ComfyUI Node
H3 Reference to Video (refs) (alpha)
MiniMax H3 Reference to Video with its references from one H3 References input. Same conditioning as the core node; without refs it is plain text-to-video.
H3 Reference to Video (refs) (alpha)
- clip
- vae
- audio_vae
- refs
- positive
- LATENT
◄prompt—►
◄width1344►
◄height768►
◄length124►
◄ref_image_sizematch►
CategoryMAINodes/H3
Inputs (9)
| Name | Type | Default | Description |
|---|---|---|---|
| clip | CLIP | — | |
| vae | VAE | — | |
| audio_vae | VAE | — | |
| prompt | STRING | — | |
| width | INT | 134432–16384 | — |
| height | INT | 76832–16384 | — |
| length | INT | 1245–3600 | Frame count at 24 fps, (124 = ~5s, trained range is ~124-362) |
| ref_image_size | COMBO | match | Reference image sizing. 'match' scales each ref (down only, keeping aspect) to the generation's pixel area; 'max' uses the reference pipeline's 2048px short edge for best identity fidelity. Reference tokens ride through every sampling step, so 'max' can be several times slower. |
| refsopt | H3_REFS | — |
Outputs (2)
| Name | Type | Description |
|---|---|---|
| positive | CONDITIONING | — |
| LATENT | LATENT | — |