以下部分引用 AI 总结，现阶段 AI 仍然有幻觉。请以内容的原文为准。

数据新鲜度群聊 07-14 ✓卖方 07-14 ✓Wrap 断档15天 ✕News 07-15 ✓X 断档12天 ✕页面生成 07-15

Stability AI

5 atoms · 跨 1 天 · 首见 2026-05-20 · 最近 2026-05-20

三色: 🟦 fact 5 · 🟥 take 0 · stance ▲0/▼0/◆3

来源: X 5

时态: fresh:5

标签: 好信源:5

2026-05-20 · releases new audio model
Stability AI releases a new audio model that can create six-minute songs
tags: 好信源 · → daily
value: qty=six-minute songs · date=2026-05-20
2026-05-20 · SAME (音乐自动编码器) 发布
Stability AI just released SAME on Hugging Face
tags: 好信源 · → daily
2026-05-20 · 发布新版音频模型
Stability AI releases a new family of audio models called Stability Audio 3.0 that is trained on licensed data; the top model can generate six-minute songs
tags: 好信源 · → daily
value: date=2026-05-20
2026-05-20 · 发布 Stable Audio 3
Stability AI just released Stable Audio 3 on Hugging Face
tags: 好信源 · → daily
value: date=2026-05-20
2026-05-20 · 发布 Stable Audio 3 特性
Features a novel semantic-acoustic autoencoder, adversarial post-training for ultra-fast inference, and support for inpainting and LoRA fine-tuning.
tags: 好信源 · → daily
value: date=2026-05-20