MiniMax-H3 Drama

Plugin minimax-h3-drama in chiphoton/MiniMax-H3-Codex-Drama. Commands read from the repo's manifest — 5 days ago.

Skills (27)

• canvas-adviser

  Set up, launch, troubleshoot, and use the local Codex Drama web canvas. Apply when the user asks about the Canvas plugin, its environment, vd-workflows, provider connections, project import/export, or Codex Plan text/image nodes. For full video production, use available Drama production skills.

• canvas-builder

  Plan, build, and revise Canvas workflows from chat. Place attachments and connect typed ports.

• layout-optimizer

  Arrange Canvas cards into stages, avoid overlap, reduce wire crossings, and clarify titles.

• sketch-to-h3

  Build a canvas that turns a sketch and short brief into a ComfyUI reference, an Ollama prompt, and a MiniMax H3 video.

• 3d-animation-short-generator

  Plan stylized 3D animated shorts with the official MiniMax workflow, adapted from Hub canvas into Codex briefs, character and scene locks, shot tables, storyboards, H3 prompts, and production handoffs. Use for complete animated narratives, not a single generic shot or photorealistic live action.

• 3d-animation-short-generator

  Create complete stylized 3D animated shorts from a story idea through an ordered production workflow covering project brief, story outline, character and environment cards, standardized shot planning, text or optional pencil storyboards, video-model selection, single-shot generation, assembly, BGM m

• brand-promo-video-generator

  Plan brand-safe promotional videos with the official MiniMax workflow, adapted from Hub canvas into Codex truth sheets, provenance manifests, story spines, beat plans, prompts, and production handoffs. Use for launches, products, apps, websites, shops, and campaigns; do not invent claims or brand as

• co-op-game-intro-generator

  Design two-player co-op game menu or opening animations with the official MiniMax workflow, adapted into Codex confirmation-image prompts, identity and UI locks, event timing, and an H3 video handoff. Not for playable game development or multi-page interfaces.

• h3-prompt-writing

  Write MiniMax H3 video generation prompts for T2VA, I2VA, FL2VA, L2VA, and Ref2VA. Use when rewriting multimodal requests into H3 prompt structures, composing integrated_multimodal_description, overall_soundscape, and non_diegetic_music, aligning keyframes, or defining reference labels for images, v

• handdrawn-live-video-generator

  Write surreal single-scene H3 video concepts that blend rough glowing hand-drawn animation with live-action spaces, using the official MiniMax workflow adapted for Codex. Use for continuous physical contact, morphing, escape, and delayed handheld chase motion; not polished CG, horror, or multi-scene

• minimalist-product-ad-generator

  Plan premium minimalist product-ad shorts with the official MiniMax workflow, adapted from Hub canvas into Codex product facts, narrative spine, copy, independent visual anchors, beat storyboards, H3 prompts, and production handoffs. Not for talking-head ads, generic editing, or complex demos.

• music-video-subtitle-generator

  Plan music videos and emotional shorts where music, locked lyrics, beat timing, spatial typography, references, performance, and camera language work together, using the official MiniMax workflow adapted for Codex. Use for lyric-led or typography-led MVs, not ordinary subtitle transcription.

• paper-collage-explainer-generator

  Plan tactile halftone paper-collage explainers with the official MiniMax workflow, adapted from Hub canvas into Codex production plans, visual metaphors, still prompts, stop-motion shot prompts, audio policy, QC, and assembly handoffs. Not for presenter ads, editable layers, or generic prompt-only s

• papercraft-stop-motion-explainer

  Plan tactile layered papercraft and miniature stop-motion explainers with the official MiniMax workflow, adapted from Hub canvas into Codex creative directions, paper assets, preview prompts, storyboards, H3 prompts, sound plans, and production handoffs. Not for standard cartoons or live action.

• compress-video

  Compress or convert a private local video with FFmpeg while keeping its visual and audio content inaccessible to the agent and off network or cloud services. Use for content-blind local video compression; do not use when the task requires watching, listening to, transcribing, describing, or judging

• sanitize-metadata

  Audit and remove embedded metadata, EXIF, GPS, author/device identifiers, timestamps, descriptions, and hidden previews from private local images or videos without exposing metadata values or media content to the agent or cloud services. Use for content-blind local metadata sanitization; do not use

• slice-video

  Split a private local video into time-based files with FFmpeg while keeping its visual and audio content inaccessible to the agent and off network or cloud services. Use for content-blind local video slicing, including 10- or 15-second chunks; do not use for scene-aware, dialogue-aware, or visually

• minimax-h3-adviser

  Advise, enhance, diagnose, and route MiniMax H3 video or audio prompts across official H3 style workflows, text-to-video, first/last-frame, multimodal reference-to-video, precise video-editing, verified 32x32 audio-only generation, and optional ComfyUI execution. Use when a user has a media idea, dr

• minimax-h3-audio

  Create, enhance, diagnose, and optionally execute MiniMax H3 audio-only prompts through the verified fixed 32x32 ComfyUI proxy. Use for prompt-generated dialogue, narration, announcements, ambience, foley, robot sounds, or animal calls when no reference media is required; use R2V for reference-contr

• minimax-h3-comfyui

  Prepare, validate, submit, monitor, and retrieve MiniMax H3 text-to-video, first/last-frame image-to-video, reference-to-video, and verified 32x32 audio-only workflows on a local or self-hosted ComfyUI instance. Use when a user explicitly asks to run, generate, execute, queue, preview, or fetch Mini

• minimax-h3-drama-producer

  Produce or resume complete profile-driven videos in Codex with GPT-Image visual development, MiniMax-H3 shot generation through ComfyUI, optional voice and captions, sound design, deterministic FFmpeg editing, local delivery, and technical plus visual QC. Use when a user asks Codex to turn a story,

• minimax-h3-frame-to-video

  Create, enhance, or diagnose MiniMax H3 first-frame and first/last-frame animation prompts when supplied images are literal opening or closing frames. Use for animating posters, key art, portraits, UI mockups, product stills, or controlled transitions that must begin from one exact image or travel b

• minimax-h3-profile-distiller

  Distill one or more local reference videos into a safe, declarative MiniMax-H3 Drama production profile with evidence, confidence, storytelling grammar, shot patterns, audio and caption behavior, deliverables, and QC rules. Use when a user asks Codex to analyze, reverse-engineer, extract a reusable

• minimax-h3-reference-to-video

  Create, enhance, or diagnose MiniMax H3 multimodal reference-to-video prompts using images, videos, and audio for identity, product design, style, location, storyboard, motion, camera, editing rhythm, performance, music, or voice. Use when multiple assets need explicit jobs, unwanted cross-reference

• minimax-h3-text-to-video

  Create, enhance, or diagnose MiniMax H3 text-to-video prompts when the entire video should be invented from language without image, video, or audio references. Use for prompt-only cinematic shots, ads, animation, motion design, social clips, UI demos, or other H3 concepts that need a timed action pl

• minimax-h3-video-editor

  Create, enhance, or diagnose precise MiniMax H3 prompts for editing an existing video while preserving everything outside requested changes. Use for subject or object replacement, removal, wardrobe changes, background replacement, relighting, localized VFX, text or signage changes, dialogue or voice

• qwen-image-edit

  Prepare and run the pinned Qwen Image Edit consistency workflow through local ComfyUI with one or two reference images, an exact edit prompt, deterministic workflow copies, dependency preflight, monitoring, and result retrieval. Use only when the user explicitly invokes `$qwen-image-edit` or `$qwen-

MCP servers (1)

• comfyui

  runs: npx -y [email protected] --comfyui-url http://localhost:8188

Similar plugins