Extensions/ComfyUI-MiniMaxH3-Context-Loop
ComfyUI Extension

ComfyUI-MiniMaxH3-Context-Loop

Clip chaining for MiniMax H3 in ComfyUI - motion and audio genuinely continue across joins

By ethanfel·Created 2 months ago·Updated about 22 hours ago· 463
ethanfel/ComfyUI-MiniMaxH3-Context-Loop
Nodes90
On cloudLocal install
Categoryconditioning/minimax/context_loop/upscale, conditioning/minimax/context_loop/policies
Stars463
Updatedabout 22 hours ago

Nodes (90)

H3 Conditioning Sync From Latents
conditioning/minimax/context_loop/upscale
MiniMax H3 Advanced Policy Override
conditioning/minimax/context_loop/policies
MiniMax H3 Audio Tracks
conditioning/minimax/context_loop/media
MiniMax H3 Context Loop Assemble
conditioning/minimax/context_loop
MiniMax H3 Chapter Delivery
conditioning/minimax/context_loop
MiniMax H3 Chapter Recovery Load
conditioning/minimax/context_loop
MiniMax H3 Checkpoint Manager
conditioning/minimax/context_loop
MiniMax H3 Context Loop Context
conditioning/minimax/context_loop
MiniMax H3 Context Loop Current Shot
conditioning/minimax/context_loop
MiniMax H3 Chain De-Rope Budget
conditioning/minimax/context_loop/upscale
MiniMax H3 Chain De-Rope Continuity
conditioning/minimax/context_loop/upscale
MiniMax H3 Chain De-Rope Freeze Mask
conditioning/minimax/context_loop/upscale
MiniMax H3 Chain De-Rope Guard
conditioning/minimax/context_loop/upscale
MiniMax H3 Context Loop Export PNG Sequence + Audio
conditioning/minimax/context_loop
MiniMax H3 Existing Video Context
conditioning/minimax/context_loop
MiniMax H3 Frame Gate
conditioning/minimax/context_loop
MiniMax H3 Frame Index Switch
conditioning/minimax/context_loop
MiniMax H3 Full-Chain Latent Video Adapter
conditioning/minimax/context_loop
MiniMax H3 LMS Upscale Guide (Experimental)
conditioning/minimax/context_loop/upscale
MiniMax H3 Context Loop End
conditioning/minimax/context_loop
MiniMax H3 Context Loop Start
conditioning/minimax/context_loop
MiniMax H3 Scene LoRA Scheduler
conditioning/minimax/context_loop
MiniMax H3 Context Loop Load Manifest
conditioning/minimax/context_loop
MiniMax H3 Pass-2 AV Prepare
conditioning/minimax/context_loop/upscale
MiniMax H3 Context Loop Plan
conditioning/minimax/context_loop
MiniMax H3 Plan (Modern)
conditioning/minimax/context_loop
MiniMax H3 Plan Studio (Experimental)
conditioning/minimax/context_loop
MiniMax H3 Chain Preflight
conditioning/minimax/context_loop
MiniMax H3 Chain Recovered AV
conditioning/minimax/context_loop/upscale
MiniMax H3 Context Loop Review Gate
conditioning/minimax/context_loop
MiniMax H3 Rich Scene Prompt Editor (Experimental)
conditioning/minimax/context_loop
MiniMax H3 Run Manager
conditioning/minimax/context_loop
MiniMax H3 Scene Prompt Editor
conditioning/minimax/context_loop
MiniMax H3 Context Loop Segment + Checkpoint
conditioning/minimax/context_loop
MiniMax H3 Chain SelfLift Sampler — Experimental
sampling/minimax/context_loop
MiniMax H3 Checkpoint Upscale Adapter
conditioning/minimax/context_loop/upscale
MiniMaxH3ChainUpscaleAdvance
_internal/minimax/upscale
MiniMax H3 Upscale Current Scene
conditioning/minimax/context_loop/upscale
MiniMaxH3ChainUpscaleHandoff
_internal/minimax/upscale
MiniMax H3 Upscale Loop End
conditioning/minimax/context_loop/upscale
MiniMax H3 Upscale Manifest Load
conditioning/minimax/context_loop/upscale
MiniMax H3 Pixel Upscale Conditioning (Experimental)
conditioning/minimax/context_loop/upscale
MiniMax H3 Pixel Upscale Current Scene (Experimental)
conditioning/minimax/context_loop/upscale
MiniMax H3 Upscale Reference Conditioning
conditioning/minimax/context_loop/upscale
MiniMax H3 Upscale Segment Save
conditioning/minimax/context_loop/upscale
MiniMax H3 Masking · Loop Mask Slice
conditioning/minimax/context_loop/masking
MiniMax H3 Context Loop Seam Probe
conditioning/minimax/context_loop
MiniMax H3 Masking · Loop Source AV Target
conditioning/minimax/context_loop/masking
MiniMax H3 Masking · Two-Clip AV Bridge
conditioning/minimax/context_loop/masking
MiniMax H3 Masking · Apply Target Mask
conditioning/minimax/context_loop/masking
MiniMax H3 Masking · Grid Preview
conditioning/minimax/context_loop/masking
MiniMax H3 Masking · Master Audio + Video Prefix
conditioning/minimax/context_loop/masking
MiniMax H3 Masking · Trim Source AV
conditioning/minimax/context_loop/masking
MiniMax H3 Current Tagged Ref2VA Scene
conditioning/minimax/context_loop/references/prompt_driven
MiniMax H3 Current Tagged Scene Pack (Internal)
conditioning/minimax/context_loop/internal
MiniMax H3 Drift-Control Model Patch (Sigma Split)
conditioning/minimax/context_loop
MiniMax H3 Generation Profile
conditioning/minimax/context_loop/policies
MiniMax H3 Lazy Motion Scene Preview
conditioning/minimax/context_loop/references/prompt_driven
MiniMax H3 Lip-Sync Options
conditioning/minimax/context_loop/policies
MiniMax H3 Context Loop Trim
conditioning/minimax/context_loop
MiniMax H3 Patch Priority
conditioning/minimax/context_loop
MiniMax H3 Pending Review
conditioning/minimax/context_loop
MiniMax H3 Pixel Continuity • Keep Boundary Sources
conditioning/minimax/context_loop/upscale
MiniMax H3 Pixel Continuity • Experimental Boundary Export
conditioning/minimax/context_loop/upscale
MiniMax H3 Pixel Continuity • Boundary Experiment
conditioning/minimax/context_loop/upscale
MiniMax H3 Pixel Continuity • Finish
conditioning/minimax/context_loop/upscale
MiniMax H3 Pixel Continuity • Protect Tail
conditioning/minimax/context_loop/upscale
MiniMax H3 Project Asset Carousel
conditioning/minimax/context_loop/project
MiniMax H3 Project Asset Carousel (Tree)
conditioning/minimax/context_loop/project
MiniMax H3 Reference Video Fade (Experimental)
conditioning/minimax/context_loop/experimental
MiniMax H3 Reference Video Prep
conditioning/minimax/context_loop
MiniMax H3 Review Gate Relay
conditioning/minimax/context_loop
MiniMax H3 Scene Data Extract
conditioning/minimax/context_loop/references/prompt_driven
MiniMax H3 SelfLift Project — Experimental
conditioning/minimax/context_loop
MiniMax H3 SelfLift Seed Hunt — Experimental
sampling/minimax/context_loop
MiniMax H3 SelfLift Tiling — Experimental
sampling/minimax/context_loop
MiniMax H3 Semantic Anchor Bundle
conditioning/minimax/context_loop/references/semantic
MiniMax H3 Semantic Anchors (Internal)
conditioning/minimax/context_loop/references/internal
MiniMax H3 Semantic Picture Anchor
conditioning/minimax/context_loop/references/semantic
MiniMax H3 Source Timeline
conditioning/minimax/context_loop/media
MiniMax H3 Source Timeline Scene Preview
conditioning/minimax/context_loop/media
MiniMax H3 Tagged Audio Ref
conditioning/minimax/context_loop/references/prompt_driven
MiniMax H3 Tagged Motion Ref
conditioning/minimax/context_loop/references/prompt_driven
MiniMax H3 Tagged Motion Ref (Lazy VIDEO/Path)
conditioning/minimax/context_loop/references/prompt_driven
MiniMax H3 Tagged Motion Ref (Source Timeline)
conditioning/minimax/context_loop/references/prompt_driven
MiniMax H3 Tagged Picture Ref
conditioning/minimax/context_loop/references/prompt_driven
MiniMax H3 Tagged Ref2VA
conditioning/minimax/context_loop/references/prompt_driven
MiniMax H3 Tagged Scene Options
conditioning/minimax/context_loop/references/prompt_driven
MiniMax H3 Tagged Video Ref
conditioning/minimax/context_loop/references/prompt_driven
MiniMax H3 Upscale Reference + Prompt Override
conditioning/minimax/context_loop/upscale
Readme
<p align="center"> <img src="assets/minimax-h3-context-loop.svg" alt="MiniMax H3 Context Loop 0.7 — scene plans that survive the render" width="100%"> </p>

ComfyUI MiniMax H3 Context Loop

Build a multi-scene MiniMax H3 video with one reusable sampling graph. Every scene can be reviewed, retried, checkpointed, resumed, and assembled later.

Start here · Node guide · Choose a workflow · All documentation

0.7.0: the tested nightly/RC is now the stable release on main. See the release summary, shareable improvements table, migration notes, and validation record. Back up workflows and projects before updating. The Registry package ID retains its historical contex-loop spelling for compatibility.

What this pack does

  • Groups full mix, vocals and instrumental tracks: vocals drive lip-sync while the full mix stays the soundtrack, with a per-scene On/Off control.
  • Runs one scene at a time through the same H3 sampler body.
  • Carries visual motion, generated sound, or protected source audio between scenes according to a simple Generation Profile.
  • Saves each accepted take to disk, so a stopped or failed run can resume. See cancellation and scene-level resume for DeRoPE/upscale checkpoints and recoverable VIDEO PNG publication.
  • Provides scene review, alternate takes, branch management, final assembly, masked editing, and deferred upscaling.
  • Captures a frame from a saved Review Gate preview into the Project Asset Carousel as a new tagged picture, without replacing the original take.

Models are not included.

Context Loop execution and recovery

  • Context brush. In Plan Studio → Context → Picture, use Weaken context… to paint fixed regions that may change more under AV Mask. Usage and limits.
  • Optional top-level requeue. Examples use recursive execution by default. For a separate prompt boundary between accepted scenes, enable top-level requeue in Loop End and ComfyUI settings. See execution modes for setup and limits.
  • Reference propagation fix. Valid prompt @tags again see the connected Tagged registry during preflight without rewriting prompt text or storing reference data in the Plan.
  • Crash-safe review and resume. Review snapshots stay visible after a refresh or restart, and durable handoffs/manual resume keep the same Plan semantics while avoiding duplicate queues.
  • Migration guidance. The original Plan remains supported. Removed legacy nodes and controls are listed in the 0.7 migration guide.

Install

From ComfyUI/custom_nodes:

git clone https://github.com/seitanism/ComfyUI-H3-Motion-Context-MultiRef.git
git clone --branch main \
  https://github.com/ethanfel/ComfyUI-MiniMaxH3-Context-Loop.git

Restart ComfyUI after cloning or updating either pack. A current ComfyUI build with native Add Guide for MiniMax H3 support is recommended. ffmpeg on PATH gives the best review and assembly support; ComfyUI's PyAV is used as a fallback where supported.

The MultiRef pack provides the maintained public Motion Context node. Context Loop uses it automatically for compatible Guide scenes and keeps its own specialized fallback for loop-only modes.

Make your first video

  1. Open T2V Normal in ComfyUI.
  2. Select the H3 diffusion model, text encoder, video VAE, and audio VAE.
  3. In Plan, give the run a unique run_name and edit the scene prompts.
  4. Keep the workflow's default visual continuity and generated-audio settings.
  5. Queue the workflow. Preflight checks the plan before the models load.
  6. At Review Gate, choose Approve & continue, Retry, Reroll seed, or Approve & stop.
  7. The active Assemble node writes the final MP4 after the last scene.

To extend a running Plan, append scenes before approving its last scene. With Loop Start's scene_range left blank, Approve & continue finishes the current run, then queues the updated workflow at the first appended scene using the saved checkpoint. Keep that workflow and branch open until it queues. Explicit scene ranges and Approve & stop do not automatically extend the run.

To reuse a still as a reference, scrub the saved Review Gate preview, click Capture frame…, check the destination project and tag, then Save to Carousel. Reusing a tag creates a numbered take. Capture requires ffmpeg and follows the destination project's workflow-ownership rules.

For a screen-by-screen explanation, expected output paths, and common first-run problems, use the Getting started guide.

For disposable batch renders, Assemble has an opt-in delete_checkpoints_after_assembly setting. It frees checkpoint space only after a completed export. Leave it off if you need resume, latent upscale, or checkpoint-based reassembly later.

Choose a workflow

| I want to… | Open this workflow | |---|---| | Start simply with reference pictures | Ref2V Basic — direct image loaders | | Manage project references, scenes and optional source audio | Carousel / Studio | | Generate from text | T2V Normal | | Animate an opening image | I2V Normal | | Move from a first image to a last image | FL2V Normal | | Inpaint part of a video | Masked Video Inpaint | | Continue an existing clip | Masked AV Extension — Single Clip | | Continue a reviewed chain | Masked AV Extension — Chain | | Generate the gap between two clips | Two-Clip Masked AV Bridge | | Upscale a saved run | Deferred upscale workflows |

Prefer explicit reference-loader wiring? The manual Tagged examples are available separately. For SelfLift, use the Seed Hunt example with review enabled or disabled.

The 0.7 release uses the maintained 0.6-named workflow catalog, rebuilt for this checkout's nodes. Choose Normal for Production Plan and Scene Prompt Editor. Studio adds Plan Studio, Project Asset Carousel, the rich prompt editor, and Checkpoint Manager; it does not change the generation graph. Pre-0.6 examples were retired in 0.7 and remain available in Git history. See 0.7 migration notes.

How the graph is organized

<p align="center"> <img src="assets/workflow-overview.svg" alt="Context Loop node flow with active generation nodes and a muted recovery branch" width="100%"> </p>

Only the current scene enters the sampling body. Loop End either starts the next scene or emits a manifest for Assemble.

The supplied generation workflows also contain a muted recovery branch:

  • Muted nodes are present but do not execute. The grey dashed Load Manifest → Assemble later pair is intentionally muted during normal runs.
  • Bypassed nodes pass a compatible input through without applying their normal operation. Some optional attention nodes in upscale examples ship bypassed intentionally.
  • To assemble an existing run without rendering, unmute the recovery pair and queue its Assemble node. No sampler graph needs to run.

The diagrams use the same idea as a disabled-pack node preview: sockets remain visible so you can understand the wiring even when the node does not execute. See How disabled nodes are shown.

Core nodes

| Node | Main input | Main output | Use it for | |---|---|---|---| | Generation Profile | Continuity and audio choices | chain_policy | Choose normal behavior in two controls. | | Plan (Modern) | Scene prompts, organized settings, required policy | plan | Define the production without legacy fallback controls. The original Plan remains available for existing workflows. | | Preflight | plan | checked plan, ready, status | Catch problems before model loading. | | Loop Start | checked plan | flow, state | Start or resume a run. | | Current Shot | state | prompt, seed, timing, size | Drive the current scene. | | Chain Context | state, conditioning, VAE, latent | conditioned latent and trim count | Add the selected continuity. | | Segment + Checkpoint | state, frames, sampled latent | segment | Save a take and its resume state. | | Pending Review | one defer toggle | pending_review | Optionally store a complete candidate batch for later review without leaving an execution waiting. | | Review Gate | state and saved segment | reviewed segment | Approve, retry, reroll, or stop. | | Loop End | flow, state, frames, latent, segment | manifest | Advance or finish the loop. | | Chapter Delivery | manifest and Export current chapter toggle | scoped manifest | On exports the chapter containing the last generated scene, including unfinished chapters. Off exports everything in the incoming manifest. Automatically follows new chapters. Review Gate's Approve & Stop partial export follows the connected toggle too. | | Assemble | manifest | video_path | Build the final MP4. |

The Node guide lists the important sockets, settings, reference nodes, recovery tools, masking nodes, and advanced groups.

Dialogue audio for one scene

In Plan Studio, select a scene and choose Lip-sync source · this scene only. Pick an audio file from the Project Asset Carousel (use Refresh audio after importing it). This turns that scene's Lip-sync on. The file can remain disabled for prompt tags; it does not need to become the project's Source track.

Audio file start selects the position heard at the first delivered frame, snapped to 1/24 second. AV context remains before that position. Short audio is padded with silence and longer audio is cut to the scene; scene timing and other scenes' sources do not change. Editorial trims/slips move dialogue with the picture.

With a Source final soundtrack, choose dialogue over the project track (default) or replace the track during this scene. Generated output uses the dialogue once; None remains muted. Source, offset and mix choice are saved with the generated take and retained for checkpoint recovery, chapter delivery and upscale export. Keep the carousel audio file: saved exports reference that original asset. The player previews the current Plan selection through its Source track / scene dialogue monitor; regenerate the scene after changing its dialogue source. Choose Inherit project timeline to return to the existing source behavior. Existing workflows without a scene source keep their previous behavior.

Important behavior

  • Collapsible Studio chapters. Use ▾ beside a chapter title to fold its scenes into a compact group. Click the group to play/scrub the chapter on a local timeline, including trims, ALTs and internal black gaps. Folding is saved with the workflow and does not alter generation or exports. See chapter folding and playback.
  • Chapter resolution. Click a chapter marker in Plan Studio, then choose Inherit from Plan or set its Width / Height (multiples of 32). Connect Current Shot width/height to the H3 conditioning node. A locked saved scene pins its entire chapter to its original size; changing the Plan default can then affect Chapter 2 without changing Chapter 1. Unlock the saved scenes before explicitly changing their chapter's size. Existing media is not resized. Native AV/latent video context cannot cross different sizes: use zero video context at that boundary. Export different-sized chapters separately through Chapter Delivery; mixed-resolution whole-run assembly is rejected.
  • run_name identifies a production and its checkpoint history. Use a new name for a new production; keep it unchanged to resume.
  • Preflight rejects incompatible resume state instead of mixing checkpoints produced with different generation inputs.
  • Accepted scene media, manifests, and recovery data live under ComfyUI/output/h3_chains/<run_name>/.
  • Uploaded project assets live under ComfyUI/input/h3_projects/<run_name>/ and are mirrored into the run for recovery.
  • Browser-driven asset imports are confined to media listed from ComfyUI input, another project, or an H3 recovery backup. Move other server files into the configured ComfyUI input directory before importing them.
  • Direct prompt optimization allows OpenAI, Gemini, and OpenRouter by default. A server operator can add exact provider origins, including a local API, before startup with a comma-separated H3_PROMPT_OPTIMIZER_ALLOWED_ORIGINS value such as http://127.0.0.1:1234,https://api.example.com.
  • New projects put scene MP4s in generation/clips/ and assembled videos in exports/videos/<scope>/. Existing projects keep their original paths, including final/. Assemble can also copy to the regular ComfyUI output folder. See simple layout and optional copy conversion.
  • The exact saved checkpoint supplies the next scene's continuity. Preview or assembly filters never rewrite that checkpoint.
  • Plan Studio can render a picture-only Alternate final-cut take without changing downstream scene ancestry or audio. See Runs and recovery.

Documentation

| Task | Guide | |---|---| | Install and render the first scene | Getting started | | Understand nodes and sockets | Node guide | | Pick an example | Workflow catalog | | Manage a project's media library | Project Asset Carousel | | Write scenes and prompts | Scene authoring | | Choose visual/audio continuity | Audio and continuity | | Use tagged references | Tagged references | | Retry, resume, recover, or assemble | Runs and recovery | | Inpaint, outpaint, extend, or bridge | Masked editing | | Check runtime compatibility | Compatibility |

Advanced implementation, migration, provenance, and research references are listed in the documentation index.

Origins and license

This project began with NikoDemon80's H3 Motion Context and grew into a separate checkpointed production-loop pack. Feature origins are mapped in Feature traceability; exact upstream revisions and licenses are in Third-party notices.

GPL-3.0. See LICENSE. Contributions are covered by CONTRIBUTING.md.