From the source
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.
AudioLDM 2, but faster ⚡️
From the source
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
huggingface.co
