# Hugging Face — AudioLDM 2, but faster ⚡️

- Company: Hugging Face (huggingface.co)
- Announced: 2023-08-30
- Category: not stated
- Coverage: not counted
- Announcement: no
- Group: routine
- Source: https://huggingface.co/blog/audioldm2
- Record: https://forck.live/items/2004-audioldm-2-but-faster
- Subject: Platform
- Models affected: AudioLDM 2, cvssp/audioldm2, cvssp/audioldm2-music, cvssp/audioldm2-large

To use AudioLDM 2 in the Hugging Face Diffusers library with optimizations that reduce inference time by over 10 times, achieving 10-second audio generation in about 1 second.

## Evidence

Verbatim from https://huggingface.co/blog/audioldm2:

> we showcase how to use AudioLDM 2 in the Hugging Face 🧨 Diffusers library, exploring a range of code optimisations such as half-precision, flash attention, and compilation, and model optimisations such as scheduler choice and negative prompting, to reduce the inference time by over 10 times

---

Record: https://forck.live/items/2004-audioldm-2-but-faster
Catalogue: https://forck.live/llms.txt
Current issue: https://forck.live/feed.md