ComfyUI Node
H3 Continuum Sampler V3.5
H3 Continuum V3.5 sampler. It preserves the V3.4 outputs and adds one physical-group refine context for context-aware Hi-Res Fix or an external latent Second Pass.
H3 Continuum Sampler V3.5
- model
- clip
- video_vae
- sampler
- sigmas
- first_frame
- last_frame
- reference_image_1
- reference_image_2
- reference_image_3
- reference_video_1
- driving_audio
- audio_vae
- reference_audio_1
- reference_audio_vae
- video_latents
- audio_latents
- assembly_plan
- status
- driving_audio
- refine_context
◄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►
◄project_id►
◄video_reference_sizeEfficient - 0.4 MP►
CategoryMiniMax H3/Continuum
Inputs (35)
| Name | Type | Default | Description |
|---|---|---|---|
| model | MODEL | — | |
| clip | CLIP | — | |
| video_vae | VAE | Used only to encode image conditioning. T2VA does not use it; Continuum never decodes with it. | |
| sampler | SAMPLER | — | |
| sigmas | SIGMAS | — | |
| sequence_prompt | STRING | Connect one Text (Multiline) for the complete sequence. | |
| prompt_mode | COMBO | Auto | Auto accepts Fixed, list-separated, and timeline prompt styles. |
| chunks | INT | 31–16 | Number of sequential Continuum chunks to generate. |
| chunk_seconds | FLOAT | 5.04–15 | Target duration per chunk. Five seconds is the validated default. |
| width | INT | 134432–16384 | Output width. Use a multiple of 32. |
| height | INT | 76832–16384 | Output height. Use a multiple of 32. |
| continuity | COMBO | Balanced — 22 frames | Amount of prior video context retained at each chunk boundary. |
| base_seed | INT | 00–18446744073709550000 | Base seed used to derive deterministic per-chunk seeds. |
| audio_continuity | BOOLEAN | true | On passes prior audio context into continuation chunks. Turn it off only to isolate or replace generated audio. |
| diagnostics | COMBO | Basic | 3 options: Basic, Detailed Report, Off |
| reroll_from_chunk | COMBO | Auto | Auto resumes the longest compatible saved prefix. Choosing a chunk reuses earlier chunks and regenerates that chunk and everything after it. |
| reroll_nonce | INT | 00–4294967295 | Change only when regenerating an explicit chunk and you want a new variation with otherwise identical settings. |
| strict_compatibility | BOOLEAN | true | — |
| debug | BOOLEAN | false | — |
| show_preview | BOOLEAN | true | — |
| run_storage | COMBO | Off | Atomically save raw AV chunks and resume a compatible saved run. |
| run_name | STRING | Enter a stable name for this saved run. Compatible chunks are selected automatically. | |
| reference_size | COMBO | Match Output | Match Output is the practical default; Max Identity preserves more reference detail. |
| project_id | STRING | Optional. Leave blank to derive a stable ID from this sampler node. Run Name remains the explicit override. | |
| video_reference_size | COMBO | Efficient - 0.4 MP | Efficient limits Video Guide Frames to about 0.4 MP; Balanced uses about 0.6 MP; Match Output uses the output pixel area. Source aspect ratio is preserved and smaller sources are not enlarged. |
| first_frameopt | IMAGE | Optional. Leave all image inputs disconnected for T2VA. | |
| last_frameopt | IMAGE | — | |
| reference_image_1opt | IMAGE | — | |
| reference_image_2opt | IMAGE | — | |
| reference_image_3opt | IMAGE | — | |
| reference_video_1opt | IMAGE | Optional video guide. Connect the IMAGE frame batch from a video loader; source-video audio is not included. Frames are interpreted at 24 fps and applied to every chunk. Non-native frame counts are padded by repeating the final frame to the next H3 17k+5 count, up to the one-chunk limit. | |
| driving_audioopt | AUDIO | Optional original audio timeline. It is used as native H3 guide conditioning and selected unchanged for final output. | |
| audio_vaeopt | VAE | Required only when Driving Audio is connected. Uses the same Audio VAE encode path as ComfyUI Core MiniMax H3 Add Guide. | |
| reference_audio_1opt | AUDIO | Optional standalone audio reference for H3 conditioning. It is not the audio track of Video Guide Frames. Unlike Driving Audio, it does not replace the generated final audio. | |
| reference_audio_vaeopt | VAE | Required only when Reference Audio is connected. It encodes the reference for H3 conditioning; generated audio remains the output. |
Outputs (6)
| Name | Type | Description |
|---|---|---|
| video_latents | LATENT | — |
| audio_latents | LATENT | — |
| assembly_plan | H3_CONTINUUM_ASSEMBLY_PLAN | — |
| status | STRING | — |
| driving_audio | AUDIO | — |
| refine_context | H3_CONTINUUM_REFINE_CONTEXT | — |