Hand Tie Clips — Multi-Shot Studio for MiniMax H3

Multi-hop MiniMax H3 video from one ComfyUI node. Author shot cards, manage reference stills and voices on a visual rail, lock or solo-retake individual hops from a lossless cache, run guided character/head swaps, and upscale to 2 MP.

Six consecutive frames crossing the join between Hop 1 and Hop 2 — no cut, flash, or identity jump.

🚀 Launch the Interactive Node UI Demo in Your Browser (docs/demo.html) — Click through Script · Refs · Timeline · Media · Write · Swap and the ⚙ (RUN) render-controls page live, toggle shot locks, solo-retake hops, and inspect the 10-hop hand_tie setup (compatible with both Classic LiteGraph and ComfyUI Vue Nodes 2.0).

New: Sand Tie one-take music video, 2:03, no cuts, song locked

Sand Tie: two people, one 52 s take, street to boardwalk to bench

Sand Tie: 65 s walking selfie, one take, upsampled

Hand-Tie 10x8s example

Hand-Tie music video: 12x15s, one take, the song locked (master_audio_file)

What You Can Do

Tab / Surface	What It Does
🎬 SCRIPT (`Simple` & `Shots`)	Switch to `Simple` mode (`chains = 1`) to paste standard MiniMax H3 `ref2va` / `t2va` 6-field prompts (passed through untouched!) or plain prose for single-clip generations with `realism_boost: on` + `audio_refine: on` — or switch to `Shots` mode to author per-hop cards (5 s – 15 s each) with camera, framing, pace, and join controls.
🖼️ REFS (`@tags` & `RefMod`)	Drop up to 9 character/setting stills straight onto the node. Assign stable `@tags`, subject numbers, per-photo megapixel caps, per-hop schedules (`rides hops`), and per-character voice clips without wiring `Load Image` chains.
🎞️ TIMELINE (Retake Board)	Scrub every rendered hop, inspect the exact join frames, lock the shots you want to keep, or click `⏵` on Shot 3 to re-roll only Shot 3 while Shots 1–2 load from the lossless cache.
🎵 MEDIA (Clips, Voices & Lip-Sync)	Load a starting frame, up to 3 reference videos, 3 voice timbre clips, a background music bed (with auto-ducking), or a Master Audio File that locks lip-sync across the entire film.
✍️ WRITE (AI Draft Assistant — WIP)	Connect a local OpenAI-compatible server (nInfer / LM Studio / llama.cpp) to propose films, draft shot cards, surgically edit individual hops (`Edit shots`), or lay out bar-synced music videos (`Song` → `Lay out`). Note: WRITE is an experimental work-in-progress drafting tool, not a 100% hands-off autopilot — always review the generated beats and photo descriptions before rendering.
🎭 SWAP (Guided Video Swap)	Standalone one-hop character or head swap driven by a reference video's motion and audio (`replace_person`, `head_swap`, `face_only`, `keep_person`) with a free-text wardrobe override box and automatic dual Swap LoRA loading. Leaves your multi-shot `SCRIPT` and `REFS` untouched.
📄 STANDARD (Single-Gen Writer)	One standard MiniMax H3 prompt (T2VA or Ref2VA) for a single generation in `Simple` mode: the model plans a storyboard, you edit it, then it writes the block, checked against the official field contract. Pictures on `REFS` make it Ref2VA.

Three Ways to Join Shots (`pin_mech`)

Mode	Status & Best Use Case	How It Works & Honest Tradeoffs
`motion_context` (Default — Built-In)	Stable — Continuous relays (~5–6 hops on Turbo, ~7–8 hops on non-Turbo with Refine) & multi-scene `restart` cuts	Built directly into Hand Tie Clips (no separate node install required; credit to NikoDemon80's ComfyUI-H3-Motion-Context for the latent-slice + end-aligned audio timeline design). Relays the previous hop's sampler AV latent into the next hop with in-latent head inpainting and distribution locking — and resets cleanly on `restart` cuts.
`hand_tie` (Single-Take Previs)	Public Experimental — Continuous one-location walking vlogs & tracking shots (🎬 10-Hop 72 s Example), and one-take music videos on a `master_audio_file` (🎬 12-Hop 2:51 MV)	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 via 7 per-step Motion-Context keyframes (with muted-window audio stripping and ambient floor locking) so hops never copy texture from each other. Previs Compiler Model (Recommended in `ComfyUI/models/text_encoders/`): Drop any `qwen3vl_4b.safetensors` or `qwen3vl_8b.safetensors` into `models/text_encoders/` — e.g. `qwen3vl_4b_fp8_scaled.safetensors` (Comfy-Org), `qwen3vl_4b` (silveroxides/K2Q), or `qwen3vl_8b_int8_convrot.safetensors` (Comfy-Org). It loads at the start of the run to compile your beats into continuous bridge moments and unloads from VRAM before H3 starts. Caveat: Because every hop must meet its bridge window, beats that ask for a sudden location change, hard camera angle jump, or fast prop action across a join can cause the previs to cut or morph. It works best when the camera and subject flow continuously in one setting, and may occasionally need a seed re-roll if a beat moves too far.
`sand_tie` (One Continuous Take)	New — Long continuous takes with no joins: a whole song as one walking shot (🎬 2:03 One-Take MV), a two-person scene that moves from street to boardwalk to bench (🎬 52 s Two-Person Take), selfie vlogs (🎬 65 s Walking Selfie, upsampled). Song-locked (`master_audio_file`) takes keep lip sync for the whole song.	Each take (every hop up to the next `anchor: restart`) is rendered as one video: its hops are overlapping windows, each drawn continuing the one before it, then the whole take is finished together, so there is no join to see. Retake one hop and only that hop's window is re-drawn between its kept neighbours. `tone_lock` keeps a long take from drifting brighter window after window. Write every hop of a take with the same camera sentence and the action on an `At mm:ss-mm:ss,` timeline (PROMPTING.md, "One continuous take"); WRITE does this for you. Needs a ComfyUI with MiniMax H3 context windows (Comfy-Org/ComfyUI#17425) and `overlap` 0.9 s; without it the node says so before encoding anything. A take decodes into a self-deleting temp file on disk, so a 2-minute take does not have to fit in RAM.

Built-In Finishing (`⚙ RUN` Page)

1. Realism Boost + Audio Refine (Built for `Simple` Mode / Standard `ref2va` & `t2va` Clips)

Using HTC for standard single generations (ref2va / t2va): You don't need a multi-hop chain to use Hand Tie Clips — switch SCRIPT to Simple mode (chains = 1 in ⚙ RUN) and paste your standard 6-field MiniMax H3 ref2va / t2va prompt (subject_definitions:, summary:, detailed_description:, etc.) or plain prose. HTC detects structured H3 prompts and passes them through untouched while giving you the visual REFS rail, realism_boost, and upsample on a single clip — which is what realism_boost: on is built for!
realism_boost: on runs a 2-stage split schedule inside the sampler (at steps = 6: 2 base steps set composition, then 10 realism LoRA steps paint skin and lighting with no fresh noise).
Important Audio Note: Because stage 2 adds no noise, the audio stream only gets those first 2 noisy steps and will sound thin or under-converged on its own. When using realism_boost, turn on audio_refine: on (under the Soundtrack group, 4–5 steps) — it re-samples the soundtrack cleanly while keeping your finished video 100% frozen.

Simple Mode (15s · Realism Boost + 2 MP Upsample) example

2. Refine Pass (`hop_refine: full`) — Honest Limitations

Runs a gentle low-sigma detail pass per hop (supports wiring a stock 30-step H3 DiT to refine_model while your main wire runs a Turbo model).
The honest truth on chain length: Refine holds back relay degradation and keeps joins clean, pushing continuous motion_context chains to 5–6 clips on Turbo before very visible texture changes appear, and 7–8 clips on non-Turbo. Under motion_context, plan to transition to a cut (anchor: "restart") every 4–5 clips or so to maintain the integrity of your textures (or use pin_mech: sand_tie for one continuous take with no joins).

3. Tiled Upsampler (`upsample: on`) & Standalone Node

Enlarges the finished film to 2.0 MP in latent chunks and re-draws it with the Open-H3-Regenerate-2K LoRA: 3 Euler steps from sigma 0.6 on Regen2K's schedule ([0.6, 0.48, 0.3, 0]; 0.8 is the original recipe, sharper but faces drift more), overlapping chunks re-drawn together so joins don't show, sparse attention for speed, at LoRA strength upsample_denoise 0.8 (0 only enlarges), each hop's own text prompt as conditioning (regen2k_cond), seed 42, 102-frame chunks with 17 shared, tiles sized for your GPU automatically (upsample_tile_tokens 0 learns what your card can take; a number fixes it). On by default in the shipped workflows. An optional HTC Upsample Settings node on the upsample_settings socket exposes every one of those numbers. Toggling upsample on a cached chain skips hop generation and runs only the upscaler.

Required Files for Upsampling:

Latent Upscaler (ComfyUI/models/latent_upscale_models/): Download minimax_h3_latent_upscaler_3d_bf16.safetensors from LBH-123-AI/Minimax_h3_latent_Upscaler (or h3_upscaler_lms_v0.1.safetensors).
Regen2K LoRA (ComfyUI/models/loras/): Download open_h3_regenerate_2k_r256pp_bf16.safetensors (3.77 GB, a rank-256 compression of NVlabs' Open-H3-Regenerate-2K LoRA). Pick it (or another Regen2K LoRA) in upsample_redraw.
upsample_dit wire (optional): a separate model for the re-draw, e.g. a plain H3 UNETLoader with no LoRAs. Unwired, the re-draw uses the boost model or the MODEL wire, with hop LoRAs stripped.

The old h3upscale x2 LoRA is retired: upsample_lora is ignored.

Want to upscale any existing video outside a chain? Use the included H3 Video Upsampler (file to file) node (workflows/HandTieClips_Upsample_Video_File.json, flat RAM at any length) or H3 Video Upsampler (finished clip) (workflows/HandTieClips_Upsample_Video.json) or the standalone repo: sandpies/ComfyUI-H3-Video-Upsampler.

Quick Start (60 Seconds)

From your ComfyUI/custom_nodes/ folder:

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

Restart ComfyUI and hard-refresh your browser (Ctrl+Shift+R). Zero pip dependencies.
Drag workflows/HandTieClips_Starter.json onto ComfyUI and point the loaders at your MiniMax H3 ref2va checkpoint, text encoder, and VAEs.
In REFS, drop your character photo onto Row 1 and give it a tag like @maya.
In SCRIPT, write one beat per shot card and press Queue.

Recommended Companion Packs & Optional Models

Component	Where to Get It
Turbo / SLA / AdaLN Nodes	ComfyUI-PlagueKind-Nodes & ComfyUI-KJNodes
Upscaler LoRA & Standalone Pack	sandpies/ComfyUI-H3-Video-Upsampler (HF) · GitHub
3D Latent Upscaler Weights	LBH-123-AI/Minimax_h3_latent_Upscaler (`models/latent_upscale_models/`)
Hand-Tie Previs Compiler (`models/text_encoders/`)	`qwen3vl_4b_fp8_scaled.safetensors` (5.2 GB) · `silveroxides/K2Q (4B)` · `qwen3vl_8b_int8_convrot.safetensors` (9.3 GB)

Prompting Cheat-Sheet (The 5 Golden Rules)

MiniMax H3 samples at CFG 1.0 with no negative prompt — every word you write is added to the scene.

❌ Don't Write	✅ Write Instead
"She stops talking." (Names talking → keeps her talking)	"She smiles with her lips closed. The low hum of the refrigerator."
"No background music, silent room." (Silence = model invents speech)	Always name a specific room tone: "Soft rain on the windowpane, distant traffic hum."
Re-describing hair, face, and clothes on Shots 2, 3, 4	Describe only the new action on Shots 2+ — the reference rail and join pin carry her look.
Ending Shot 2 mid-sentence when Shot 3 should be quiet	Finish the action/sentence at the end of Shot 2 so Shot 3 inherits a settled state.
Leaving the final shot's `tail` on `ongoing`	Set the last shot's `tail` to `settle` or `hold` so the film lands cleanly.

Full authoring guide: PROMPTING.md · Release history: CHANGELOG.md · Credits & Notices: THIRD_PARTY_NOTICES.md

Included Nodes (Category: "Hand Tie Clips")

H3 Ref2VA Chain (HandTieClips): The main studio node (images, audio, info, contact_sheet).
H3 Chain Preview (HTCChainPreview): Live progress, seam side-by-side viewer, and end-of-run A/V drift monitor.
H3 Video Upsampler (HTCVideoUpsampler): Standalone node to upscale any finished video clip with the same tiled latent upsampler recipe.
H3 Video Upsampler (file to file) (HTCVideoUpsamplerToFile): The same upsampler from Load Video straight to an MP4, read, encoded, re-drawn, decoded and saved a chunk at a time so RAM stays flat at any length.
HTC Video Frames (lean) (HTCVideoFrames): Drop-in for Get Video Components with half its peak RAM; start_seconds, duration_seconds, a 24 fps re-time and a resize applied while decoding.
HTC Load Video (path) (HTCLoadVideoPath): Load Video from a file path: no upload, no copy, no 100 MB upload limit; reports resolution, fps (variable-rate flagged), length, codec and audio.
H3 Tiled Upsampler (HTCTiledUpsampler): Latent-input tiled upsampler for custom graphs.
HTC Upsample Settings (HTCUpsampleSettings): Every number of the chain's upsample, on its optional upsample_settings socket; unwired, the defaults (Regen2K from 0.6, stepped joins).
HTC Save Video (long-form) (HTCSaveVideo): Replaces RTX Frame Generation -> CreateVideo -> SaveVideo for long films: streams the frames, frame generation per pair on the GPU, NVENC constant quality, a keyframe on every cut.
H3 RefMod Builder (HTCRefModBuilder): Builds reusable visual/voice reference modules for the REFS rail.
H3 Cache (HTCH3Cache): Residual step cache on the MODEL wire (silveroxides / PlagueKind; see THIRD_PARTY_NOTICES.md).

sandpies/ComfyUI-Hand-Tie-Clips

Hand Tie Clips — Multi-Shot Studio for MiniMax H3

What You Can Do

Three Ways to Join Shots (pin_mech)

Built-In Finishing (⚙ RUN Page)

1. Realism Boost + Audio Refine (Built for Simple Mode / Standard ref2va & t2va Clips)

2. Refine Pass (hop_refine: full) — Honest Limitations