no spectrograms. We hope to get models like this released within the next few months! </i> [1]<p>It is difficult to judge without knowing the &quot;raw materials&quot; for each generation (prompt&#x2F;seeds…). Audio Quality is understandably better than Riffusion. What most surprised me in Riffusion was those coherent, intricate (and musical !) melody lines. Here I&#x27;m (now) hearing mostly EDM&#x2F;IDM(ish) music, and it is the tonal textures (and beats) that are surprisingly coherent.<p>I suppose it is highly curated . Still, it is promising.<p>[1] <a href="https:&#x2F;&#x2F;twitter.com&#x2F;harmonai_org&#x2F;status&#x2F;1604903187978547201" rel="nofollow">https:&#x2F;&#x2F;twitter.com&#x2F;harmonai_org&#x2F;status&#x2F;1604903187978547201</a>
hobbitstan超过 2 年前
The AI-generated dubstep was spot on. Sounded just like Excision!