Plan a multi-shot AI video before paid generation by shaping its story, grouping shots, and blocking cameras in a simple 3D animatic. Export scene references and prompts for Seedance video-to-video, helping review timing, geography, and framing before rendering.
Plan and pre-visualise any multi-shot AI video before spending credits on varg - music videos, ads and product promos, UGC-style spots, trailers, short films, explainers. Write the story (Hero's Journey, hook-problem-payoff, 3-act), lock character/product/vehicle sheets and one master plate per location, group shots into master scenes, block every camera in a three.js grey-box previz on the timeline (auto cameras from plain storyboard words like "MCU, 3/4 left, push in"), then export clean previz clips as @video1 references for Seedance 2.5 video-to-video and run one short generation per scene. Any aspect ratio, with or without a song. Use when the user asks for a previz, a 3D animatic, camera blocking or approval, shot lists, scene grouping, character or product sheets, story structure for a clip or ad, or a Seedance video-to-video pack.
Run score Not tested
See how to installReview the instructions the agent will receive before you install.
AI video models redraw the world on every call. A previz fixes what they are worst at, camera, geography, scale and timing, for free before the paid step. It is a cheap grey-box: it approves cameras and blocking, never the look.
Built on a 36-shot, 99 s music video ("I Don't Wanna Pick", 9:16, 133.8 BPM) and tested on a 6-shot product ad.
The app is in templates/previz/; scripts/new_previz.py sets it up in a project.
| project | do |
|---|---|
| 1–3 shots, simple camera | skip the previz: anchors (step 3) + image-to-video |
| 4–15 shots, one or two places, ad / UGC / promo | steps 1–3, auto cameras from the storyboard, a quick approval pass in the previz, pack |
| music video, trailer, short film, anything with geography, scale or many places | everything below |
references/story-structure.mdstoryboard.json is the single source of truth for timing. Every shot gets id, start, end, scene, set, picture, action, camera, plus line (lyric/VO), beat, overlay, source as needed. Cuts on downbeats
when there is a song. → schema in references/threejs-previz.mdreferences/character-sheets.mdreferences/scene-grouping.mdpython3 <skill>/scripts/new_previz.py <project> then python3 <project>/previz/serve.py.
Build one grey-box set per location, check every auto camera, fix the bad ones in the UI, approve each shot,
save, export the camera plan. Check frames in headless Chrome. → references/threejs-previz.mdbuild_pack.py --check, capture clean clips, build the pack (one @video1 per run + only the
stills of what is in frame + prompts), review the board, estimate, then generate. → references/seedance-v2v.mdSpend nothing before step 6 except cheap anchor stills. Steps 1, 2, 4 and 5 are free, and the director's notes cost least there.
needs_new_still), do not feed it to the model.estimate_cost on one real request, quote it as the ceiling, report the billed
cost after (get_job_cost). Check check_balance and which team the connection bills (get_current_team).build_pack.py … --runs <key>).brief.md with the date; apply each note to the storyboard, scene
table, treatment and previz in the same pass so they never disagree.brief.md (the director's words, dated), treatment.md (logline, structure with timings, colour script, recurring
markers, references)storyboard.json + scenes.md (scene table: shots, cut time, gen length, refs, cost)previz/ (three.js app, config.json, data/edits.json, camera_plan.md)previz/seedance/ (pack.json, video/video_XX__<run>__<shots>.mp4, refs/, PROMPTS.md, requests.json,
index.html board, jobs.json once submitted, out/ results)varg-ai (single generations, rendering), hyperframes (text, captions and graphics drawn in code on top of the
clips, final assembly), varg-music-video if installed (song measurement, lip-sync pass, platform masters).
No reviews yet. Tell others what you thought.
No login needed. Share how it worked for you, ask a question, or note where it did not run.
No comments yet. Be the first to write one.
Plan worthwhile local tasks by checking dependencies, effects, resources, and platform boundaries, then execute the exact approved plan. It can use safe parallel work or suitable Apple-silicon backends when the project exposes them.
Turn a winning TikTok or Meta ad into a structured creative test plan. Identify what made it work, plan distinct concepts, set test budgets and review timing, and use funnel metrics to decide whether to stop, iterate, or scale each ad.
Record deferred engineering decisions and temporary workarounds in a debt registry, with context such as effort, ongoing cost, affected area, and payoff trigger. Entries receive short labels so they can be reviewed or dropped later.
Generate or compare AI agent code for LangChain, EINO, AutoGen, AgentScope, and CrewAI using framework-specific templates, API mappings, conventions, and project structures. Reference files include verification dates to help identify potentially outdated guidance.
Investigate a reproducible bug, test failure, or unexpected page behavior, then make a narrowly scoped fix. The workflow calls for a regression test before changing code, verifies the fix, and reports remaining risks and evidence while avoiding unrelated refactoring or feature work.
Build an AI agent project through six collaborative stages, from requirements and architecture to tools, prompts, code generation, and verification. Start framework-independent, then generate a runnable project for frameworks such as LangChain, EINO, AutoGen, AgentScope, or CrewAI.