ComfyUI Node
Audio-Visual Synesthesia (S42)
A ComfyUI node in S42 CutFlow/Audio/Latent/Experimental with 2 inputs and 1 output.
Audio-Visual Synesthesia (S42)
- image_latent
- LATENT
◄target_audio_seconds5►
CategoryS42 CutFlow/Audio/Latent/Experimental
Inputs (2)
| Name | Type | Default | Description |
|---|---|---|---|
| image_latent | LATENT | A latent tensor generated by an Image VAE. | |
| target_audio_seconds | INT | 51–30 | — |
Outputs (1)
| Name | Type | Description |
|---|---|---|
| LATENT | LATENT | — |