With these Workflows (you'll also need to download my Custom Nodes via the ComfyUI Manager) you can create MiniMax H3 videos of pretty much infinite length by chaining shorter clips together.
I specifically built the Nodepack around the MiniMax H3 FL2VA model.
The main idea is to keep the visual quality and control of FL2VA while allowing you to continue a video over and over again without having to rely on only the last rendered frame.
Starting with v1.4, continuation now uses ComfyUI's native Masked AV Latent Continuation. Instead of asking H3 to recreate the beginning of the next clip from guidance, a safe part of the previous video + audio latent is copied directly into the next generation and protected from denoising.
In my testing this significantly improved continuity between clips and, especially, fixed the small brightness / color changes that could sometimes happen with the older continuation method.
v1.4 also supports flexible H3 conditioning and multiple Qwen Reference Images, so you can use the workflows with different combinations of First Frames, Last Frames and References.
Included Workflows
The following Workflows are included:
1. Start Video
Herrgotts_H3_Infinite_v1.4_01_Start.json
Use this Workflow to create the first Clip of your video.
v1.4 supports flexible H3 conditioning, so depending on what you connect you can use it similar to:
T2VA
I2VA
L2VA
FL2VA
You can provide:
Prompt
First Frame
Last Frame
Up to 9 Qwen Reference Images
First and Last Frames are optional, although for most projects I'd recommend using both.
After generation the Workflow automatically saves the complete Video + Audio Latent that will be used for the next Clip.
2. Continue Video into infinity
Herrgotts_H3_Infinite_v1.4_02_Continue.json
Use this Workflow for every Clip after the first one.
Load the saved AV Latent from your previous Clip, enter your new Prompt and optionally provide a new Last Frame and Qwen Reference Images.
The Workflow automatically analyzes the previous Clip, removes the typical unusable FL2VA tail and selects a safe latent context before it.
That context is then inserted directly into the next generation using the new Native Masked AV continuation method.
After the new Clip finished generating, the new complete AV Latent is saved again and can be used for Clip 3, Clip 4, Clip 5 and so on.
Just make sure you're loading and saving the correct Clip Index.
Using the same Save Index as an existing latent will overwrite that latent, which can actually be useful if you intentionally want to regenerate an individual Clip.
Net New Content
Net New Content is now the default Duration Mode.
This means that if you select roughly 5 seconds, the Workflow tries to give you roughly 5 seconds of new usable content, instead of counting the 39-frame continuation context as part of those 5 seconds.
This requires H3 to generate a somewhat longer latent and therefore increases sampling time, but I think it makes the Workflow much more intuitive to use.
You can still switch back to Total Generation if you prefer the old behavior.
3. 3-Clip Showcase / Auto Stitch
Herrgotts_H3_Infinite_v1.4_03_3Clip_Showcase_AutoStitch.json
This Workflow creates:
Start Video → Continue Video → Continue Video → Final Stitch
all inside one graph.
You'll mainly have to provide:
Starting Frame
Prompts for the individual Clips
Optional Last Frames
Optional Qwen Reference Images
The graph is intentionally structured so you can duplicate the final continuation block for Clip 4, Clip 5 and beyond.
For very long projects I'd still recommend generating individual Clips separately using Workflows 1 and 2, since it's much easier to regenerate only one Clip if something goes wrong.
4. Stitch Saved Chain
Herrgotts_H3_Infinite_v1.4_04_Stitch_Saved_Chain.json
Use this Workflow to combine a longer chain of Clips that you've generated separately.
It loads and processes one saved AV Latent at a time and writes the final sequence directly to MP4.
Because the entire video doesn't need to exist decoded in memory at the same time, memory usage during final stitching stays roughly tied to the size of an individual Clip instead of continuously increasing with the total video length.
This makes it much more practical to stitch very long projects without eventually running into a length-dependent OOM during the final stitch.
Installation
To install the Nodepack, open one of the Workflows and use Missing Custom Nodes, or search for:
Herrgotts-H3-Infinite-Continuation-Suite
or simply:
Herrgott
inside ComfyUI Manager.
Important
v1.4 uses ComfyUI's relatively new native H3 Masked AV support, so you'll need a recent version of ComfyUI.
If the required H3 mask functionality isn't available in your installation, the Node will tell you to update ComfyUI instead of silently falling back to another continuation method.
After updating ComfyUI I'd recommend doing a full restart before using the v1.4 workflows.
Main Features
Easy to use Workflows with an intentionally simple structure so you can rearrange, duplicate and modify Nodes easily.
Native Masked Video + Audio Latent Continuation using ComfyUI's H3 denoise masks.
No decode / re-encode handover between Clips.
Freeze- and brightness-aware Auto Handover.
Safe pre-freeze latent context selection instead of blindly using the final frames of the previous Clip.
Recommended 39-frame Native Masked AV context for stable continuation.
Independent Audio Tail Carryover to improve dialogue continuity across Clip boundaries.
Net New Content duration mode so continuation context doesn't have to reduce the amount of new visible content you requested.
Total Generation mode still available if you prefer shorter / faster generations.
Flexible T2VA / I2VA / L2VA / FL2VA-style starting conditions.
Up to 9 Qwen Reference Images.
Automatic Picture Map for Qwen prompt references.
Repeated Last Frame anchors for visual control and regular quality resets.
Freeze detection for the typical static FL2VA tail.
Video + Audio aware stitching.
Full, Stitch Ready and Final Clip output modes.
Save / Load complete AV Latents including stitch and handover metadata.
Memory-bounded Saved Chain Stitcher for very long projects.
Older v1.3 workflows remain compatible through the included Legacy Nodes.
Why generate shorter Clips instead of one very long H3 generation?
Apart from having much more control, shorter individual generations can also be significantly more practical than asking H3 to create one very long Clip in a single pass.
For example, instead of generating one 15-second Clip you could generate:
5s + 5s + 5s
If something goes wrong in the third section, you only have to regenerate that individual Clip instead of starting the entire sequence again.
Using regular Last Frames also gives H3 a new visual target every few seconds, which in my experience helps a lot with maintaining quality during longer sequences.
If you use the Nodepack or the Workflows, it'd be awesome if you could share your favorite creations!
Have fun Prompting. :)
Description
v1.4.0 replaces the v1.3 guide-based continuation handover with ComfyUI's native MiniMax H3 Masked AV path.
The goal is the same: keep FL2VA's visual quality and First/Last-Frame control while making long H3 chains practical. The difference is that the previous latent context is now copied directly into the next target and protected in-place instead of being reconstructed from guide rows.
What's new
Native Masked AV continuation using ComfyUI's native H3 video/audio denoise masks.
Freeze/brightness-safe source selection: Auto Handover cuts before the unusable FL2VA landing, then snaps to the exact Masked-AV boundary used by both stitching and the next protected video context.
39-frame protected video context by default (~1.625 s at 24 fps / 65 H3 audio-latent ticks). Longer exact context options remain available.
Independent Audio Tail Carryover: video can cut early for freeze/brightness safety while useful original audio remains protected farther into the discarded visual tail. This substantially improves dialogue continuity when a word continues past the visual handover.
Net New Content is now the default Continue duration mode. A requested 5 s Continue targets roughly 5 s of newly generated visible content after the protected head is removed.
Total Generationremains available for the old duration behavior.Flexible v1.3 conditioning remains: T2VA / I2VA / L2VA / FL2VA Start, optional First/Last Frames, and auto-growing Qwen References.
Memory-bounded saved-chain stitching remains available for long projects generated clip by clip.
Recommended defaults
Masked video context: 39 frames
Duration Mode: Net New Content
Audio Tail Carryover: Full Previous Tail
Audio feather: 0 ticks
Auto Handover: Balanced
Safe Tail Bridge: 0
Video crossfade: 4 frames
Audio de-click crossfade: 15 ms
Boundary luminance match: OffNet New Content is a convenience feature, not a speed optimization. It samples a longer total latent so the requested duration remains approximately available as new visible content, which increases sampling time and memory usage compared with Total Generation.
ComfyUI requirement
v1.4 requires a current ComfyUI build containing native MiniMax H3 AV-mask support from PR #15375.
The nodes capability-check the live H3 implementation instead of relying only on a version string. If the v1.4 Continue node reports missing native Masked AV support, update ComfyUI, fully restart it, and reload the browser UI.
Included workflows
Herrgotts_H3_Infinite_v1.4_01_Start.jsonHerrgotts_H3_Infinite_v1.4_02_Continue.jsonHerrgotts_H3_Infinite_v1.4_03_3Clip_Showcase_AutoStitch.jsonHerrgotts_H3_Infinite_v1.4_04_Stitch_Saved_Chain.json
Use the new v1.4 workflows together with the v1.4 nodes because the Continue path now consumes the safe Auto Handover metadata directly.
Compatibility
Older v1.3 guide-based nodes and the existing legacy stitch/save/load registrations remain in the package so older workflows can still load. Experimental later-frame Alignment Recovery was intentionally not included in the release after live testing showed visible motion/alignment errors without adding net-new timeline content.
Validation
110/110 automated tests passed
Python compilation passed
all four workflow JSON files validated
workflow graph links checked
Registry metadata checked at
1.4.0install/source archive contents checked
live testing confirmed the targeted brightness-safe video seam and independent dialogue-tail carryover cases
Have fun Prompting. :)
FAQ
Comments (2)
It works great. Is it possible to add an option to save the clips as projects, so that you could change or modify it later. Also can you save the clips into different folders and what has to be the syntax for the path?
Thanks! You can save the individual Clips of a generation & continuation run by saving the latents in a different folder. I'd recommend just adding folders to the current Latent output folder (should be "h3_continuous" in your ComfyUI Output-Folder, e.g. ComfyUI_windows_portable\ComfyUI\output\h3_continuous). So if you want to save a continuation run: Add a folder in the "h3_continuous" folder, name it any way you want to and move all the latents over to that folder (e.g. ComfyUI_windows_portable\ComfyUI\output\h3_continuous\Project1). If you then start a new continuation run, it'll work normally and leave the old latents in the new folder untouched.
You can also change the output folder by replacing the "filename_prefix" in the save latent nodes. Works the same way any other save node in ComfyUi works. It always uses your output folder as baseline. So if you want to save the latents inside the folder "Minimax" inside your Output folder, you should input "Minimax/clip". If you'd want to save them inside an individual folder inside of the Minimax folder (e.g. "Project-1"), you should input "Minimax/Project-1/clip" and so on.
I'm currently looking into a better way to organize/ automatically recognize and load latents with the nodes. Might add that in a later version if I find a good solution.