comfyui-obvpm-timeline
A MiniMax H3 ComfyUI workflow and nodes that allow generating, extending, prepending, bridging and editing videos in an easy to use UI.
The timeline node is like a mini video editor.
And it also supports creating seamless looping videos.
Updates
0.1.1-004
Updated defaults, fix model wiring disconnected for some users issue
Watch the Tutorial
The best way to learn how to use the Timeline and workflow is by watching the YouTube tutorial video:
Watch on YouTube: https://youtu.be/kqP09NfJXaQ
Features
The main node is the Timeline node: the clips you generate are placed on it, and it is where you arrange, cut and preview them, and pick which clip the next generation continues from.
Generate a clip, see if you like it, add it to the timeline, then extend from it. Any part you don't like can be redone later.
Every generated clip is saved together with a motion context file (.mctx) that holds its latents. Extensions continue from those original latents using latent masks, not from re-encoded pixels, so there are no lighting changes or flickers at the joins. And because the files sit next to the clips, a clip can still be extended at full quality days or months later.
Generating
Extend a clip seamlessly.
Prepend: generate what happens before a clip
Bridge: generate what happens between the end of one clip and the beginning of another. This lets you redo any section of the video, and bridging onto a fresh generation brings the quality back if it has drifted.
Loop: bridge the last clip back to the first clip to make a seamless looping video.
Extend from a cut: if a clip ends badly, cut off the bad part and extend from the good part. Snap cuts keeps cuts on the latent frame grid.
Clips that have no motion context (external clips, clips from other workflows) can be extended too, with seam improvements applied automatically.
Result preview: plays each new clip joined to its neighbours and rates how seamless the join is. From there you add it to the timeline, delete it or dismiss it.
Model preview override: Integrated into the result preview. Lets you quickly see if a generation is going wrong.
Timeline
Mini Video Editor: Drag in clips from anywhere, reorder them by dragging, trim the ends, cut left / cut right at the playhead, undo cuts, and open gaps.
Quick preview: plays through the clips right away. Full preview assembles them into a single video file, losslessly where possible. Export saves the finished video.
Load Settings, Prompts from Clips: restores the prompt, seed, settings and references that a clip was generated with, so you don't have to keep track of them yourself.
Swap takes: Swap between previous takes generated for the same extension, so you can go back to them and swap between them on the timeline.
The sequence is also available as text, for copying a timeline into another workflow.
Upscaling
A latent upscale and refine of the whole sequence in one pass, so details stay consistent across the joins and the result is still seamless.
Sampling is done in windows, so long or high resolution videos still fit in VRAM.
Generate at low resolution for fast iteration, then upscale once at the end. This is optional, you can also generate the first pass at final quality.
Each clip's conditioning is saved with it, so the upscale uses the same references the clip was generated with.
Workflow
Organized for fast and easy use. All inputs are in one area. No pan all over the workflow to change things.
Settings Presets: Allows you to save frequently used settings such as steps, turbo, and sampling settings and control them in one place
Up to four image references, plus video and audio references. (More can be added)
Dependencies
The workflow uses these custom node packs, so install them first (ComfyUI Manager's Install Missing Custom Nodes finds them):
comfyui-obvpm-timeline: Timeline, extend / prepend / bridge / loop generation, and the whole-sequence upscale
comfyui-obvpm: Bundles, Settings Presets, switches and gates, Load Images & Compose
ComfyUI-KJNodes — Set / Get nodes, model preview override, Sage attention patch
Comfyui_Minimax_h3_latent_Upscaler: The latent upscaler used by the upscale pass
ComfyUI-MiniMax-H3-Turbo: Turbo LoRA loader for larryvrh turbo
ComfyUI-Spectrum-MiniMax-H3: Spectrum acceleration
rgthree-comfy: Power Lora Loader
Description
More sensible defaults (vanilla 20 steps) so users get better results by default.
FAQ
Comments (16)
This is the easiest and most reliable method for connecting motion contexts that I have ever used. Thank you very much.
Nice one, have been playing around creating node that did some similar things, looking forward to diggin into this https://github.com/isitrepo/SeamStitch
yours looks alot smoother :D
May I make a suggestion? I would like to be able to specify the file path when exporting the merged video. Since I work over a network, it would be great to have a "Save As" option.
Do you mean "Save As" to select a local folder? Or a folder on the server?
@obvpm I need to set up a local folder. Personally, I run Comfy on my PC and access it via a browser on my MacBook. In any case, I’m very satisfied with it as it is. It’s all thanks to your talent! :)
@kennedysworks Got it. I'll note that as a possible future feature
Whenever I try to run this workflow, it gets to the minimaxh3 reference to video node and throws this error. # ComfyUI Error Report ## Error Details - Node ID: 797 - Node Type: MiniMaxH3ReferenceToVideo - Exception Type: TypeError - Exception Message: TypeError: '>' not supported between instances of 'NoneType' and 'int'
Any idea what might be going wrong?
Please try updating comfyui-obvpm and comfyui-obvpm-timeline to the latest versions. There might have been some fixes that apply to this as I fixed quite a few bugs.
@obvpm That didn't affect it, still the same problem.
@capnreynolds999504 Do you use ComfyUI in a non-english language setting?
@obvpm No, I use english.
@capnreynolds999504 @obvpm Numerous issues are arising since the version update of Comfy UI. In my case, my computer goes black when I try to generate a 15-second video using this workflow. It generates normally again after I downgraded the Comfy UI frontend and version.
@kennedysworks Thanks for the heads up! Yeah, ComfyUI 0.36 version is the more stable version to use now I think.
This is really great. I have been using it for about a week now, you did a great job making this. Thank you for sharing it!
I'd like to suggest an improvement, if possible.
I came across this other workflow https://civitai.red/models/2891077/minimax-h3-ref2video-fast-2-pass-latent-upscale?modelVersionId=3268574 that achieve amazing quality and large generation (i'm currently having 0.8mp outputs, without the RTX upscaling) in a fraction of the time (obviously depending on the size of your references.
I would love if you could take a look, and maybe fine a way to integrate his solution for fast gen and upscaling.
With your version, the upscaling is kinda the weakest part.
For information, i'm running the H3HerosMax_beta5_fp8 14~gb with the 4 steps turbo lora (and an extra step i added on the 2nd refiner sigma)
This could probably even remove the need of the upscaling feature in your node, since it can generate a 12s 0.8mp in under 10 minutes. (may vary, even way less).
What do you think?
Great job 👍
can you make a workflow that works with music?. i can't for the life of me create a long lip sync video without the audio meshing in on itself with each extended take. i use video helper suites audio loader node to set the correct start time and duration but it doesnt really help.

