SandTie PromptRig (H3)
Source repository on GitHub: https://github.com/sandpies/ComfyUI-SandTie-PromptRig · Full multi-hop chain engine: ComfyUI-Hand-Tie-Clips
Stop hand-typing 6-field MiniMax H3 walls of text. Drop SandTie PromptRig (H3) into any stock MiniMax H3 workflow (
Ref2VA,T2VA,I2VA,FL2VA,L2VA, orp-h3-image), pick your cast & director dials in SandTie Studio, and drive eitherpromptat 0 VRAM or nativepositive+latentdirectly.
Why This Exists
MiniMax H3 wants strict six-field prompts (subject_definitions:, summary:, retention_analysis:, detailed_description:, overall_soundscape:, non_diegetic_music:), clean <Picture N> / <Subject N> / <Audio N> binding, zero negations outside <d> dialogue tags, and exact MM:SS.mmm beat pacing. Writing those by hand—or juggling LoadImage chains across every new workflow—kills flow.
SandTie PromptRig (H3) wraps the entire H3 authoring engine from ComfyUI-Hand-Tie-Clips into one plug-and-play ComfyUI V3 node:
- Zero HTC dependency — install alone or side-by-side with
ComfyUI-Hand-Tie-Clipswith zero node, CSS, or HTTP route collisions. - Dynamic
Autogrowsockets — starts with 1ref_image_1pin and expands up toref_image_9(ref_video_1..3,ref_audio_1..3) as you wire nodes, matching stockMiniMaxH3ReferenceToVideo. - Two drop-in modes on one node — run pure
prompt(STRING) into any stock H3 node, or flipwire_modetoDirect H3 Conditioning (+ CLIP/VAE)to output nativepositive(CONDITIONING) +latent(LATENT) directly intoBasicGuider&SamplerCustomAdvanced. - Persistent Reference Bible (
S1..S9) — upload once, run a cached 2.5 MP Eye Scan, assign voice.wavs, and reuse cast across workflows without re-wiringLoadImagetrees.
Two Ways to Wire into Stock MiniMax H3
| Mode | Set wire_mode to |
Wire IN | Wire OUT | Best When |
|---|---|---|---|---|
| 1. Stock Prompt Drop-In | Prompt Only -> Stock H3 Node |
Optional ref_image_1..9 / brief_in |
prompt → MiniMaxH3ReferenceToVideo.prompt / ImageToVideo.prompt |
Dropping straight into FastH3 / stock H3 templates (0 VRAM) |
| 2. Direct H3 Conditioning | Direct H3 Conditioning (+ CLIP/VAE) |
clip, vae, optional audio_vae + Bible or canvas refs |
positive → BasicGuider · latent → SamplerCustomAdvanced |
Casting from Reference Bible without LoadImage spaghetti |
Ready-to-run graphs ship in example_workflows/:
Three Ways to Author
◩ CPU Tie(0 VRAM, Instant) — Deterministic multi-beat H3 assembler combining active dials, camera motion laws, weighted beat timelines (5–15 s), and Reference Bible descriptions. No LLM required.⚡ Quick Tie (1-Pass)/Plan -> Write(Local LLM) — Calls any local OpenAI-compatible server (LM Studio, nInfer, llama.cpp, vLLM) with structured output, 2.5 MP Eye Scan vision context, and ✧ Double-Knot pass-2 continuity verification. PickLM Studio/nInferright next to the status pill (or click⚙) inside Open SandTie Studio to set your URL, Model, and server path.▶ Video -> Beats(30-FPS OpenCV Extractor) — Point at a reference.mp4, optionally trimIN/OUT, and extract motion cadence + camera trajectory + jump cuts directly into timed[Shot N]beats.
Inside SandTie Studio (⬒ Open SandTie Studio)
- 19 Clean-Room Director Dials (2-Tier):
- Primary 8:
Cam(171),Light(71options incl.Soft Natural Light&Soft Natural Window Light),Style(94),Place(127incl. plain enclosed & window bedrooms + combat/dance plates),Wear(149),Action(178incl. blow-for-blowmsfights),Stage(380),Speech(60). - Optics, Grade, Dance & Audio Drawer (11):
Optics(94),Grade(44),FX(106,Delayed Mid/From Start),Dance / Pose(200TikTok, K-Pop idol, waacking/crunk, duet & ensemble flows),Playbook(49),Cast Type(40),Genre(8),Era(17),Accent(30),Ambience(45incl.Pure Music N/A),Music(52).
- Primary 8:
- 114 Built-In Presets + Smart Roll: Domain-locked & aspect-safe (
16:9/4:3/9:16) Surprise Roll, Match Dials from brief keywords, Compose Brief, 47 Clean Showcase Scripts, and ❝ Fresh Dialogue rewrites. - Built-In MiniMax H3 Rules: Zero non-
<d>negations, automatic TTS cleanup (<d>[voice] "..."</d>), semicolon/speech stripping fromoverall_soundscape:&non_diegetic_music:, 12 H3 motion primitives, Open-End Range & Background Plate amplitude laws, and a live7,000-char encoder counter. - All 6 MiniMax H3 Output Formats:
Ref2VA / T2VA,I2VA(0.00 secondsanchor),FL2VA(0.00+ end-mark),L2VA(end-mark),Start Frame Prep(p-h3-image), andStoryboard Beats Only.
Quick Start
- Clone into
ComfyUI/custom_nodes/:git clone https://github.com/sandpies/ComfyUI-SandTie-PromptRig.git - Restart ComfyUI (requires ComfyUI v0.38.0+) and hard-refresh your browser (
Ctrl+Shift+R). - Drop SandTie PromptRig (H3) (under
MiniMax H3) or loadexample_workflows/SandTie_Direct_H3_Conditioning.json. - Optional local LLM writer: click
⬒ Open SandTie Studio→ pickLM Studio/nInfer(or click⚙besideStart / Stop) to configure your URL, model, or server exe (or stay on Instant CPU Tie for 0-VRAM deterministic prompts).
Required Stock Models (for H3 Video Generation)
| Component | Recommended Model | Folder |
|---|---|---|
| Diffusion Model | minimax_h3_ref2va_int8_convrot (or FastH3 OmniRef) |
models/diffusion_models |
| Text Encoder | qwen3vl_32b_minimax_h3_nvfp4_awq |
models/text_encoders |
| Video VAE | minimax_h3_video_vae_int8_convrot |
models/vae |
| Audio VAE | minimax_h3_audio_vae_fp32 |
models/vae |
Credits & License
Built in ComfyUI-Hand-Tie-Clips (MIT).
Architecture and prompting insights acknowledge LD Studio (original PromptMaster layout inspiration), wangweihong/comfyui-cinematic-gallery, and loopforge0/minimaxh3-shots-skills. See THIRD_PARTY_NOTICES.md.
