ComfyUI Node
H3 Sequence Dexogen
Generates one or more causally dependent MiniMax H3 audio/video chunks from a validated Dexogen storyboard. The MODEL is consumed after all upstream LoRA and sampling patches. Continuation keeps paired video and audio tails in latent space as native frame-zero AV guides, and can author experimental in-chain edits after the discarded replay overlap. It can resume atomic safetensors chunks from ComfyUI's output directory.
H3 Sequence Dexogen
- model
- clip
- video_vae
- audio_vae
- sampler
- sigmas
- storyboard
- first_frame
- last_frame
- reference_images
- av_latent
- sequence_state
- report
◄width1344►
◄height768►
◄cfg1.0►
◄seed0►
Category🧬 Dexogen/🎬 Video
Inputs (14)
| Name | Type | Default | Description |
|---|---|---|---|
| model | MODEL | — | |
| clip | CLIP | — | |
| video_vae | VAE | — | |
| audio_vae | VAE | — | |
| sampler | SAMPLER | — | |
| sigmas | SIGMAS | — | |
| storyboard | DEXOGEN_STORYBOARD | — | |
| width | INT | 134432–16384 | — |
| height | INT | 76832–16384 | — |
| cfg | FLOAT | 1.00–100 | — |
| seed | INT | 00–18446744073709550000 | — |
| first_frameopt | IMAGE | — | |
| last_frameopt | IMAGE | — | |
| reference_imagesopt | IMAGE | — |
Outputs (3)
| Name | Type | Description |
|---|---|---|
| av_latent | LATENT | One native MiniMax H3 NestedTensor containing the joined video and audio latents. |
| sequence_state | DEXOGEN_H3_SEQUENCE | Canonical resumable H3 sequence state without filesystem paths or prompt graph data. |
| report | STRING | Readable chunk, seed, timing, and cache summary. |