Nodes/ComfyUI-AudioX/AudioX Enhanced Text to Music
ComfyUI Node

AudioX Enhanced Text to Music

A ComfyUI node in AudioX/Generation with 13 inputs and 1 output.

By lum3on·Created about a year ago·Updated about a year ago· 53
AudioX Enhanced Text to Music
  • model
  • audio
text_promptA peaceful piano melody
steps250
cfg_scale7.0
seed-1
duration_seconds10.0
negative_promptdiscordant, harsh, atonal, noise, distorted
music_stylenone
temponone
moodnone
enhance_prompttrue
conditioning_modeenhanced
adaptive_cfgtrue
CategoryAudioX/Generation

Inputs (13)

NameTypeDefaultDescription
modelAUDIOX_MODEL
text_promptSTRINGA peaceful piano melodyDescribe the music you want to generate
stepsINT2501–1000
cfg_scaleFLOAT7.00.1–20Classifier-free guidance scale for prompt adherence
seedINT-1-1–4294967295
duration_secondsFLOAT10.01–30
negative_promptoptSTRINGdiscordant, harsh, atonal, noise, distortedNegative text prompt (currently logged only - implementation pending)
music_styleoptCOMBOnoneMusical style to apply
tempooptCOMBOnoneTempo indication
moodoptCOMBOnoneMusical mood
enhance_promptoptBOOLEANtrueAutomatically enhance prompt with music-specific keywords
conditioning_modeoptCOMBOenhancedConditioning enhancement level
adaptive_cfgoptBOOLEANtrueAutomatically adjust CFG based on prompt specificity

Outputs (1)

NameTypeDescription
audioAUDIO