I found that merging Stable Audio 3 Medium base and non-base at 1:2 ratio allows one to increase CFG without the model breaking down. This virtually eliminates the infamous "SA3 crunch" and considerably improves audio quality.
This merge has been converted to gguf for use in sa3.cpp
Example (16steps, cfg3)
- Downloads last month
- 73
Hardware compatibility
Log In to add your hardware
16-bit
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support
Model tree for worstplayer/Stable_Audio_3_medium_base_merge-GGUF
Base model
stabilityai/stable-audio-3-medium-base Finetuned
stabilityai/stable-audio-3-medium