Hand Tie Clips — multi-hop MiniMax H3 video + audio, one queue

Turn 8-second MiniMax H3 clips into 1-minute+ multi-shot films — same face, same voice, synced dialogue, solo shot retakes, and 2 MP guided upscaling — all from one ComfyUI node.

🕹️ Try the Interactive Node UI in Your Browser (click through Script, Refs, Timeline, Swap & ⚙ RUN before installing)
📦 GitHub Repository · Hugging Face Mirror

🎬 What You Can Do

• Simple Mode (Standard MMH3 ref2va / t2va + Realism Boost): Paste standard 6-field MiniMax H3 ref2va / t2va prompts (passed through verbatim!) or plain prose for single-clip generations (chains = 1) with the visual REFS rail, realism_boost: on (steps = 6 → 2 base + 10 realism LoRA steps) + audio_refine: on (5 steps), and 2 MP Guided Upsampling!

• Shots Mode (Multi-Hop Chains): Write one short beat per card (5 s – 15 s each) with camera, framing, pace, and join controls.

• Visual & Voice Reference Rail (REFS): Drop up to 9 character/location stills and voice timbre clips straight onto the node with @tags and per-hop schedules (no Load Image spaghetti).

• Lossless Retake Board (TIMELINE): Every hop caches losslessly. Lock the shots you like, or click ⏵ on Shot 4 to re-roll only Shot 4 while Shots 1–3 load in 1 second.

• Standalone Guided SWAP: One-hop character or head swap driven by a reference video's motion & audio (replace_person, head_swap, face_only, keep_person) with a wardrobe override box and auto-loaded Swap LoRAs.

• Built-In 2 MP Guided Upsampler: Enlarges the finished film in 3D latent chunks and runs a 2-step tiled redraw with the h3upscale_v2_x2 guide LoRA.

• Local AI Draft Assistant (WRITE — WIP): Connect LM Studio / nInfer / llama.cpp to draft shot cards or bar-synced music video layouts from a 1-sentence brief.

🔗 Two Ways to Join Shots (pin_mech) & Honest Limits

• motion_context (Default — Built-In): Native latent-slice + audio relay (no external custom node needed; credit to NikoDemon80).
  Honest runway with hop_refine: full: Holds clean for ~5–6 continuous clips on Turbo and ~7–8 clips on non-Turbo before texture changes become visible. Plan a transition to a cut (anchor: "restart") every 4–5 clips to keep textures fresh across long multi-scene films.

• hand_tie (Single-Take Previs — Public Experimental): Renders one low-res single-take bridge previs first and ties each full-res hop's opening and closing 0.9 s to those clean windows so hops never copy texture from each other (10+ hops in one continuous take). Best for continuous walking/talking vlogs in one setting; pair with qwen3vl_4b_fp8_scaled.safetensors in models/text_encoders/.

⚡ 60-Second Install

Zero Python/pip dependencies. In ComfyUI/custom_nodes/:

git clone https://github.com/dntpi/ComfyUI-Hand-Tie-Clips.git

1. Restart ComfyUI and hard-refresh your browser (Ctrl+Shift+R).

2. Drag workflows/HandTieClips_Starter.json onto ComfyUI.

3. Drop your character photo onto Row 1 in REFS (e.g. @maya), write your beats in SCRIPT, and press Queue.

Recommended Models & Companion Nodes:

• Turbo DiT: Wuli MiniMax H3 8-Step Turbo + plain minimax_h3_ref2va on refine_model / upsample_dit

• Guided Upscaler: minimax_h3_latent_upscaler_3d_bf16.safetensors (models/latent_upscale_models/) + h3upscale_v2_x2.safetensors (models/loras/)

• Speed / Attention Nodes: ComfyUI-PlagueKind-Nodes & ComfyUI-KJNodes

💡 The 5 Golden Prompting Rules (H3 runs at CFG 1.0 — every word is additive)

1. Never name what you want to stop: Don't write "She stops talking" — write "She smiles with her lips closed. Gentle pool water lapping."

2. Silence must be written as a room tone: An empty soundtrack invents speech. Always name a narrowband sound ("low hum of the refrigerator", "soft breeze").

3. Don't re-describe the face on Shots 2+: Describe only the new action; the reference rail and join pin carry her look.

4. No ellipses (...) inside dialogue: Connect clauses inside speech with a simple comma (,) so the audio branch never fills pause gaps with gibberish.

5. Set the final shot's tail to settle or hold: So the film lands cleanly instead of starting a new gesture on the last frame.