ComfyUI Node
H3 Latent Slice
Slices an H3 AV latent along the latent-frame axis and drops or trims the audio stream to match. For a single frame as an image use MiniMax H3 Decode Frames — a lone latent token does not decode to the frame it was inside a clip.
H3 Latent Slice
- samples
- LATENT
- latent_frames
◄start0►
◄count0►
◄audiodrop►
CategoryNynxz/H3/Latent
Inputs (4)
| Name | Type | Default | Description |
|---|---|---|---|
| samples | LATENT | An H3 latent, nested (video+audio) or bare. | |
| start | INT | 0-4096–4096 | First latent frame to keep. Negative counts from the end. |
| count | INT | 00–4096 | How many latent frames to keep. 0 means everything from start on. |
| audio | COMBO | drop | 'drop' returns video only, which is what a VAE Decode wants. 'trim' keeps a proportionally cut audio stream so the result stays a playable AV latent. |
Outputs (2)
| Name | Type | Description |
|---|---|---|
| LATENT | LATENT | — |
| latent_frames | INT | Latent frames in the result. |