ComfyUI Node
Mpi LTX Audio Video Mask
Creates noise masks for video and audio latents from time ranges. New content is generated inside the masked regions.
Mpi LTX Audio Video Mask
- video_latent
- audio_latent
- video_latent
- audio_latent
◄video_fps25.00►
◄video_start_time0.00►
◄video_end_time5.00►
◄audio_start_time0.00►
◄audio_end_time5.00►
◄max_lengthtruncate►
◄existing_mask_modeadd►
CategoryMpiNodes/KJ
Inputs (9)
| Name | Type | Default | Description |
|---|---|---|---|
| video_fps | FLOAT | 25.000–100 | — |
| video_start_time | FLOAT | 0.000–10000 | Start time in seconds for the video mask. |
| video_end_time | FLOAT | 5.000–10000 | End time in seconds for the video mask. |
| audio_start_time | FLOAT | 0.000–10000 | Start time in seconds for the audio mask. |
| audio_end_time | FLOAT | 5.000–10000 | End time in seconds for the audio mask. |
| max_length | COMBO | truncate | 'truncate': cut latent to end_time length. 'pad': extend latent to end_time. 'partial': mask range within existing latent. |
| video_latentopt | LATENT | — | |
| audio_latentopt | LATENT | — | |
| existing_mask_modeopt | COMBO | add | How to combine with existing noise masks if present. 'add' takes the max of existing and new, 'overwrite' replaces with the new mask, 'subtract' sets the masked region to 0, effectively unmasking it. |
Outputs (2)
| Name | Type | Description |
|---|---|---|
| video_latent | LATENT | — |
| audio_latent | LATENT | — |