ComfyUI Node
AudioX Enhanced Text to Audio
A ComfyUI node in AudioX/Generation with 12 inputs and 1 output.
AudioX Enhanced Text to Audio
- model
- audio
◄text_promptTyping on a keyboard►
◄steps250►
◄cfg_scale7.0►
◄seed-1►
◄duration_seconds10.0►
◄negative_promptmuffled, distorted, low quality, noise, silence►
◄prompt_templatenone►
◄enhance_prompttrue►
◄style_modifiernone►
◄conditioning_modeenhanced►
◄adaptive_cfgtrue►
CategoryAudioX/Generation
Inputs (12)
| Name | Type | Default | Description |
|---|---|---|---|
| model | AUDIOX_MODEL | — | |
| text_prompt | STRING | Typing on a keyboard | Describe the audio you want to generate |
| steps | INT | 2501–1000 | — |
| cfg_scale | FLOAT | 7.00.1–20 | Classifier-free guidance scale for prompt adherence |
| seed | INT | -1-1–4294967295 | — |
| duration_seconds | FLOAT | 10.01–30 | — |
| negative_promptopt | STRING | muffled, distorted, low quality, noise, silence | Negative text prompt (currently logged only - implementation pending) |
| prompt_templateopt | COMBO | none | Use predefined prompt template |
| enhance_promptopt | BOOLEAN | true | Automatically enhance prompt with audio-specific keywords |
| style_modifieropt | COMBO | none | Add style modifier to the prompt |
| conditioning_modeopt | COMBO | enhanced | Conditioning enhancement level |
| adaptive_cfgopt | BOOLEAN | true | Automatically adjust CFG based on prompt specificity |
Outputs (1)
| Name | Type | Description |
|---|---|---|
| audio | AUDIO | — |