- articleWhat does focal length change in an image, what does camera-to-subject distance change, and where does the 'telephoto compression' idea come from?
Two inspected manufacturer sources agree on the structure: focal length (for a given sensor) sets how much of the scene is captured; perspective is set by where the entrance pupil (centre of projection) sits relative to the subject. Panavision states that the same field of view can show different perspective when focal length and distance both change, and Zeiss states that holding subject size constant means roughly doubling distance with doubled focal length. 'Telephoto compression' is therefore, in these sources, the combined result of choosing a longer lens and standing farther back to keep framing; whether the lens alone does anything is not argued by either source in so many words (the Panavision sentence is ambiguous on this, see conflicting_evidence). Practitioner accounts use 'compression' as a look they like (attributed).
- articleWhere can a digitised blank paper animation exposure sheet (X-sheet) from a named studio and date be found in a public collection, and what columns does it show?
The only dated, named-studio X-sheet found in public catalogues is an Internet Archive user upload (UPA New York, 1952; one JPEG, no licence, no text layer, provenance a discontinued blog), so whether it is blank and what columns it has are unestablished without viewing the image. A generic classic layout (Action, Dial, five cel-level columns, Background, Camera; 96 rows = 4 seconds) comes from a 2023 CC BY-NC-ND 4.0 teaching item with no studio or date. Institutional finding-aid examples were not found in limited queries (not proof of absence).
- articleWhat do practitioners state about handing a sequence from storyboards to previs to the live shoot, and what do they say is lost or changed at each handoff?
Practitioners on large VFX productions describe building an animatic from storyboards and script, then techvis to validate camera moves, placement and lenses; on set, operators and DPs went beyond the previs; producers find cut-in storyboards hard to read for feel, keyframed previs cameras feel mechanical, plate eyelines and camera motion force recomposition in postvis, and many postvis shot ideas come from director reviews.
- articleWhat does a Korean-language press account report about a director who draws the full storyboard (conti) before shooting, and what does it say that practice buys on set?
A 2019 Korean press report says the director draws his own storyboards (since his first feature) with camera angle, movement lines, background and even handheld feel, says he will not go to set without one, and relays the DP's credit of a nearly 1,000-cut storyboard for finishing Parasite in 77 shooting sessions; the article links the planning to fewer on-set trials and to keeping the standard labour contract. Causation is the journalist's and DP's attribution, not measured.
- articleWhat does a Ghana-shot independent short's producer/co-director say about low-budget planning, crew, and the producer role on set?
A Ghanaian producer-director-actor says low budgets demand intentional, planned shots and a crew that shares the vision, and describes tracking budget use and crew welfare (being fed) while also acting; no budget figures are given.
- articleHow does an open scheduling tool derive stripboard strip colours and a Day Out Of Days (DOOD) chart, and which status codes does it use?
One open scheduling tool (OpenShotDesigner, GPL) colours strips white for INT/day, pale yellow for EXT/day, pale blue for INT/night and pale green for EXT/night, and builds day-out-of-days cells with SW, WF, SWF, WD (drop) and PW (pick-up) codes; its comments call these industry codes and attribute a one-drop/pick-up rule to SAG-AFTRA, which this review did not check against union or payroll documents.
- articleWhat do first-person storyboard accounts say about shot numbering, camera-move arrows and shot labels, and where do they disagree?
Practitioner accounts tie board panels to script or breakdown numbering but differ: scene number plus a letter per shot (No Film School), or sequential numbers never renumbered with letter inserts such as 12A (storyboard instructor); camera moves drawn as start and end frames joined by one arrow and one label. A feature artist reported avoiding arrows (producer reading).
- articleWhat does a storyboard tool carry into an animatic export for an editor (names, timing, dialogue audio, notes), and what does OTIO core offer to hold what the export drops?
Storyboarder's FCP7 XML exporter names each board clip from its dialogue, else action, else filename, and puts notes into the clip description; the FCPX exporter names clips by filename and assigns an audio role; neither exporter has a scene-ID or shot-label field, so those survive only if carried in names. Storyboarder does not emit OTIO (producer reading).
- articleWhen a screenplay is imported into a storyboard tool (Storyboarder), which script elements become scene data, how are scenes keyed, and what is dropped or modified?
Storyboarder keys Fountain scenes by the #...# scene number and, when absent, writes '#<count>-<uid>#' into the user's script; for FDX it writes a generated Number attribute but keys scenes as 'G<n>' (the scene_number assignment is commented out); scene durations are word-count estimates, not authored timings. A pipeline that diffs or locks scripts should expect the file to change on first open.
- articleWhen I send a Fountain or FDX screenplay into a breakdown/scheduling tool, what comes across (scene headings, characters, tagged elements, revisions, scene numbers) and what must be exported another way?
A plain .fdx import into Movie Magic Scheduling brings only sluglines and speaking characters; breakdown tags need a Final Draft Scheduling Export (.sex). Fountain offers scene numbers, notes, sections and synopses but no tag or revision markup, so a Fountain-only project has no standard carrier for breakdown tags. Revision-mark handling on import is not documented in the pages read.
- articleI have a Fountain or FDX screenplay and need an edit timeline: at which handoffs does a scene number, a clip name or a timecode survive, and where must I carry it myself?
Across screenplay, breakdown, storyboard, animatic and edit timeline, no single identifier is defined end to end in the sources read: scene numbers survive script-to-storyboard, while reel/clip names and timecode become the keys once a cut exists; EDL drops what it has no slot for.
- articleHow do practitioners and guild descriptions say blocking, screen direction and coverage are tracked, and why do they deliberately cross the line?
A guild job description assigns the script supervisor to assist during blocking, record action, positions, angles and coverage, and send a lined script to editorial daily; practitioner reports describe deliberate line-crossing for effect (Libatique and Aronofsky using the two sides of the line to mark a tonal shift in Requiem for a Dream). No primary DGA/ASC source on floor plans or overhead diagrams was found.
- articleWhat does an approved animatic carry into the next stage in documented tools (scene length, panels, soundtrack, markers) and what does it not carry?
Storyboard Pro exports each animatic scene to a Harmony scene of the same length with its panels and soundtrack portion, either as rendered reference frames or as editable drawings, 3D objects, images, videos and camera moves; transitions are dropped and markers carry time, duration and note. Storyboarder writes an ffconcat list with each board's duration in seconds, listing the last board twice for ffmpeg.
- articleWhat is an animatic and what are the first steps to time one from storyboard panels with scratch audio?
An animatic is storyboard panels cut in sequence with a scratch soundtrack to test timing and sync; practice is to order and time panels, play, and iterate while changes are cheap. Storyboard Pro starts every panel at one second (so a new board is a basic animatic), edits durations as H:MM:SS:FF and ripples later panels by default; a Blender tutorial times slides by frame count at 25 fps and later swaps in renders of the same length.
- articleWhat are storyboards, animatics, previs, techvis, stuntvis and postvis, and how does Epic's guide order them?
Epic's Virtual Production Field Guide v1.3 defines visualization as prototype imagery conveying a shot's creative intent, lists pitchvis, previs, virtual scouting, techvis, stuntvis and postvis (techvis about physics and camera data, postvis merging live action with temporary effects), and calls storyboards and animatics precursors to previs. No Previsualization Society definition was available.
- articleHow does an open storyboard tool number boards and shots (1A, 1B...), and how does it derive a shot list with camera setups from boards?
Storyboarder (master 8b81a25c, package 3.0.0) generates shot labels as shot number plus sub-shot letter, restarting at newShot boards (first board always opens a shot), or '<n>A' per board when no flags are set; its shot-list model groups cameras into setups when roll/rotation/tilt differ by less than 60 degrees and x/y/z by less than 6 scene units. Correction to the candidate: the setup numbers produced by getCameraSetups are assigned from a counter reset for every board, so different setups on different boards can share number 1 (code inference, unexecuted); the grouping is real but the numbering is not a stable setup index.
- articleIn Beat 2.1.18, what does a #n# suffix on a Fountain scene heading do, and how are scene numbers shown, locked and unlocked?
In Beat 2.1.18 a trailing #n# fixes (forces) a heading's number; other headings are numbered automatically from the document start value; 'lock' writes ' #N#' into every unnumbered heading and leaves forced ones alone.
- articleWhen a screenplay with locked scene numbers moves between Trelby, Starc, Beat and afterwriting, where are the numbers written and where are they read?
At the pinned commits, Starc (when its scene-number option is on) and Beat write a Number attribute on FDX scene-heading paragraphs, Trelby writes none, and none of the four importers read (Starc, Beat outside tag definitions, Trelby, afterwriting) take a scene Number from FDX, so locked scene numbers such as 12A are at risk of renumbering on any FDX round trip through these tools (static reading).
- articleWhere do the Fountain 1.1 syntax page, an FDX sample, and the BBC Writers format PDFs agree and disagree about screenplay elements, and what could not be read (Nicholl, Final Draft documentation)?
Fountain 1.1 (changelog 14 Mar 2014) marks dual dialogue with a trailing caret on the second character cue; the Final Draft sample .fdx expresses it with a DualDialogue XML wrapper and carries (CONT'D) in three character cues (typographic apostrophe) plus an automatic-continueds setting; the BBC film-format sample prescribes layout (double-spaced action, short paragraphs) and says CONT'D is not essential.
- articleWhat does an openly licensed worked example look like that turns a short written scene into numbered storyboard panels, with each panel mapped to a line of the scene and a stated reason for the shot?
The WikiU Film School lesson on Wikiversity (page revision 2146020, 2020-04-29) gives a complete short scene, "Seduced by the Dark Side!" (nine short prose paragraphs, revision 1878977 of Template:Origscript), and one storyboard of it in 14 numbered panels. Each panel carries a transition or move label (Fade In, Dolly In, Pedestal Down, Dolly Left, Cut To), the dialogue line or stage direction it covers, and for panels 1-13 a first-person note saying what the author wants (for example wide lens for emotional distance, 85 mm then 135 mm for warmth). The text is stated CC BY-SA; the panel drawings are separately licensed (mostly CC BY-SA 2.5, some GFDL, one listed public domain). It is a teaching example by the course author: nothing was measured, and the drawings themselves were not inspected here.
- articleWhat numbers does Writing the Photoplay (1913, revised 1919) give for scenes per reel, synopsis length, footage for action versus inserts, and leader or letter length, and how do those compare with what the 1916 Sargent manual and the 1915 Zuver lessons are recorded as saying in cycle 3?
The book gives ranges, not hard caps. A reel is about 1,000 feet and holds 25 to 50 scenes (40 per reel in the five-reel example, scenes per reel "almost doubled" with close-ups); no word count governs a script, footage does; a five-reel story's action takes about 3,800 to just over 4,000 feet, leaving under 1,000 feet for inserts; synopses shrank from about 250 words (earlier) to "as many words as needed", with 6 to 12 typed pages for a feature and 3,000 to 6,000 words in one writer's method. No numeric cap on leaders was found; the stated limit is qualitative. Against Sargent (1916) and Zuver (1915), as published in other cycle-3 rows, the leaders advice agrees in spirit (state the interval, avoid many time jumps, use letters sparingly), but the scene-count figures are not like-for-like. Label: 1913 practice. The pinned Gutenberg text is the Revised Edition (title page "Copyright 1913 / Copyright 1919"; it mentions 1918 releases and "February, 1919" postage), so some passages are ...
- articleWhat parts did a 1913-era photoplay script submission contain (synopsis, cast of characters, scenario/continuity, scene-plot), in what order and form, and what job did each part do for the editor and director?
Esenwein and Leeds call the whole manuscript the "photoplay script" and say it has three essential parts in this order: the Synopsis, the Cast of Characters, and the Scenario or Continuity of Scenes, plus an optional Scene-Plot on a separate sheet (omitted when a company wants "synopsis only"). The synopsis is the editor's first read and is finalised last; the cast list is a separate division that tags minor characters with scene numbers; the continuity starts on a fresh sheet and numbers every scene. Label: 1913 practice. The pinned Gutenberg text is the Revised Edition (title page "Copyright 1913 / Copyright 1919"; it mentions 1918 releases and "February, 1919" postage), so some passages are 1919 revisions and are not 1913 practice. Excerpts drop Gutenberg italic underscores; line numbers are those of the CRLF file as pinned.
- articleWhat do sunrise, sunset, civil/nautical/astronomical twilight, golden hour and blue hour mean, and which of these have official definitions?
The U.S. Naval Observatory defines sunrise/sunset as the Sun's centre 90.8333 degrees zenith distance (about 50 arcminutes below the horizon: 16 arcminute radius plus 34 refraction) and civil, nautical and astronomical twilight as the Sun's centre 6, 12 and 18 degrees below the horizon. 'Golden hour', 'blue hour' and 'magic hour' have no official definition: the Photographer's Ephemeris compares five apps with golden hour ranging from -4 to +6, 0 to +6 and 0 to +10 degrees of solar elevation, and the SunCalc library sets its evening 'goldenHour' at 6 degrees elevation. A cinematographer's clarification quoted there describes magic hour as the time after direct sun is gone but the sky is bright, close to civil twilight.
- articleWhat do 1990s TV-animation director's notes say about slugging and timing conventions (slug lengths, minimum frame counts, dialogue on twos) and what does the timer hand to layout and animators?
A reposted 1990s TV-animation procedure sheet defines slugs as leader between recorded dialogue, gives a six-step flow from approved board to slugged board for editing, and sets frame rules: anticipations generally at least 8 frames, zip-outs about 2 frames with an anticipation, the first 6-8 frames of a scene hard to read, and dialogue exposed on odd frames because animation is shot on twos.
- articleWhat does a Storyboarder project file store for each board (shot number, timing, layers, camera)?
A .storyboarder file is JSON with project fields (version, aspectRatio, fps, defaultBoardTiming) and a boards array; each board carries uid, image url, newShot, number, generated shot label, time, per-layer image file names and an optional 'sg' 3D scene with camera objects (fixture at file version 2.0.1). Shot labels are generated from board order and newShot flags, not typed; with more than 25 sub-boards in one shot the generated suffixes become irregular (curator trace, unexecuted).
- articleWhich open-source screenwriting apps (Trelby, Starc, Beat, afterwriting) read and write FDX and Fountain, and what licence does each ship under?
Trelby 2.4.16.2 licence statements disagree: LICENSE is GPL v2 text, setup.cfg declares GPL-3.0-or-later and debian/copyright says GPL-2 (curator-read pinned bytes); afterwriting v1.17.3 README states MIT. The Trelby conflict is preserved, not resolved.
- articleHow do storyboards mark camera moves (arrows, zoom lines, labels), and where do sources disagree on move names like truck, track and dolly?
'Truck' is used for Z-axis motion by Toon Boom Storyboard Pro 24 docs, for lateral motion by the IIT Bombay D'source course (archived 2025-03-18), and for following action generally by Penn State Media Commons; no single usage is shared across these sources.
- articleFor keeping one person's face identity across storyboard panels, what do the PhotoMaker and InstantID papers and official repositories measure, what limits and compute do they state, and how are their code and checkpoints licensed?
PhotoMaker (arXiv 2312.04461v1; repo 060b4fc) stacks 1-4 ID photos into one embedding for SDXL; its Table 1 reports PhotoMaker CLIP-I 73.6, DINO 51.5, Face Sim. 61.8 at 10 s on a V100 (IPAdapter has higher Face Sim. 67.1), trained on 8 A100 for two weeks; it handles one person per image and is better at half-length portraits. InstantID (arXiv 2401.07519v2; repo 2145b67) uses one face photo with an InsightFace embedding, a ControlNet-style IdentityNet and an image adapter, trained on 48 H800; the paper has no quantitative table (qualitative comparisons) and the README supports only the largest face. Licence components differ: both codebases are Apache-2.0 (PhotoMaker's LICENSE header mentions third-party components but lists none after the Apache text); InstantID's README says InsightFace face models are non-commercial research only and its released checkpoints are research only, while the Hugging Face card says the project is Apache.
- articleHow does ConsiStory keep one subject consistent across prompts without training, how was that measured, what are its stated failure modes and costs, and can the official code be used commercially?
ConsiStory (arXiv 2402.03286v3, SIGGRAPH 2024 TOG) shares internal activations between the images of a set so that a subject stays consistent without any optimisation step; the first two prompts act as anchors (paper: two anchor images, 0.5 dropout). The authors evaluate 100 image sets with DreamSim (background removed) and CLIP and a 3,000-response two-alternative user study; the quantitative headline is a plot, not text. Timing: 32 s on an H100 for two anchors plus one new image, about 25x faster than The Chosen One (their estimate of 13 min). Stated limits: it relies on cross-attention localisation (failures below 5% in their observation, fixable by changing the seed), images in a set must share one style, and SDXL biases carry over. The official NVlabs code is under the NVIDIA License, which permits only non-commercial use and only with NVIDIA Processors.
- articleHow does a director use storyboards to plan and to persuade a studio (Ridley Scott's account)?
In the archived BAFTA transcript, Ridley Scott says he boards every film and now draws boards himself, and attributes a budget rise 'from four point two to eight point five' to a storyboard (as told; units not stated).
- articleWhat concrete paper tools (scripted shot lines, overhead sketch, shot list) does a cinematographer describe for turning a script into coverage, and who uses them?
Jay Holben's ASC-published guide (2021) describes lining the script with lettered coverage lines (e.g. A - Wide Master) and two thumbnail types, a rough storyboard and an overhead sketch (director's plan / bird's eye) for crew communication.
- articleHow do animatic durations stored in milliseconds, seconds or H:MM:SS:FF convert to frame-exact exposures, and where can rounding drift occur on export?
Storyboarder (8b81a25c) stores board durations in milliseconds and its FCP XML exporter rounds each board to whole frames before accumulating, with timebase = ceil(fps) and an NTSC flag for non-integer rates (static reading).
- articleHow does the Japanese-method digital timesheet workflow (24-frame seconds, 3-frame holds, empty cells, .xdts exchange) work, as described by a studio-method tutorial?
A CELSYS tutorial describing Nippon Animation's digital drawing method sets the timeline to 24 frames per second, reads it horizontally (unlike paper sheets) and exchanges timesheet data as .xdts between the digital timesheet editor and CLIP STUDIO PAINT (Japanese original reinspected).
- articleWhat does The Chosen One (iterative consistent-character extraction from a text prompt alone) cost per character, how was it measured, what failure modes do the authors list, and is there official code?
The Chosen One (arXiv 2311.10093v4, SIGGRAPH 2024) takes only a text prompt, generates a set of images, clusters their embeddings, optimises LoRA weights and two learned text tokens on the most cohesive cluster, and repeats until convergence. The authors report 1-2 iterations, about 13-26 minutes on an A100 (bfloat16), and list the cost as a limitation (about 20 minutes). Consistency is measured as pairwise CLIP image-embedding similarity across prompts and prompt similarity as CLIP score; the main result is a trade-off plot (Fig. 6) plus an AMT user study; the numbers are not in the HTML text. Stated failure modes: identity may not fully converge, a supporting character such as a pet is not kept consistent, spurious attributes can bind to the identity, one character at a time, and simplistic centred scenes. The author project page lists only an 'unofficial' code link. The catalogue already holds this paper as a source entry; this candidate adds the pinned v4 details.
- articleWhat do I need to run StoryDiffusion's consistent-character comic generation for the first time (prompts, GPU, defaults), what does it keep consistent, and what is and is not released or licensed?
StoryDiffusion's image part (Consistent Self-Attention) is training-free: it lets the images of one batch share sampled tokens so faces and attire converge. Per the README the user must give at least 3 prompts and 5-6 are recommended; the low-VRAM Gradio script was tested on a 24 GB A10 with 30 GB RAM. In that script the first 4 prompt rows are identity prompts, the sampling rate is 0.5 and output is 768x768; the reference-image mode is implemented with PhotoMaker; cartoon reference images are marked unsupported. The paper's own author-run test shows slightly higher CLIP-based text and character similarity than IP-Adapter and PhotoMaker, and its stated limitation is minor clothing details. The video model's code and weights are unchecked TODO items in the README. Code is Apache-2.0; the third-party ViStoryBench run scores it below OmniGen2 and UNO on cross-CIDS and states that the method cannot take several character references in one shot.
- articleWhich controls and evaluations from driving and robot world models could carry over to media previs or virtual camera planning, and what has not been shown?
SYNTHESIS, not a measured result. Transferable pieces: (1) camera-pose conditioning from a single image with Plucker rays (Cosmos; joystick-style paths shown qualitatively, scored by pose re-estimation on static scenes); (2) multi-view synchronised re-rendering along arbitrary camera trajectories (Predict2.5 robot multiview; cross-view Sampson error 19.73 px vs 26.61 px baseline); (3) re-driving a logged scene while holding everything else fixed ("world-on-rails", GAIA-3/4 company pages) and embodiment (rig) transfer; (4) edit-by-partial-noising for weather/time-of-day and box-guided agent inpainting (GAIA-2, qualitative); (5) language -> trajectories (DriveDreamer-2). Transferable evaluations: re-estimate the camera path from the output and compare with the commanded path (pose success, rotation/translation error, Vista IDM), Sampson cross-view error with a real-footage floor. Not shown by any source read: film-style subjects (actors, close-ups), cuts, lens language, or non-static ...
- articleHow can an agent check whether a character or location stayed the same across the shots of a generated sequence, and which checks mislead?
Published benchmarks give a concrete checking recipe an agent can follow: detect and crop each scheduled entity per shot from a written registry description, compare crops by DINOv2 embedding to an order-invariant centroid, add a face-ID model for faces, ask a vision-language model a same/different question per crop against an anchor, admit only crops that passed a per-shot fidelity check, and plot similarity against the number of shots between appearances. EntityBench reports that embedding similarity and LLM identity judgement can rank methods in opposite order (DINOv2 face similarity favoured StoryMem 0.792 vs 0.737 while LLM face accuracy favoured EntityMem 0.406 vs 0.226), so one number is not enough. All of this is the benchmark authors' protocol; nothing here was run by this worker.
- articleWhat clip durations and how many actions or shots per prompt do the vendors document at 2026-10-22, and which models or products listed have been retired?
Documented clip lengths at the observation dates: Veo 3.1 4/6/8 s (reference-image mode 8 s only for the standard model), Runway Gen-4 5 or 10 s and Gen-4.5 2 to 10 s, Luma Ray3.14 5 or 10 s (Ray 3.2 API 5 or 10 s), Kling 3.0 3 to 15 s, Sora 2 API 4 to 20 s (retired 2026-09-24). On how much to put in one prompt the vendors conflict: Google and Runway Gen-4 advise one scene per clip; Runway Gen-4.5, OpenAI's guide and Kling 3.0 describe multi-step or multi-shot prompts as supported. Product churn is large: Gemini API Veo 3.1 Preview is shut down on 2026-10-22 and Sora is retired.
- articleBeginner: which question should an agent ask first to choose between a world model, a video generator, a game engine or a 3D scene representation, and which of these tradeoff statements come from primary sources?
No inspected primary source gives a decision procedure; the decision rule below is my synthesis. Sources do state tradeoff facts. Game engine: GameNGen describes games as manually crafted systems running a game loop; the UE 5.1 in-camera VFX page (IA snapshot) describes real-time rendering with camera tracking. 3D Gaussian Splatting: input is images of a static scene; real-time rendering after training; memory and artifacts in unseen regions are limits; the paper says nothing on editing. Action-conditioned world models: GameNGen (20 FPS DOOM, ~3 s history), Genie 3 (24 fps, 720p, few minutes consistency), NWM (planning in known environments). Video generators: physics and consistency measured elsewhere (C3-B006-W3). Proposal: pick by what must stay fixed (see decision table in finding F1).
- articleBeginner: has any film, TV, advertising or game production documented blocking a scene in an engine and then restyling it to photoreal video with a generative model, and what exists instead?
No production evidence was found: no dated first-person studio account, vendor case study with a named production, or measured on-set outcome for engine-blocking followed by generative restyling to photoreal video. What exists is research on game or simulator footage (RealMaster on GTA-V; Cosmos-Transfer on robotics and driving), a simulator integration (CARLA), a previs research prototype already in the catalogue (CinePreGen), and a vendor beta announcement (Reallusion AI Render). Absence is bounded to the searches and sources listed under negative_results.
- articleWhy does Holodeck have the LLM output relations and use a solver instead of coordinates, and what does its evidence actually show about that choice?
Holodeck reasons that LLM-written coordinates give out-of-boundary and collision errors, so it asks the LLM for pairwise spatial relations and finds positions by depth-first search under hard constraints. Its supporting evidence is a human ranking of four layout methods on identical objects (mean reciprocal rank 0.706 for constraints, 0.645 edge-placement, 0.369 random, 0.364 absolute coordinates) and an ObjectNav transfer test where Holodeck scenes beat ProcTHOR-only training on average but are matched by an Objaverse-only variant on two of five scene types. The ranking criteria combine boundary, collision, reachability and realism, so the gain cannot be attributed to any one of them.
- articleWhich dated LED-volume / virtual-production jobs used AI-generated Marble worlds and what outcome does each source actually report, with what evidence class?
Three dated productions were found, all with vendor-authored sources: the World Labs launch video (Pixomondo virtual production team, page dated 2025-11-12), the VIVE Mars / Moonshine Studio XR tests (same date), and Volinga's 'Be Like Me' music-video case (Feb 2026). Each reports speed in prose ('weeks to days', 'one afternoon', 'months to roughly an hour'); none gives a measured baseline, a count of worlds in the final cut, rework, quality ratings, or a Marble version. They are company statements plus named-person quotes, not measurements.
- articleWhat should a first video-generation prompt contain according to the vendors' own guides, and what do they all say to do after the first result?
Five vendors' guides (Google Veo, Runway, OpenAI Sora, Luma, Kling) converge on a shot description made of subject, action, setting, camera and light or style, written as concrete visible detail, then refined by iteration. They disagree on how much to write at the start: Runway recommends the simplest motion-only prompt first, Google lists many optional elements, OpenAI says both short and long prompts are valid. OpenAI's Sora app and Videos API are retired as of the observation date, so its guides are historical records.
- source絵コンテ (Japanese Wikipedia: e-conte, storyboard)
- sourcewonderunit/storyboarder
- sourceStory Architect (Starc)
- sourceFountain screenplay markup syntax
- discussionMethod. Steps 1-8 are stated in the MHLW handout by a JAniCA lawyer-auditor (2023); step 9 is the collector's inference. 1. Pre-production: scenario, character and world settings are produced and the director or 演出 draws the 絵コンテ, the keystone that records acting, movement timing, backgrounds, dial…
- discussionSteps, each attributed. (1) Break the script into breakdown sheets, usually one per scene or part of a scene; each sheet has a scene header and elements assigned to categories such as cast, props and wardrobe [mms Breakdown]. Strip fields available for display include scene number, I/E, set, locati…
- discussionNo primary non-commercial standard was found. Wikipedia's Script breakdown article asserts that 'The film industry has a standard for color-coding' and tabulates element colors and symbols (cast red, stunts orange, extras yellow or green, special effects blue, props purple, vehicles and animals pin…