ComfyUI Node
H3 Extras
The canvas from an h3_inputs wire, as plain numbers: width, height, the requested length and the frame count it snaps up to, the video and audio latent lengths, and the real duration in seconds.
H3 Extras
- h3_inputs
- width
- height
- length
- frame_count
- latent_t
- audio_t
- seconds
- task
- is_keyframes
- is_references
- summary
◄modeauto►
CategoryNynxz/H3
Inputs (2)
| Name | Type | Default | Description |
|---|---|---|---|
| h3_inputs | NYNXZH3_INPUT | From H3 Inputs, or anywhere along the chain. | |
| mode | COMBO | auto | Match whatever H3 Encode is set to, so the task reported here is the task that will actually run. |
Outputs (11)
| Name | Type | Description |
|---|---|---|
| width | INT | — |
| height | INT | — |
| length | INT | The length the canvas asked for. |
| frame_count | INT | What it snaps up to on the model's 17k+5 grid — the frames you actually get. |
| latent_t | INT | Video latent frames. |
| audio_t | INT | Audio latent frames (40 Hz). |
| seconds | FLOAT | frame_count / 24. |
| task | STRING | t2va, fl2va or ref2va — what the same list will make H3 Encode do. |
| is_keyframes | BOOLEAN | True for fl2va — a first and/or last frame is driving the clip. Wire into a switch to branch a graph on it. |
| is_references | BOOLEAN | True for ref2va — <Picture i> / <Video k> / <Audio j> references. |
| summary | STRING | One line naming all of it, for a text preview. |