ComfyUI Node
H3 Continuum Second Pass V3.5
V3.5 context-aware Second Pass. Connect externally upscaled H3 video latents, the matching first-pass audio latents, and the original assembly plan. Connect the optional Continuum refine context to preserve the physical group's First/Last/Reference conditioning. SIGMAS controls the low-denoise refine schedule; audio output is preserved bit-exact from the first pass.
H3 Continuum Second Pass V3.5
- model
- clip
- sampler
- sigmas
- video_latents
- audio_latents
- assembly_plan
- refine_context
- video_vae
- refined_video_latents
- audio_latents
- updated_assembly_plan
- status
◄refine_seed0►
CategoryMiniMax H3/Continuum/Advanced
Inputs (10)
| Name | Type | Default | Description |
|---|---|---|---|
| model | MODEL | — | |
| clip | CLIP | — | |
| sampler | SAMPLER | — | |
| sigmas | SIGMAS | — | |
| video_latents | LATENT | — | |
| audio_latents | LATENT | — | |
| assembly_plan | H3_CONTINUUM_ASSEMBLY_PLAN | — | |
| refine_seed | INT | 00–18446744073709550000 | Base seed independently derived once per physical group. |
| refine_contextopt | H3_CONTINUUM_REFINE_CONTEXT | — | |
| video_vaeopt | VAE | — |
Outputs (4)
| Name | Type | Description |
|---|---|---|
| refined_video_latents | LATENT | — |
| audio_latents | LATENT | — |
| updated_assembly_plan | H3_CONTINUUM_ASSEMBLY_PLAN | — |
| status | STRING | — |