Nodes/H3 Continuum/H3 Continuum Sampler V3.3
ComfyUI Node

H3 Continuum Sampler V3.3

Timeline Video sampler. It slices one Core VIDEO per chunk, resizes only that slice, and reuses the stable Continuum sampling engine.

By ukr8b3g-cmyk·Created 9 days ago·Updated 2 days ago· 11
H3 Continuum Sampler V3.3
  • model
  • clip
  • video_vae
  • sampler
  • sigmas
  • first_frame
  • last_frame
  • reference_image_1
  • reference_image_2
  • reference_image_3
  • reference_audio_1
  • reference_audio_vae
  • timeline_video
  • video_latents
  • audio_latents
  • assembly_plan
  • status
sequence_prompt
prompt_modeAuto
chunks3
chunk_seconds5.0
width1344
height768
continuityBalanced — 22 frames
base_seed0
audio_continuitytrue
diagnosticsBasic
reroll_from_chunkAuto
reroll_nonce0
strict_compatibilitytrue
debugfalse
show_previewtrue
run_storageOff
run_name
reference_sizeMatch Output
timeline_video_sizeEfficient - 0.4 MP
project_id
CategoryMiniMax H3/Continuum

Inputs (33)

NameTypeDefaultDescription
modelMODEL
clipCLIP
video_vaeVAEUsed only to encode image conditioning. T2VA does not use it; Continuum never decodes with it.
samplerSAMPLER
sigmasSIGMAS
sequence_promptSTRINGConnect one Text (Multiline) for the complete sequence.
prompt_modeCOMBOAutoAuto accepts Fixed, list-separated, and timeline prompt styles.
chunksINT31–16Number of sequential Continuum chunks to generate.
chunk_secondsFLOAT5.04–15Target duration per chunk. Five seconds is the validated default.
widthINT134432–16384Output width. Use a multiple of 32.
heightINT76832–16384Output height. Use a multiple of 32.
continuityCOMBOBalanced — 22 framesAmount of prior video context retained at each chunk boundary.
base_seedINT00–18446744073709550000Base seed used to derive deterministic per-chunk seeds.
audio_continuityBOOLEANtrueOn passes prior audio context into continuation chunks. Turn it off only to isolate or replace generated audio.
diagnosticsCOMBOBasic3 options: Basic, Detailed Report, Off
reroll_from_chunkCOMBOAutoAuto resumes the longest compatible saved prefix. Choosing a chunk reuses earlier chunks and regenerates that chunk and everything after it.
reroll_nonceINT00–4294967295Change only when regenerating an explicit chunk and you want a new variation with otherwise identical settings.
strict_compatibilityBOOLEANtrue
debugBOOLEANfalse
show_previewBOOLEANtrue
run_storageCOMBOOffAtomically save raw AV chunks and resume a compatible saved run.
run_nameSTRINGEnter a stable name for this saved run. Compatible chunks are selected automatically.
reference_sizeCOMBOMatch OutputMatch Output is the practical default; Max Identity preserves more reference detail.
timeline_video_sizeCOMBOEfficient - 0.4 MPEfficient limits each chunk-local reference slice to about 0.4 MP. Match Output uses the output pixel area and may be substantially heavier.
project_idSTRINGOptional. Leave blank to derive a stable ID from this sampler node. Run Name remains the explicit override.
first_frameoptIMAGEOptional. Leave all image inputs disconnected for T2VA.
last_frameoptIMAGE
reference_image_1optIMAGE
reference_image_2optIMAGE
reference_image_3optIMAGE
reference_audio_1optAUDIO
reference_audio_vaeoptVAE
timeline_videooptVIDEOOptional. One continuous Core VIDEO covering every configured chunk. When omitted or bypassed, the node uses the standard conditioning path. Its audio is ignored; use the normal audio inputs for generated audio.

Outputs (4)

NameTypeDescription
video_latentsLATENT
audio_latentsLATENT
assembly_planH3_CONTINUUM_ASSEMBLY_PLAN
statusSTRING