--- name: varg-previz description: >- 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. license: MIT metadata: author: vargHQ version: "1.0.0" openclaw: requires: bins: - python3 homepage: https://varg.ai compatibility: >- The previz app needs python3 (local server) and a browser; three.js is vendored, no npm. Clip capture needs bun + playwright-core + Chrome/Chromium; the pack build needs ffmpeg. Generation needs the varg MCP connection (https://mcp.varg.ai/mcp) or a VARG_API_KEY. allowed-tools: Bash(python3:*) Bash(bun:*) Bash(bunx:*) Bash(ffmpeg:*) Bash(ffprobe:*) Bash(curl:*) Bash(shasum:*) Read Write Edit --- # varg previz: story → anchors → 3D previz → Seedance v2v 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. ## Pick the depth first | 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 | ## The pipeline (in this order) 1. **Story**: pick a structure for the format and map it onto the timeline (song sections, VO beats or seconds). One story beat per section, the hook in the first 2–3 s. → `references/story-structure.md` 2. **Storyboard**: `storyboard.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.md` 3. **Anchors**: character sheet, product/vehicle sheet with a human for scale, antagonist sheet if any, ONE master plate per location. Close-ups are generated from the master. Once the previz exists, make plates by image-editing a previz render ("keep camera and geometry exactly") instead of from text. → `references/character-sheets.md` 4. **Master scenes**: group shots by location; each scene becomes one or more 4–11 s Seedance runs. → `references/scene-grouping.md` 5. **3D previz**: `python3 /scripts/new_previz.py ` then `python3 /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.md` 6. **Seedance pack**: `build_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.md` Spend nothing before step 6 except cheap anchor stills. Steps 1, 2, 4 and 5 are free, and the director's notes cost least there. ## Hard rules learned the expensive way - **One location = one master plate = one set.** Wide and close coverage of a place share the same set and refs, or faces, layouts and lighting drift between shots. - **References only for what is in frame.** A sheet that also shows the monster pulls the monster into a shot that should not have it, so crop. Never use an exterior still as a ref for an interior scene. When a shot is rewritten, its old still is stale: flag it (`needs_new_still`), do not feed it to the model. - **Narrow frames hide things.** Horizontal half-FOV = atan(tan(vFOV/2)·W/H). At 9:16 and vFOV 55° a subject 17° off-axis is out of frame. Check every camera in the map view: cameras end up inside walls, behind headrests, or inside a subject that walks into them. - **Scale is explicit.** Put a human on every vehicle/product/creature sheet and state the ratio in every prompt (car ≈ 2.5× a person, ship ≈ 5×, monster ≈ hundreds of ships); otherwise models draw a man as big as his ship. - **No text from the model.** "No text, letters, numbers, logos or UI" in every prompt. Lyrics, captions, prices, HUD and logos are drawn later in code (HyperFrames). Text labels are hidden in exported reference clips. - **Price before you promise.** Run `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`). - **Ask before spending and before switching the billing team.** Uploading and generating are outward actions. Test one short run before a batch (`build_pack.py … --runs `). - **Record the director's words verbatim** in `brief.md` with the date; apply each note to the storyboard, scene table, treatment and previz in the same pass so they never disagree. ## Deliverables - `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____.mp4`, `refs/`, `PROMPTS.md`, `requests.json`, `index.html` board, `jobs.json` once submitted, `out/` results) ## Related skills `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).