Major update
Hand Tie Clips 2.0 — Native MiniMax H3 Chains in ComfyUI

I highly suggest feeding the git/hf page to a LM to study all the respective settings for control within your planning itself. It has a LOT of fine tune controls available now. This is NOT a plug-and-play one click setup, requires some tinkering to achieve what you want.

MiniMax H3 produces stunning six-second clips, but building longer sequences is notoriously messy—character faces drift, lighting shifts, and audio restarts on every generation. Hand Tie Clips runs your entire sequence in a single queue: it passes final frames forward and locks character consistency from start to finish.

Key Features

• 🎙️ Continuous Voiceover: Drop in a single audio file. Every shot automatically lip-syncs to its own slice without audio resets, seam cuts, or manual re-timing.

• 🧍 Persistent Character Consistency: Feed it one reference photo. The node carries the identity through every shot, preventing face drift across the chain.

• 🎬 Beat-Based Directing: Write simple one-line actions per shot ("She turns to the window," "He walks to the counter"). The node handles prompt generation, camera movements, and cut transitions.

• 🔄 SWAP Mode: Combine motion from a video with identity from a photo—the source clip drives movement and scene context, while your reference photo drives the person.

• ✍️ Built-in Scripting (WRITE Tab): Connect a local LLM to automatically draft multi-shot sequences directly from a short concept paragraph.

Quick Start

1. Drop the ComfyUI-Hand-Tie-Clips folder into your custom_nodes/ directory and restart ComfyUI.

2. Load the included starter workflow.

3. Add a character photo to the REFERENCES tab, write 3 shots, and hit queue.

Includes starter and showcase workflows out of the box, with detailed tooltips for every setting.

Needs

• ComfyUI new enough to include Add Guide for MiniMax H3 (MiniMaxH3AddGuide)

• A ref2va (or hybrid ref2va) checkpoint — fl2va has no reference rows

• Video VAE + audio VAE + MiniMax text encoder

• Recommended: ComfyUI-H3-Motion-Context for the latent join. Without it the node falls back to MiniMaxH3AddGuide, which still works and still chains — it is a different join, so a seam you are comparing against someone else's render may not be the same code path.

The two shipped workflows wire the turbo stack this node is actually run with, because an example without it is not the graph anyone uses:

UNETLoader -> LoRA Loader Stack -> H3 AdaLN LoRA Fix -> MiniMax H3 Low VRAM
           -> H3 SLA Attention -> Model Preview Override -> Hand Tie Clips

packnodes inside workflow :
ComfyUI-PlagueKind-NodesLoRA Loader Stack, H3 AdaLN LoRA Fix, H3 SLA Attention
ComfyUI-KJNodesMiniMax H3 Low VRAM Attention (experimental), Model Preview Override

Realistic Limitations

• ⚠️ Quality Drift: Image quality degrades on long chains. 3 to 5 shots is the realistic ceiling before colors and textures begin to wander.

• 📊 Degradation Study: The README details a 10-run, 9-shot study measuring exact failure points and identifying settings that yielded no impact.

Requirements & Links

• ComfyUI Build: v0.34.0 or newer (required for H3 support)

• Dependencies: None (no extra Python packages needed)

• 🔗 GitHub Repository & Full Docs: https://huggingface.co/sandpies/ComfyUI-Hand-Tie-Clips