ACE-Step Create Sample

A ComfyUI node in Audio/ACE-Step with 9 inputs and 6 outputs.

By kana112233·Created 6 months ago·Updated 6 months ago· 27

◄query►

◄checkpoint_dirAce-Step1.5►

◄lm_model_pathacestep-5Hz-lm-1.7B►

◄deviceauto►

◄instrumentalfalse►

◄vocal_languageauto►

◄top_k50►

◄top_p0.95►

◄temperature0.00►

CategoryAudio/ACE-Step

Inputs (9)

Name	Type	Default	Description
query	STRING		Natural language query describing the music you want to generate.
checkpoint_dir	COMBO	Ace-Step1.5	Directory containing ACE-Step model weights (DiT model).
lm_model_path	COMBO	acestep-5Hz-lm-1.7B	Path to the language model used for generating lyrics and metadata.
device	COMBO	auto	Computing platform to run the model on.
instrumentalopt	BOOLEAN	false	Whether to generate instrumental music only (no vocals).
vocal_languageopt	COMBO	auto	Vocal language (e.g., zh, en, ja).
top_kopt	INT	500–1000	Top-K filtering parameter for sampling.
top_popt	FLOAT	0.950–1	Top-P (nucleus sampling) filtering parameter.
temperatureopt	FLOAT	0.000–2	Sampling temperature for the language model. 0.0 is most stable (recommended).