Save 4 hours! We auto-setup your workflow! Free!

Drop your workflow.json — we handle every dependency, custom node, and model. Just open the link and run.

Auto-Setup Workflow Json (Free) Now!
ComfyUI > Nodes > MiniMax-H3-Flow-Aligned-Regenerate

ComfyUI Extension: MiniMax-H3-Flow-Aligned-Regenerate

Repo Name

MiniMax-H3-Flow-Aligned-Regenerate

Author
xmarre (Account age: 2627 days)
Nodes
View all nodes(1)
Latest Updated
2026-11-10
Github Stars
0.02K

How to Install MiniMax-H3-Flow-Aligned-Regenerate

Install this extension via the ComfyUI Manager by searching for MiniMax-H3-Flow-Aligned-Regenerate
  • 1. Click the Manager button in the main menu
  • 2. Select Custom Nodes Manager button
  • 3. Enter MiniMax-H3-Flow-Aligned-Regenerate in the search bar
After installation, click the Restart button to restart ComfyUI. Then, manually refresh your browser to clear the cache and access the updated list of nodes.

Visit ComfyUI Online for ready-to-use ComfyUI environment

  • Free trial available
  • 16GB VRAM to 80GB VRAM GPU machines
  • 400+ preloaded models/nodes
  • Freedom to upload custom models/nodes
  • 200+ ready-to-run workflows
  • 100% private workspace with up to 200GB storage
  • Dedicated Support

Run ComfyUI Online

MiniMax-H3-Flow-Aligned-Regenerate Description

MiniMax-H3-Flow-Aligned-Regenerate reuses low-resolution H3 trajectories for high-resolution video refinement in ComfyUI and extends video across chunks while preserving accepted audio/video overlaps.

MiniMax-H3-Flow-Aligned-Regenerate Introduction

MiniMax-H3-Flow-Aligned-Regenerate is a collection of ComfyUI nodes that helps you reuse a lower-resolution MiniMax H3 generation when creating a higher-resolution result. It also provides dedicated tools for continuing a video across multiple chunks while preserving the accepted audio and video overlap.

Instead of asking H3 to do every stage of generation at the final resolution, you can establish the scene on a smaller working grid, transfer that work to a larger grid, and refine it there.

For you as an AI artist, this provides three main possibilities:

  • Reuse an established composition: guide a higher-resolution pass using information from the lower-resolution generation, rather than relying only on its final frame or final latent.
  • Move between resolutions during generation: begin on a smaller grid and switch to your target resolution within one sampling schedule.
  • Continue longer scenes: use the recommended Native Source Continuation path with H3 Continuum-Plus to carry forward source information and protect the accepted audio/video overlap.

The extension is training-free: you do not need to train a new model to use its guidance or handoff nodes. However, the recommended learned-transfer workflow uses a separately trained latent upscaler.

What it can—and cannot—do

The extension is designed to improve how generation work is reused across resolutions and continuation chunks. It does not guarantee identical composition, seamless joins, perfect camera behavior, or a particular speed improvement for every prompt.

Higher-resolution H3 refinement still needs enough GPU memory for the target-resolution stage. Starting at a smaller resolution does not eliminate that requirement.

The author describes this project as an independent research implementation informed by public work. It does not reproduce MiniMax’s closed H3-Regenerate-2K implementation or an unreleased sparse-attention model. No Keyless implementation is included.

How MiniMax-H3-Flow-Aligned-Regenerate Works

A few useful terms

TermPlain-language meaning
LatentA compressed representation of your video that the model works on before it is decoded into visible frames.
Sampling / denoisingThe sequence of model steps that gradually turns noise into generated content.
TrajectoryThe intermediate predictions made during that sequence—not just the final result.
Source gridThe smaller working resolution used during the early stage.
Target gridThe final working resolution.
Protected prefixThe beginning of a continuation chunk copied from the preceding chunk and marked to remain unchanged.
VAE decodeThe step that converts video latents into viewable frames.

Approach 1: flow-aligned two-pass guidance

Think of a low-resolution generation as a sequence of rough sketches. The last sketch is useful, but the earlier sketches also show how the scene developed.

The two-pass path records those intermediate H3 predictions and uses matching states to guide a later higher-resolution pass.

Low-resolution H3 generation
        |
Trajectory Capture
        |
Captured trajectory ---------------------+
                                          |
Learned upscale / refine initialization --+
                                          |
                              Flow-Aligned Regenerate
                                          |
                               Higher-resolution H3

A typical workflow uses:

  1. MiniMax H3 Flow Trajectory to hold the shared trajectory.
  2. MiniMax H3 Trajectory Capture during the first pass.
  3. A learned latent upscale/refine initialization.
  4. MiniMax H3 Flow-Aligned Regenerate during the second pass.

For a Continuum refinement workflow using refine_state, use MiniMax H3 Flow-Aligned Refine State.

Recommended starting guidance for this explicit two-pass approach: direction.

Approach 2: progressive handoff

Progressive handoff works more like drawing a composition on a small canvas, enlarging the working canvas partway through, and finishing at the larger size.

The normal progressive path:

  1. Performs early sampling on the reduced source grid.
  2. Takes an exact handoff probe.
  3. Transfers the predicted-clean video to the target grid.
  4. Continues H3 refinement at the target resolution.

The learned spatial transfer affects video only. Audio does not pass through the latent upscaler.

MiniMax H3 Native Source Continuation is the recommended progressive interface for both single chunks and Continuum sequences.

For continuation, it reuses the preceding chunk’s already-computed source clean prediction, paired with the exact returned target suffix. Its default target-band reconciliation adjusts the broad source layout to agree with the video that was actually returned.

An analogy is keeping both a rough sketch and a finished painting: before continuing the sketch, you align its major shapes with the finished painting so the next section follows the scene viewers actually saw.

The learned upscaler then transfers the generated trajectory to the target grid. High-resolution refinement uses the original protected target prefix, and the returned protected audio/video prefix remains authoritative.

Important distinctions:

  • Native source carry adds no extra H3, upscaler-provider, or VAE calls.
  • A learned handoff still occurs as part of the progressive workflow.
  • Missing or mismatched native source context stops generation before low sampling; it does not silently switch to another continuation method.
  • Exact overlap preservation does not guarantee that newly generated content immediately after the overlap will be visually seamless.

MiniMax-H3-Flow-Aligned-Regenerate Features

Main generation nodes

NodeWhat it doesWhen to use it
MiniMax H3 Flow TrajectoryHolds the shared trajectory used by capture, guidance, and progressive execution.When building trajectory-based workflows.
MiniMax H3 Trajectory CaptureRecords first-pass predicted-clean H3 states.On the low-resolution pass of a two-pass workflow.
MiniMax H3 Flow-Aligned RegenerateGuides a later H3 pass using the matching captured state.For explicit upscale-and-refine workflows.
MiniMax H3 Flow-Aligned Refine StateProvides flow-aligned guidance through Continuum’s refine_state.When refining Continuum chunk outputs.
MiniMax H3 Progressive HandoffProvides a generic source-sized resolution handoff.For workflows defined from the smaller source input.
MiniMax H3 Progressive Handoff (Target Input)Provides progressive control for workflows defined at the final target geometry.For general target-input workflows; protected prefixes have a special fallback described below.
MiniMax H3 Native Source ContinuationCombines a uniform source trajectory, native source carry, learned transfer, and exact protected audio/video ownership.Recommended for new single-chunk and Continuum progressive workflows.
MiniMax H3 Partitioned Exact-Prefix Handoff [Legacy Controls]Preserves the older control layout and explicit continuation settings.For existing saved workflows rather than new projects.
MiniMax H3 Continuum Decode ContextSupplies future latent context to the native temporal decoder at exact chunk joins.To address the separate decoder-window boundary problem.

Source-prefix projection choices

These settings determine how the reduced-grid prefix is prepared. None changes the authoritative target prefix.

source_prefix_projectionBehavior
native_source_carry_target_bandRecommended new-node default. Uses broad spatial information from the resized returned target prefix and retains finer carried detail only where the latent structures agree.
native_source_carryPrevious behavior: uses the preceding chunk’s reduced-grid estimate at the handoff noise level without target-band reconciliation.
latent_bicubicReconstructs only the source prefix when paired native context is unsuitable.

The author reports that target-band reconciliation removed a visible boundary and a background redraw shortly after the join in user-reviewed continuation renders. This is evidence from those renders, not a universal seam-quality guarantee.

Detail transport

uniform_source_detail_transport=true enables a checked detail correction before high refinement.

It uses the last protected prefix to estimate detail lost during learned transfer. The correction is applied only when its calibration and holdout checks pass; otherwise, the extension reports that it was skipped.

  • It adds no H3, provider, or VAE evaluation.
  • Its calibration still uses compute and memory.
  • It has no prefix to correct in an entirely generated single chunk.
  • Existing saved false values and legacy-node defaults remain unchanged.

Guidance modes and customization

ControlMeaning and practical use
directionConservative recommendation for explicit two-pass guidance.
direction+temporalRecommended progressive default, combining directional and temporal guidance.
direction+accelerationResearch control that activates acceleration_weight.
downsample_consistencyResearch control that activates consistency_weight.
direction_weightAdjusts the contribution of directional guidance.
temporal_weightAdjusts the contribution of temporal guidance.
low_frequency_cutoffControls the low-frequency band used by guidance. See the usage documentation for its exact interpretation.

For example, changing acceleration_weight while using direction+temporal has no effect: that weight is inactive in this mode. Switch modes only when you intentionally want to test a different guidance method.

When comparing settings, keep your seed, prompt, references, model, resolution, duration, and sampler unchanged. Judge the decoded video as well as any metrics.

Target Input’s exact-prefix fallback

Progressive Handoff (Target Input) behaves differently depending on the mask:

  • Unprotected or fractional-mask input: runs the normal progressive low/probe/high path.
  • Exact protected video prefix: forwards the original target-grid noise, latent, mask, and schedule through one ordinary target-grid sampler lifetime.

In the exact-prefix fallback, there is:

  • No private low-grid sampler.
  • No exact handoff probe.
  • No learned-upscaler call.
  • No resolution boundary or progressive-history boundary.

For canonical exact-prefix continuation, Target Input also uses a validated four-tick audio-overlap ramp during sampling. The original exact video/audio mask remains authoritative at output.

This is separate from Native Source Continuation’s default sampler_mask_exact_timestep audio-overlap mode. Do not assume the two interfaces use identical continuation behavior.

Decoder context and diagnostics

Continuum Decode Context is placed immediately before normal Video VAE Decode. It supplies real future latent context at chunk joins without changing accepted sampling latents, continuation state, masks, audio, or the assembly plan.

For deeper investigation:

  • MiniMax H3 Local Boundary Audit replays saved boundary bundles through the production native video VAE.
  • MiniMax H3 Metrics JSON writes structured model, sampler, geometry, and forecasting metrics.
  • Full-stage continuity replay saves matched PNGs and stage records without running H3 sampling.

Audit measurements help locate changes between stages. They do not automatically prove that a camera movement, focus change, or soft background is a defect.

Legacy and experimental controls

The following remain available for compatibility or controlled research:

NodeStatus
Progressive Mixed-Grid ContinuumDeprecated compatibility path; not recommended for new production work.
Progressive Target-Sparse ContinuumExperimental and not recommended for final output. Testing showed cascading skin, clothing, and background defects.
Refine Target GeometryExperimental target-sizing metadata control.
Resolution-Aware SigmasExperimental resolution-dependent refinement schedules; off by default.
Reference BudgetExperimental reference diagnostics and guarded reference cap.
Attention LabExperimental attention and retention diagnostics.

Retired live replay and kernel-observer controls may still occupy saved widget slots so older graphs load, but they no longer add sampling calls or hooks.

Using MiniMax-H3-Flow-Aligned-Regenerate

Choose an example workflow

Start from the loadable example workflows rather than rebuilding the graph from scratch.

ExamplePurpose
Native Source ContinuationRecommended single-chunk and Continuum interface with learned 3D transfer and exact protected audio/video.
Progressive Target InputGeneral progressive control defined at target resolution.
Progressive Source InputProgressive control defined from the source input.
Partitioned Exact PrefixPreserved legacy control layout.
Full-stage continuityDiagnostic example for investigating continuity across stages.

Matching .api.json graphs are included. Wiring overlays are specifications, not loadable workflows.

  1. Use MiniMax H3 Native Source Continuation (H3NativeSourceContinuationHandoff).
  2. Connect VDN-H3-Plus partitioned transport and the learned 3D upscaler provider.
  3. Keep VDN’s full trained linear complement enabled.
  4. Connect the patched MODEL to both the scheduler and guider.
  5. For Continuum Native Masked generation, use that same patched MODEL for the initial chunk and every continuation.

A first chunk generated with a different MODEL cannot supply the required native source carry.

Native carry requires:

  • Batch-one H3 video.
  • Native 5k+2 latent-token lengths.
  • An even spatial grid.
  • A target grid larger than the reduced source grid.

These are latent-layout requirements, not a rule to apply directly to your visible frame count.

SettingDefault
source_modescale
source_scale0.70
source_width, source_height864, 640, used only in pixels mode
handoff_coordinate0.35
handoff_selectionfixed
guidance_modedirection+temporal
direction_weight0.25
acceleration_weight0.25, inactive in the default guidance mode
consistency_weight0.25, inactive in the default guidance mode
low_frequency_cutoff0.25
temporal_weight0.20
audio_guided_overlap_modesampler_mask_exact_timestep
audio_guided_overlap_ticks16, with zero effective release in exact mode
uniform_source_detail_transporttrue
source_prefix_projectionnative_source_carry_target_band
capture_boundary_witnessfalse

source_scale=0.70 requests a reduced working size relative to the target. Switching to pixels mode makes the explicit source width and height relevant instead.

The shipped learned examples use:

  • minimax_h3_latent_upscaler_3d_bf16.safetensors
  • CUDA and bf16
  • offload_after_upscale=false
  • res_multistep
  • No Turbo LoRA

Saved workflows retain their stored values. Updating the extension does not automatically apply these defaults.

Optional patch order

For the native-source Continuum stack, preserve this order when the optional patches are present:

DiffAid
  -> Untwisting RoPE
  -> Spectrum
  -> Native Source Continuation
  -> Continuum

DiffAid, Untwisting RoPE, and Spectrum are optional. Sol-H3 is also optional; the continuation path supports the selected ComfyUI attention backend through VDN-H3-Plus.

Spectrum is a separate approximate accelerator. It forecasts some H3 feature states instead of running every full transformer evaluation, so it can change the output even with the same seed. It is not the same mechanism as Flow’s resolution handoff.

MiniMax-H3-Flow-Aligned-Regenerate Models

Does the extension include its own model variants?

The extension provides workflow nodes, not a separate family of generative checkpoints. Your MiniMax H3 model generates the content; the recommended companion upscaler enlarges its video latents.

Learned 3D upscaler checkpoints

The companion MiniMax H3 Latent Upscaler-Plus uses checkpoints available from LBH-123-AI on Hugging Face.

CheckpointStored precisionRelevance
minimax_h3_latent_upscaler_3d_bf16.safetensorsBF16Used by Flow’s supplied learned-transfer examples and preselected by the provider when available.
minimax_h3_latent_upscaler_3d_fp16.safetensorsFP16An alternative stored-precision version of the same 3D architecture.
minimax_h3_latent_upscaler_3d_fp32.pthFP32Full-precision storage version of the same architecture.

These are not different artistic styles. The provider’s precision setting controls inference precision independently of the checkpoint’s stored precision.

The companion package also has a 2D upscaler node, but Flow’s recommended learned handoff uses the 3D provider. A 3D checkpoint is not compatible with the 2D node.

Learned transfer versus bicubic

The general unprotected Target Input handoff supports:

  • learned_3d: transfers the clean video estimate using the trained upscaler; used in the supplied target-input workflow.
  • bicubic: an interpolation-based alternative.

This transfer selection is distinct from the latent_bicubic source-prefix projection option.

The learned upscaler preserves the time axis and enlarges only the spatial dimensions. It never processes audio.

What’s New with MiniMax-H3-Flow-Aligned-Regenerate

v0.3.14 — coordinated release, 17 October 2026

The recommended Native Source Continuation workflow remains unchanged.

ChangeWhy it matters
PR #107 retains Sol-H3 grouped K/V fusion in continuation.Keeps the coordinated Sol/VDN continuation integration available without replacing VDN’s required trained linear work.
PR #102, #103, and #108 expand diagnostics.Provide full-stage tone evidence, target-sized comparisons, and per-prompt lifecycle/paging records for investigating continuity and memory behavior.
PR #105 fixes old local-audit ownership retention across prompts.Prevents completed audit state from unnecessarily retaining model owners across later prompts.

Lifecycle tracing is optional. Set H3_LIFECYCLE_TRACE=1 before ComfyUI starts when you need those records.

Coordinated companion versions

ComponentRelease paired with Flow v0.3.14
Flow-Aligned Regeneratev0.3.14
Sol-H3v0.1.11, optional
VDN-H3-Plusv1.5.10
H3 Continuum-Plusv3.4.9

Later supplied Continuum notes identify v3.4.10 and v3.4.11 as compatible with Flow v0.3.14. Those releases address speech-conditioning isolation and package publishing identity; they are not Flow releases.

Earlier documented changes

  • v0.3.13: includes PR #101. The supplied summary does not describe its individual changes; consult the release history.
  • v0.3.11: established progressive_uniform_source as the default partitioned-continuation profile and supports continuation with the selected ComfyUI attention backend rather than requiring Sol-H3.

For the complete historical record, see Release Notes and Release Context. Experimental sibling-package features are not automatically part of this release.

Troubleshooting MiniMax-H3-Flow-Aligned-Regenerate

Continuation stops because native source context is missing or mismatched

  1. Confirm that the initial chunk was generated using the same Native Source Continuation-patched MODEL.
  2. Check that the same patched MODEL reaches the scheduler, guider, and Continuum sequence.
  3. Verify the required batch, temporal layout, even spatial grid, and source/target size relationship.
  4. Regenerate the initial chunk with the correct graph if it came from a different MODEL.

Stopping is intentional: native carry does not silently substitute an unrelated source estimate.

A join shows background redraw or a visible boundary

  1. Check source_prefix_projection in your saved node.
  2. If it uses the previous native_source_carry behavior, select native_source_carry_target_band.
  3. Check whether detail transport is enabled and whether its correction passed or was skipped.
  4. Compare the decoded video around the join—not only the overlap itself.
  5. If the problem remains, use full-stage continuity replay or a boundary audit to identify the stage where the change appears.

Target-band reconciliation does not guarantee every join. Camera, focus, prompt, and reference behavior remain model-dependent.

The continuation becomes slightly darker

Slight continuation darkening remains a known issue.

  1. Compare matched frames before and after the join.
  2. Use full-stage diagnostics to distinguish sampling-stage changes from decoder or assembly behavior.
  3. If you use Continuum-Plus, review its Auto 3 (Sustained Tone) video-seam option. It can reduce sustained darkening in suitable scenes, but it modifies newly generated decoded frames and is not a geometric repair.
  4. For a controlled comparison, keep generation settings fixed and compare seam modes such as Auto or Analyze Only.

The upscaler is connected but does not run

  1. Identify the handoff node.
  2. If you use Target Input with an exact protected video prefix, zero upscaler calls are expected: this path uses the target-grid fallback.
  3. For an unprotected learned handoff, check that learned_3d is selected and the 3D provider is connected.
  4. For the recommended native-source continuation workflow, use the dedicated Native Source Continuation example.

Changing a setting has no visible effect

  1. Confirm that the setting is active in the selected mode.
  2. Remember that source_width and source_height apply only in pixels mode.
  3. acceleration_weight is active only in direction+acceleration.
  4. consistency_weight is active only in downsample_consistency.
  5. Compare saved widget values with current defaults; existing workflows are not rewritten on update.

Retired replay flags cannot add sampling calls or hooks, even if their saved slots remain present.

GPU memory runs out during high-resolution refinement

  1. Remember that the high stage still runs H3 at the full target resolution.
  2. Reduce target resolution or duration and test again.
  3. Review the companion upscaler’s offload_after_upscale option if keeping its network resident contributes to memory pressure. Offloading adds transfers and can reduce speed.
  4. Keep VDN’s trained linear complement enabled; disabling required model work is not a supported memory shortcut.
  5. For a local audit, use the same production VAE and settings. The audit stops when decode memory is insufficient and does not retry a managed decode after OOM.

No universal minimum VRAM requirement or speedup is established by the supplied documentation.

A decoder-window join remains visible

  1. Distinguish the decoder boundary from a change already present in sampling latents.
  2. Place MiniMax H3 Continuum Decode Context immediately before normal Video VAE Decode.
  3. Follow the Decode Context guide.

This helper addresses a separate decoder-window issue. It does not replace sampler-time prefix protection or audio-overlap behavior.

A Local Boundary Audit cannot find its bundle

  1. Point bundle_path to the exported directory containing manifest.json and the full binary operands, or select manifest.json itself.
  2. Connect the same native video VAE instance and settings used for production.
  3. Set chunk_join_frame to the assembled output’s first new frame, or leave it at zero for labels relative to the join.
  4. In WSL, use a Linux path such as /home/..., or a matching \\wsl.localhost\<distribution>\... / \\wsl$\<distribution>\... path.

Windows Explorer paths are translated only when the distribution matches WSL_DISTRO_NAME. Quotes added by Copy as path are accepted.

Frequently asked questions

Do you need Sol-H3?
No. Sol-H3 is optional. Native Source Continuation requires VDN-H3-Plus partitioned transport and the recommended learned upscaler, but supports the selected ComfyUI attention backend.

Why does Sol-H3 show no custom-kernel acceleration on native Windows?
The supplied Sol documentation states that its custom SOL and Exact Runtime kernels do not execute on native Windows. Those nodes delegate to inherited/native paths. Supported custom-kernel targets are Linux/WSL2 on SM120/SM121 hardware.

Does exact prefix preservation mean the whole continuation is identical?
No. It preserves the accepted protected overlap. Newly generated frames can still change tone, background detail, motion, or framing.

Does this upscale or regenerate audio?
The spatial upscaler processes only video. Audio behavior is managed by the sampling and continuation contracts.

Does a successful detail-transport calibration guarantee a seamless result?
No. It permits that correction to run; final visual acceptance still requires watching the decoded output.

Can you keep using an older graph?
Legacy node identifiers and saved layouts are retained where documented. For new work, use Native Source Continuation rather than deprecated Mixed-Grid or experimental Target-Sparse paths.

Will the same settings always produce the same performance?
No. Timing depends on geometry, duration, sampler, model residency, references, Spectrum policy, hardware, and optional attention backends.

Learn More about MiniMax-H3-Flow-Aligned-Regenerate

Start here

Understanding joins and output quality

Companion tools

  • MiniMax H3 Latent Upscaler-Plus — learned video-latent enlargement and the 3D handoff provider.
  • VDN-H3-Plus — trained hybrid-attention integration and partitioned transport.
  • H3 Continuum-Plus — chunked generation, Native Masked continuation, references, audio routing, and assembly.
  • Spectrum MiniMax H3 — optional approximate feature-forecasting acceleration.
  • Sol-H3 — optional attention/runtime integration with hardware-specific requirements.

Advanced and historical documentation

MiniMax-H3-Flow-Aligned-Regenerate License

MiniMax-H3-Flow-Aligned-Regenerate is licensed under the Apache License 2.0.

Copyright 2026 xmarre.

Companion repositories, referenced papers, and third-party model weights retain their own copyrights and licenses.

MiniMax-H3-Flow-Aligned-Regenerate Related Nodes

RunComfy
Copyright 2025 RunComfy. All Rights Reserved.

RunComfy is the premier ComfyUI platform, offering ComfyUI online environment and services, along with ComfyUI workflows featuring stunning visuals. RunComfy also provides AI Models, enabling artists to harness the latest AI tools to create incredible art.

MiniMax-H3-Flow-Aligned-Regenerate detailed guide | ComfyUI