ComfyUI Node
AudioX Enhanced Video to Audio
A ComfyUI node in AudioX/Generation with 13 inputs and 1 output.
AudioX Enhanced Video to Audio
- model
- video
- audio
◄text_promptGenerate realistic audio that matches the visual content►
◄steps250►
◄text_cfg_scale7.0►
◄video_cfg_scale7.0►
◄text_weight1.0►
◄video_weight1.0►
◄seed-1►
◄duration_seconds10.0►
◄negative_prompt►
◄prompt_templatenone►
◄enhance_prompttrue►
CategoryAudioX/Generation
Inputs (13)
| Name | Type | Default | Description |
|---|---|---|---|
| model | AUDIOX_MODEL | — | |
| video | IMAGE | — | |
| text_prompt | STRING | Generate realistic audio that matches the visual content | — |
| steps | INT | 2501–1000 | — |
| text_cfg_scale | FLOAT | 7.00.1–20 | CFG scale for text conditioning |
| video_cfg_scale | FLOAT | 7.00.1–20 | CFG scale for video conditioning |
| text_weight | FLOAT | 1.00–2 | Weight for text conditioning influence |
| video_weight | FLOAT | 1.00–2 | Weight for video conditioning influence |
| seed | INT | -1-1–4294967295 | — |
| duration_seconds | FLOAT | 10.01–30 | — |
| negative_promptopt | STRING | Negative text prompt to avoid certain audio characteristics | |
| prompt_templateopt | COMBO | none | Use predefined prompt template |
| enhance_promptopt | BOOLEAN | true | Automatically enhance prompt with audio-specific keywords |
Outputs (1)
| Name | Type | Description |
|---|---|---|
| audio | AUDIO | — |