- articleWhen breaking down a script that contains intimate scenes, what should an agent flag for the producer, ADs, IC, costume, post and legal/contract teams, and which flags come from which source?
Corrected 2026-10-24 - see C3-B1108-01; the original statements below are kept for history and are superseded where the correction says so. No single source gives an agent-ready breakdown template, but the pinned union documents together imply a flag list: scene identification (nudity or semi-nudity, sexual activity, other exposing factors), required roles (IC; stunt coordinator and IC where sexual violence is depicted), people involved (performers, background and doubles who appear nude, minors), contract dependencies (rider with script pages and body-part list, 48-hour delivery before call time), schedule and call-sheet items (IC on schedule and day-out-of-days, closed-set marking and crew list, start-of-day placement for sexual-violence scenes, rehearsal slots), cross-department items (costume, prosthetics, digital additions) and downstream flags (take usability for editors, promotion consent, retention). The list is synthesis; each flag cites a source statement.
- articleHow do the OpenAI and Google image-editing guides tell me to keep identity, camera angle and lighting unchanged in an edit (change-only-X prompts, input_fidelity, text masks)?
Corrected 2026-10-24 - see C3-B955-01; the original statements below are kept for history and are superseded where the correction says so. Problem. Fixing one thing in a keyframe (wardrobe, time of day, object) without changing the face, framing or style. Conditions. gpt-image-1.5 edits (OpenAI Cookbook) and Gemini image models (Nano Banana 2/Pro, Google Cloud guide). Method. (1) State what changes and what stays: 'change only X' + 'keep everything else the same', and repeat the preserve list on every iteration to reduce drift. (2) Lock invariants explicitly: preserve identity, geometry, layout, camera angle, object placement. (3) For heavier edits that must keep a face, pass input_fidelity="high" in images.edit (cookbook examples for lighting/weather change, person-in-scene, compositing); the guide says higher input fidelity helps maintain likeness during larger scene edits. (4) Lighting or weather re-stage: change only lighting direction/quality, shadows, atmosphere, precipitation...
- articleWhat is Google's documented Veo 3.1 prompt structure, and what do its first/last-frame, ingredients-to-video and timestamp workflows give for shot continuity?
Corrected 2026-10-24 - see C3-B955-07; the original statements below are kept for history and are superseded where the correction says so. Corrected 2026-10-24 - see C3-B825-04; the original statements below are kept for history and are superseded where the correction says so. Problem. Getting controlled, multi-shot output from one video model. Conditions. Veo 3.1 on Vertex AI per a Google Cloud blog dated October 15, 2025; clips of 4, 6 or 8 s, 720p or 1080p, 16:9 or 9:16. Method. (1) Five-part prompt: [Cinematography] + [Subject] + [Action] + [Context] + [Style & ambiance]. (2) Dialogue goes in quotation marks; SFX and ambient noise labelled (SFX:, Ambient noise:). (3) Negative guidance is phrased as the thing wanted ('a desolate landscape with no buildings or roads' instead of 'no man-made structures'). (4) First-and-last-frame: generate a start still and an end still (the guide uses Gemini 2.5 Flash Image), then describe the transition, e.g. 'smooth 180-degree arc shot'. (5) Ing...
- articleWhat is an intimacy coordinator on a film or TV production, when does a guild say one should be hired, and what are they expected to do in preproduction, on set and in post?
Corrected 2026-10-24 - see C3-B1058-01; the original statements below are kept for history and are superseded where the correction says so. SAG-AFTRA's Standards and Protocols (cover-dated February 2024) define an intimacy coordinator (IC) as an advocate and liaison between actors and production who may also act as movement coach or choreographer, and say ICs should be hired for scenes with nudity or simulated sex, or on request for other intimate and hyper-exposed scenes. The protocols list preproduction duties (script-breakdown discussion, one-on-one consent confirmation on rider language, continued consent in rehearsal, coordination with costume, props and makeup), on-set duties (rider and closed-set review, continued consent, minors) and a single optional post-production duty. Bectu's UK guidance (Oct 2022 edition) agrees on early hiring but says IC services usually stop before post unless negotiated.
- articleWhat makes a Short eligible to be a template, and how do I stop others using my Short as one?
Problem. Templates copy a Short's structure, so authors want to know what is exposed. Conditions. A template carries the length and number of clips plus text, music and effects. Eligible Shorts are templates by default; the page lists remixable audio, multiple clips and text segments among conditions. Method. Others tap Remix then Use this template (or Use template on the Short), then add their own clips. To block, opt out of Shorts remixing (the Studio setting in C3-B791-04). Failure modes. A Short with non-remixable audio may not offer a template. Limitations. 'Among other conditions' means the full list is not published. Version and date. Undated.
- articleWhich reference inputs do current video-generation vendor docs accept for keeping a character or subject the same across separate generations, and what limits and failure cases do they state?
Corrected 2026-10-24 - see CUR-0618-02; the original statements below are kept for history and are superseded where the correction says so. Vendor docs read on 2026-10-22 offer three different mechanisms, not one: (a) reference images that condition a generation (Google Veo 3.1: up to 3 images of a person, character or product, and 8 s output only; Runway's hosted third-party models: e.g. up to 7 for Kling O3, 10 images plus 5 videos plus 5 audio for WAN 3.0), (b) first/last or multi-position keyframes (Luma Ray 3.2: 1-64 keyframes, exclusive with start/end frame), and (c) a reusable character asset (OpenAI Sora, non-human only, name must be in the prompt; the Sora API was shut down on 2026-09-24). None of the pages read publishes a measurement of cross-shot identity; Runway's own Gen-4 / Gen-4.5 image-to-video entries list only a single prompt image in the docs read. Vendor statements are claims; Kling's docs could not be read.
- articleCORRECTION to C3-B054-G19-07: which parts of the sound-planning candidate are in its cited pages (Haunting about 100 sounds and two months; Matrix concept from the finished script; Welles memo) and which are not (Thom 2000 questions; late hiring and composer coordination)?
Problem. C3-B054-G19-07 lists four planning artefacts and says sound people are 'typically brought on late', spotting is squeezed and composer and sound crew 'rarely coordinate', as 'Weis reports'. Audit result (cited pages re-fetched and searched whole-document). (a) Supported: The Haunting article says Rydstrom had two months to prepare, 'an unusually long time', against sound being viewed as the last and hastiest element; De Bont operated a digital audio player and used about 100 of Rydstrom's sounds on set to inspire and surprise the actors. (a) The Matrix interview: Davis says the Wachowskis had a finished script which they read and 'we developed an overall concept for its sound design'. (a) Welles's sound memo to Murch separates realistic 'background music' from sparingly used 'underscoring'; the page dates it 1958 (the original said 1957-58). (c)/(d) Not supported by the cited pages: the Thom (2000) script-reading questions (no Thom article is among the cited URLs; 'Thom' app...
- articleHow does Beat v2.1.18 turn its script tags into Final Draft tag categories, and how complete is that feature according to its own source and README?
Corrected 2026-10-23 - see C3-B686-03; the original statements below are kept for history and are superseded where the correction says so. Beat's source (v2.1.18 era) contains an FDX tag writer and reader mapping its 15 tag types (cast, props, VFX, special effects, camera, animals, extras, vehicles, costume, makeup, music, sound, stunts, set design, generic) to Final Draft categories, but the author calls tagging nearly working and the README lists tags as 'soon' and warns the repo does not match released versions. Treat Beat FDX tags as unconfirmed in shipping builds. Code is GPL-3.0-or-later.
- articleIn Trelby 2.4.16.2, which Fountain and FDX elements survive import and export, and which production reports does it generate?
Corrected 2026-10-23 - see C3-B686-02; the original statements below are kept for history and are superseded where the correction says so. Trelby's manual (86079b16) documents Fountain import losses (no emphasis markup, dual dialogue split into two dialogues, sections/synopses as notes, title pages and page breaks as action) and FDX import of text and script notes only (Final Draft 8 files, no formatting); its generateFDX writes element types and text without scene-number attributes. The manual's intro says 'three' import formats but lists six.
- articleWhat does the Beat README actually say about FDX tags, and is the 'very close to working' author comment in the cited README?
Problem. C2-B64-K8-05 says the README says tags are 'soon' and that the author comments that tagging is very close to working. Conditions. Judging how complete Beat's FDX tag feature is. Method. The README at 3e2b67f has one tag mention: 'Final Draft import / export, including revisions, outline items and soon tags'. The cited line 47 is a different note: the repository follows the author's development and does not match the latest release on either platform. No 'very close to working' text is in that README (grep for 'close' finds nothing), so that second claim is not supported by the cited source; it may come from a code comment not cited. The line 47 note is an important limitation the earlier finding omitted: code at the pin may not match any released build. Failure modes. Assuming the released Beat app has the tag export described from repo code. Limitations. I did not read the Beat source files (path guesses 404 at this pin). Version and date. Beat README at 3e2b67f, fetched 2...
- articleWhich FDX versions does Trelby's importer support, and does the earlier summary of its FDX import carry that limit?
Problem. C2-B64-K8-03 says Trelby imports FDX 'with text and script notes only (no formatting)' but does not say which FDX files the importer is documented for. Conditions. Moving a script from Final Draft into Trelby. Method. The Trelby manual at commit 86079b1 says only Final Draft files saved with version 8 of the program are supported, importing screenplay element text and script notes, and no formatting. Failure modes. A file saved by a newer Final Draft may import incompletely or not at all, and the manual does not say what happens. Limitations. The manual states the version-8 limit; I did not test import behaviour. The manual is also internally inconsistent (it says 'three file formats' then lists six), so its coverage claims should be treated as indicative. Version and date. Trelby manual at 86079b1, fetched 2026-10-23.
- articleWhat element categories does a script breakdown use, which colour is traditionally attached to each, and do sources agree?
Corrected 2026-10-23 - see C3-B688-08; the original statements below are kept for history and are superseded where the correction says so. Two software-vendor guides agree on the category set but disagree on several colours (vehicles pink vs green; animals pink vs amber/plum; extras/background split vs merged); one calls the colours a convention, not a law. Bytes match producer pins.
- articleHow does ViStoryBench define and score character consistency for story visualisation (metrics, dataset, headline numbers, validity checks, stated limits), and which components are under which licence?
Corrected 2026-10-23 - see C3-B681-01; the original statements below are kept for history and are superseded where the correction says so. ViStoryBench (arXiv 2505.24862v5, 'Accepted by CVPR 2026' per the arXiv API comment) provides 80 stories with 344 characters, 509 reference images, 1,317 shots across 10 style genres (39 photorealistic), in English and Chinese, and 12 automated metrics: cross/self style similarity (CSD), cross/self character identification similarity (CIDS: Grounding DINO crops, ArcFace/AdaFace/FaceNet for realistic characters and CLIP otherwise, bipartite matching), VLM-judged prompt alignment (scene, shot, character interaction, individual action), on-stage character count, aesthetics, Inception score and a copy-paste detector. Table 2 gives the copy-paste baseline (CIDS cross 0.929) as a reference and e.g. OmniGen2 0.548, UNO 0.485 and StoryDiffusion 0.397/0.436 on cross-CIDS. Self-CIDS correlates with a user study at Kendall 0.4978, Spearman 0.6759, Pearson 0...
- articleI want the same character to look the same across the panels of a storyboard made with an image model: what does 'consistent' mean in the primary research, and which method family should I try first?
Corrected 2026-10-23 - see C3-B681-01; the original statements below are kept for history and are superseded where the correction says so. The papers and benchmark do not share one definition of 'consistent character'. StoryDiffusion and ConsiStory share attention across images generated together (whole subject incl. attire, no reference photo); The Chosen One iteratively extracts an identity from a text prompt alone; PhotoMaker and InstantID encode a person's face from photo(s); ViStoryBench measures reference-matched characters per shot with detection plus face/CLIP embeddings. Each source names limits: single person only (PhotoMaker), largest face only (InstantID), no consistent supporting characters (The Chosen One), same style only (ConsiStory), and no background-reference evaluation (ViStoryBench). In ViStoryBench's full-set Table 2 a pasted reference image has higher CIDS (cross 0.929, self 0.984) than any generator row, so similarity must be read together with prompt alignme...
- articleCan I treat ViStoryBench's copy-paste CIDS baseline (cross 0.929, self 0.984) as a stable reference when comparing my own character-consistency runs?
Problem. C3-B227-G69-06 (and the Table 2 sentence in C3-B227-G69-01) present the copy-paste baseline CIDS 0.929 cross / 0.984 self as a fixed reference. Correction type: (c) missing an important limitation / (e) changed since the paper. Conditions. Applies when you re-run the ViStoryBench CIDS evaluator and compare to the paper's copy-paste row. Method. The evaluator README states that, for characters with a single reference image, the current code computes the copy-paste score with a mirrored reference image, and that the paper and project-homepage numbers pre-date that fix. Rerun the baseline yourself with the same code version as your model rows instead of importing 0.929/0.984. Limitations. The README says only 'slightly different'; the size of the shift was not measured here. Version and date. README at pinned commit b44ec91 (identical bytes at main, fetched 2026-10-23).
- articlePROPOSAL (1914 practice as the basis): when is an intertitle, insert or close-up justified in a silent or minimal-dialogue scene, as a check an agent can run?
Agent check, labelled 1914 practice plus a proposal: five steps drawn from Phillips (Ch. IV): try to show the point in action; if not, test it against his named cases (continuity-essential subtle point, lapse of time, mental process, premise); pick caption, simple insert, close-view, vision or spoken line by his definitions; drop the device if repeated or not carrying the story to the climax; keep the illusion by tying objects to a character's act. The order and combination are mine; no source tests the check, and Ch. IV gives no numbers.
- articleWhat are the shot sizes from extreme wide to extreme close-up, how are they framed on a person, and how do I use them as the first element of a Veo-style prompt?
Problem. Shot-size words give inconsistent framing if used loosely. Conditions. Storyboarding and prompting. Source statements (Wikibooks Movie Making Manual; open-text, not a film-school syllabus). Extreme long/wide shot: subject a tiny figure vs surroundings. Full shot: entire body, head to toe. Medium wide / medium long (3/4) shot: from the knees up. Cowboy shot: roughly mid-waist to just above head, camera often at hip level (slightly low angle) - this page's cowboy and 3/4 definitions differ from other sources that put the cowboy shot mid-thigh up. Medium shot: waist up. Medium close-up: just above head to about mid-torso. Close-up: shoulders to top of head. Extreme close-up: crops the subject, picks out a detail. Veo 3.1 guide: put camera and composition first in a five-part prompt [Cinematography] + [Subject] + [Action] + [Context] + [Style & ambiance], with composition terms such as wide shot, close-up, extreme close-up, low angle, two-shot. Method (inference). Pick one size...
- articleHow could an agent track a recurring image through a script or shot list so it can check variation and theme link?
No source gives a motif-tracking procedure for scripts. A proposed procedure (synthesis) combines: de la Prida's two-phase method (segment into sequences and list recurring elements with variations, then verify across the rest), Phillips et al.'s annotation scheme (primary/secondary motif, canonical/red-flag tags), Freeburg's variation rule and Forster's waxing/waning. The ledger records, for each sequence or shot, which motif appears, what changed, and the theme link; flags unchanged repeats, long gaps, and links missing. It is untested.
- articleGiven a latitude, longitude, date and camera heading, how does an agent compute sun azimuth and elevation, light windows and the sun's bearing relative to the lens, and does a from-scratch calculation reproduce the published NREL example?
SYNTHESIS with the worker's own arithmetic, not a source claim. Implementing the USNO approximate-solar-coordinates equations (S4) plus a standard GMST expression, the worker reproduced the NREL SPA Table A5.1 example (Golden, Colorado, 2003-10-17 19:30:30 UT) to 0.015 degrees in zenith, 0.002 degrees in azimuth, and sunrise, transit and sunset (UT-date convention) within 1 second (the script prints whole seconds). A worked shot-direction use: for a camera heading of 270 degrees (looking west) at the same site, the sun's bearing relative to the lens is -75.7 degrees at 19:30:30 UT and -24.7 degrees at 23:00 UT; with the golden-hour boundary taken at 6 degrees elevation (SunCalc's code) the window to sunset on the local evening of 17 Oct is 23:42:10 to 00:18:52 UT (about 37 minutes), and civil twilight ends at 00:46:05 UT. SPA lists rise/set for the UT calendar date, so its 'sunset 00:20:19 UT' is the previous local evening's sunset.
- articleHow do cinematographers and location people say they use sun-path plans on a scout and on set, and where do their terms differ from the algorithm sources?
Three practitioner accounts describe sun planning. ASC's Jay Holben (2021) says to look up a location's orientation on a map before the scout, bring a compass, use a sun-tracking app (he names Chemical Wedding's Helios) to predict where the sun is on any day, and estimates the sun moves about a quarter degree per minute (a finger's width at arm's length is about 15 minutes). Cinematographer Todd Martin (Filmsupply, 2016) uses the Sun Seeker app on scouts and describes a sunrise shaft of light in a pool that would last about 10 minutes, so the crew arrived early to lay track and rehearse. A producer's tech-scout checklist (2020) says to know where the sun rises and sets and mentions Sun Seeker. Holben's article calls the sun's height 'azimuth', which conflicts with the algorithm sources where azimuth is the compass bearing.
- articleWhich primary algorithm sources let an agent compute sun position and rise/set times, what accuracy do they state, and what inputs and conventions do they require?
Four primary or near-primary sources state different accuracies for different purposes. NOAA GML says its sunrise and sunset results are theoretically accurate to within a minute between +/-72 degrees latitude and within 10 minutes outside, assumes 0.833 degrees refraction, and warns the calculator is no longer actively supported and its data cannot be certified. The NREL SPA report (Reda and Andreas, revised January 2008) gives a step-by-step procedure with stated uncertainty of plus or minus 0.0003 degrees for zenith and azimuth over the years -2000 to 6000 and needs inputs such as delta T, pressure and temperature. USNO gives a simple solar-coordinates algorithm accurate to about 1 arcminute within two centuries of 2000 and says rise/set times may be in error by a minute or more even in ideal conditions. SunCalc's README claims about 0.08 degrees and 15 seconds against JPL Horizons and USNO data.
- articleWhat do public sources say a scout must establish about permits, neighbour notification and parking or base space, and who does that work?
The California Film Commission guide says many jurisdictions require notification of affected residents or merchants and some require approvals from a percentage of neighbours within a radius set by local ordinance; it also gives a planning scale of 10 to 25 equipment trucks and 60-95 automobiles for an average feature, and describes reserving street parking with no-parking signs 48 hours ahead. ScreenSkills assigns the location manager to liaise with residents, hold resident meetings, confirm filming with the local authority and police, and obtain permission for parking suspensions or road closures. A trade article quotes a New York location manager on hiring parking assistants to hold parking 24 hours ahead. All figures are local and reported, not rules.
- articleWhat should a location scout and a tech scout record at a site (access, power, sound, light and time of day, permits, safety, neighbours, holding areas), and which items are documented rather than synthesised?
No single public form was found that covers all eight topics. A checklist can be assembled from five documents: the California Film Commission owner-facing guide (access, power, parking, restrooms, neighbours, notification, holding areas in its monitor checklist), a practitioner tech-scout checklist (sun path, basecamp, holding, power, sound, hospital, phone reception), ScreenSkills job descriptions (permits, residents, parking suspensions, health and safety files, movement orders), a Disney pre-scout safety checklist (hazards before a Director's Scout) and a trade article (conflicting needs of camera and sound). The table below marks each item documented (source) or synthesised (no source says it).
- articleWhat is the difference between a location scout and a technical scout (tech recce), when does each happen, and who attends?
Public sources describe two stages. The location scout (usually the location scout or manager alone, with photographs and notes) finds and screens sites against the script; the technical scout (UK: tech recce) is a later visit by department heads to a shortlisted site. The California Film Commission (April 2024 revision) names the tech-scout attendees as director, first AD, unit production manager and production designer or art director plus other necessary personnel; ScreenSkills (2023) says the location manager arranges designers and directors to recce and assembles a tech recce pack and schedule with the first AD; a practitioner article puts the tech scout about a week before shooting. Attendee lists differ by source and production size; none of these sources is a standard.
- articleHow do I prompt PhotoMaker with several photos of one person (trigger word, merge step, style strength)?
Problem. Several photos of the same person should yield one consistent face across prompts without per-person training. Conditions. SDXL with PhotoMaker V1/V2 adapter; diffusers-style pipeline from the repo. Method. (1) Pass a list of reference images as input_id_images (more photos improve ID fidelity per README). (2) Put the trigger word img directly after the class word in the prompt, e.g. 'a half-body portrait of a man img wearing ...'. (3) Example call uses start_merge_step=10 and a seeded torch.Generator (manual_seed(42)). (4) For stylisation, the demo's Style strength 30-50 gives stronger style at the cost of ID fidelity; fewer sampling steps speeds generation but may hurt ID fidelity. (5) V2 adds improved ID fidelity and a ControlNet integration script. Failure modes. Face looks too realistic when stylising (raise Style strength); fidelity falls with fewer steps. Limitations. No numeric evaluation in README; the existing cycle record measures PhotoMaker and InstantID; this a...
- articleHow do I tune InstantID's two weights, what does the keypoint ControlNet lock, and what does its licence permit?
Problem. Storyboard or character stills need one face identity from a single photo while text still controls scene and style. Conditions. SDXL; InstantID checkpoints (ControlNetModel IdentityNet + ip-adapter.bin); insightface antelopev2 for the face embedding. Method. (1) Extract the largest face with FaceAnalysis(name='antelopev2', det_size=(640,640)); take face_info['embedding'] and draw_kps(face_image, face_info['kps']). (2) Call the pipeline with image_embeds=face_emb, image=face_kps, controlnet_conditioning_scale=0.8, ip_adapter_scale=0.8 (README example). (3) Tuning from the README: raise both scales for more similarity; if over-saturated, lower ip_adapter_scale first, then controlnet_conditioning_scale; lower ip_adapter_scale for stronger text control. (4) With LCM-LoRA use about 10 steps and guidance_scale in [0,1]. Failure modes. Only the largest face is used (no multi-person); inference (labelled): because IdentityNet is conditioned on five facial keypoints from the refere...
- articleWhat columns does a Japanese-style animation time sheet have, and what goes in each, according to an open vendor tutorial?
Partially verified: the curator re-read S23, S24; S25 was not re-read by the curator and rests on the producer's pinned reading. CELSYS's official tutorial for the Toei Animation Digital Timesheet documents Action (key drawing), cell (in-between), CAM (camera work), Direction (shooting instruction) and Sound (name + dialogue/SE) columns plus BOOK layers, and CLIP STUDIO PAINT timeline data exports as .xdts for import into the Action or Cell field.
- articleWhich VBench-2.0 dimensions can I run on my own clips (for example previs shots), what do they need, and which only work on the standard prompt suite?
At the pinned repo commit, only five of the 18 dimensions accept custom videos: Human Anatomy, Human Identity, Human Clothes, Diversity (needs 20 clips per prompt) and Multi-View Consistency. The other 13 (including Camera Motion, Instance Preservation, Motion Rationality and all Controllability and Physics state-change dimensions) assert-fail on custom input and need the standard prompt suite, which means sampling the model under test on fixed prompts (3,860 videos for a full run by my count). Requirements are heavy (CUDA 11.8, flash-attention build, several third-party weights, some from Google Drive/Dropbox).
- articleHow can an agent check a shot description or generated frame for internally consistent focal length, camera distance and perspective?
A numeric consistency check can be built from two pinned statements: for a rectilinear lens, field of view follows 2*atan(sensor_diagonal/(2*focal_length)), which reproduces the Zeiss figures (15 mm: 110 degrees, 24 mm: 84, 35 mm: 63 on a 43.2 mm image circle; recomputed by this worker, see finding F1), and for a fixed subject size the distance scales with focal length (Zeiss). The agent compares the stated lens with the described framing (how much of the scene) and the stated distance (subject size, background apparent size). No source tests this on generated frames; the application to AI-generated frames is a proposed hypothesis with a test below.
- articleWill Starc or Beat read a trailing #n# scene number on a Fountain scene heading when I open my .fountain file?
Corrected 2026-10-23 - see C3-B688-02; the original statements below are kept for history and are superseded where the correction says so. Starc (7784620) takes a scene number from a Fountain heading only if the line ends with '#', keeps it only when keepSceneNumbers is on (dialog default false per file), and cuts the #n# marker from the heading either way; Beat 2.1.18 takes the text between the last two '#' anywhere on the line (outside notes). A heading like 'INT. A #1# (CONT'D)' therefore yields a number in Beat but not in Starc (code reading, not run).
- articleDoes Beat always read the text between the last two '#' on a Fountain scene heading as the scene number?
Problem. C2-B128-X19-01 says Beat 'always' parses the text between the last two '#' characters on a heading line. Conditions. Beat commit 3e2b67f, ContinuousFountainParser.m, heading branch. Correction. The scan runs backwards and skips any index inside a note range, so a '#' inside a [[note]] on the heading is not counted. The rest of the claim (resetsSceneNumber on a trailing '>', empty result when fewer than two '#') matches the code. Limitations. Read from source only, not executed; how note ranges are computed for a given heading was not traced. Version/date. Commit 3e2b67f (Beat 2.1.18 per the earlier candidate).
- articleSeedance multi-shot practice from a heavy user: timeline prompts as shot lists, explicit rules for failure points, at most ~3 characters, draft at 480/720p, and edit across several generations
Creator-reported: statements attributed to the creator(s) come from discovery's reading of auto-caption transcript excerpts; the curator checked the video metadata (title, date, length) and any cited documentation pages, not the spoken claims. Nothing was tested; promotional or sponsored framing applies where stated. Dankieft (Daan) on Seedance 2.0/2.5 via Higgsfield. Timeline prompting (R1): a scene header (subject, wardrobe, environment, mood, music, colour logic, style) followed by time-stamped shots works as a shot list - one 15 s generation can return ~10 shots, but over-detailed beats get skipped or rushed, so cut detail per beat; he drafts the prompt with an LLM using a reusable instruction file, then edits it ("Don't trust AI blindly"). When a detail fails twice, add an explicit rule (e.g. which card is chosen and who returns it) plus a negative prompt; add a "logic"/one-continuous-take instruction or the model invents camera cuts. Glitches rise above about three characters ...
- articleDirecting AI camera moves with a Blender previs clip: an agent builds the 3D blockout and camera, then the render is fed to Seedance as a "camera movement reference only"
Creator-reported: statements attributed to the creator(s) come from discovery's reading of auto-caption transcript excerpts; the curator checked the video metadata (title, date, length) and any cited documentation pages, not the spoken claims. Nothing was tested; promotional or sponsored framing applies where stated. Dan Kieft (2026-08-05). Problem: complex camera choreography is hard to describe, and re-prompting never reproduces a lucky shot. Method: (1) make a cinematic start frame (any image model); (2) give the frame and a written camera plan (e.g. 15 s: push in on one person, move to another, pass through a window to reveal a food stand) to Claude connected to Blender via MCP - Claude builds a rough scene and animated camera (took about 5+ minutes on his PC); preview, then Render > Render Animation; (3) in Seedance 2.0/2.5 attach the start frame plus the Blender render and begin the prompt with "video 1 as a camera movement reference only", then describe action/dialogue. His A...
- articleHow do I hand storyboard boards to an editor as an animatic, and what could OpenTimelineIO carry that Storyboarder's exporter carries?
Partially verified: the curator re-read none of the cited sources; S10, S12, S8 rest on the producer's pinned reading. Storyboarder's Final Cut Pro XML export makes one clip per board named from its dialogue, otherwise its action text, otherwise the image filename, puts board notes in the clip description, rounds the timebase up from the project fps and sets the NTSC flag for fractional rates, and uses the project's default board timing (2000 ms in the example) when a board has no duration. A mapping onto OpenTimelineIO clips and markers is plausible but is a proposal, not a documented profile.
- articleI must write or check a film screenplay: what are the standard page-format elements and how are they laid out?
Partially verified: the curator re-read none of the cited sources; S18, S19, S20, S21, S22 rest on the producer's pinned reading. A film screenplay is built from a small element set: capitalised scene headings giving interior/exterior, location and day or night, action, character cues, dialogue, parentheticals and transitions, opening with FADE IN; per the BBC sample, dialogue is split across pages only after at least two lines and a full sentence, marked (MORE) and resumed with (CONT'D). Fountain encodes the same elements in plain text.
- articleHow do I pin where text goes in a generated graphic using structured controls (FLUX 3 layout boxes, Recraft V3 text_layout), and which scripts and characters do they support?
Problem. Prompt-only placement drifts; some APIs accept coordinates. Conditions. FLUX 3 Image (BFL) and Recraft V3 / V3 Vector. Method (documented). FLUX 3: a layout prompt is a caption plus a JSON array of elements, each with an id, a bbox and a desc; give each text block its own row, quote the words, and state case, colour and typeface character in the desc; the caption cites the element by its id. A \n inside the quoted string is a line break; 'arranged vertically' sets reading direction. BFL's examples include Japanese and English text on one poster. Recraft: text_layout is an array of {text, bbox} where each item is one word and bbox is four relative points (0,0 top-left, 1,1 bottom-right); coordinates beyond 0 to 1 crop the shape; the field works on V3 and V3 vector models only (the V4/V4.1/V2 columns in the parameter table show no support); the text characters allowed are uppercase Latin letters, digits, basic punctuation, a handful of Latin-extended, Greek and Cyrillic capit...
- articleWhich input modes (first frame, first and last frame, reference images/video/audio, performance video) does each model accept through Runway's API, and which combinations are rejected?
Problem. Continuity workflows (keyframes, references, motion transfer) depend on which inputs a model accepts; mixing modes silently fails or errors. Conditions. Runway Dev API reference fetched 2026-10-23; per-model request bodies are discriminated unions keyed on model, so fields valid for one model are invalid for another. Method (documented fields). Gen-4.5 image_to_video: one first-frame image, ratio list including 1280:720, 720:1280 and 1584:672, duration 2-10 s, outputFormat options (C3-B586-04). Veo 3.1 (via Runway): first frame, or first plus last; last-frame-only is not supported; duration 4, 6 or 8; ratios 1280:720, 720:1280, 1080:1920, 1920:1080; audio boolean default true. Kling 3.0 Pro: first frame, optionally last; when both are given the output aspect ratio follows the first frame; multiPrompt up to 6 segments with total 3-15 s; cfgScale 0-1 default 0.5; audio default true. Seedance 2.5, Wan 3.0 and Hailuo 3: promptImage uses position first/last for keyframe mode or ...
- articleBefore using a generated world (Marble splat or mesh, HunyuanWorld layers, WonderWorld splat) for previs or as an LED-volume background, what should an agent check, what does the one documented LED-volume use report, and what is unknown?
Partially verified: the curator re-read none of the cited sources; S25, S20, S9, S15, S16, S21, S5 rest on the producer's pinned reading. The only documented LED-volume use found is a vendor case study (Volinga, Feb 2026): a music video used Marble worlds shown as Gaussian splats in Unreal via the Volinga plugin, with stYpe camera tracking and set extension; the vendor and its customer report time saved and on-set switching, with no data on colour, resolution, latency or artifacts. World Labs' docs add plugin notes for nDisplay and depth of field. WonderWorld's authors say its own results have low density and floaters and suggest it as a coarse prototype to refine. The checks below are proposals synthesised from these statements, not tested procedures.
- articleWhen and how should sound be planned, from script reading onward, and what artefacts do practitioners say help (questions, memos, sounds played on set)?
Corrected 2026-10-23 - see C3-B622-02; the original statements below are kept for history and are superseded where the correction says so. Four planning artefacts are documented: (1) script-reading questions that pin down what a character hears and whether the setting has a voice (Thom 2000); (2) an early overall sound concept developed from the finished script (Davis on The Matrix, 1999); (3) designed sounds played on set so actors react (De Bont/Rydstrom on The Haunting, about 100 sounds, two months of prep); (4) a written sound memo that separates realistic source music from sparing underscoring (Welles, 1957-58). The sources also state the usual reality: sound people are typically brought on late, spotting is squeezed, and composer and sound crew rarely coordinate. Planning is therefore a documented best practice on some films, not the norm Weis reports.
- articleWhat is an X-sheet (exposure sheet) and how do Dragonframe, OpenToonz and Toon Boom Harmony each lay out frames, layers/exposures, holds and exposure edits?
OpenToonz 1.7.1 docs and Harmony 25 Premium menu reference (bytes match producer pins) describe the Xsheet as a frame-row by layer-column timing grid with editable exposure; Harmony defaults to overwrite and offers insert mode.
- articleWhen an edit timeline moves between OTIO, CMX3600 EDL, AAF, ALE and FCP XML, what do the adapters at pinned versions preserve (tracks, names, reel, timecode, markers, CDL) and what do they drop or reject?
At the pinned versions: the CMX3600 EDL adapter writes exactly one enabled video track and at most two audio tracks (otherwise NotSupportedError), keeps markers, transitions, linear speed and CDL (ASC comments), assumes 24 fps on read unless told, ignores FCM lines and does not keep AX reels; the AAF adapter round-trips multiple tracks, nesting, markers and transitions but not effects, CDL or image sequences (linear speed read only); the ALE adapter maps Source File to a media reference and CDL/ASC_SOP columns into cdl metadata; the FCP7 XML adapter keeps tracks, markers and nesting but drops transitions, effects, speed, CDL and image sequences. All from READMEs and code, not executed.
- articleAgentic assistants driving Blender, DaVinci Resolve and After Effects for AI film pre-production and editing (GPT-6 Astra, Sept 2026)
Creator-reported: statements attributed to the creator(s) come from discovery's reading of auto-caption transcript excerpts; the curator checked the video metadata (title, date, length) and any cited documentation pages, not the spoken claims. Nothing was tested; promotional or sponsored framing applies where stated. Dan Kieft (Higgsfield-sponsored, 2026-09-23) on OpenAI's GPT-6 Astra (launched early Sept 2026 per secondary news listings R4/R5, emphasising computer use; primary OpenAI page not read). Uses: (1) ChatGPT + Blender MCP builds a 3D set (a bar) from a prompt and references; he places cameras for shot angles, renders previs frames, has GPT Image 2.5 make them photoreal, then uses them as Seedance 2.5 references - more control than describing shots in text; Astra also built a web viewer of the set so non-Blender teammates can orbit/walk it. (2) Recreating rooms from photos to plan a studio layout. (3) Thumbnail ideation with own portrait, channel examples and inspiration, a...
- articleWorldbuilding in service of story, and using concept-art pushes to feed writing (Sanderson, Dos Santos, Stewart panel)
Creator-reported: statements attributed to the creator(s) come from discovery's reading of auto-caption transcript excerpts; the curator checked the video metadata (title, date, length) and any cited documentation pages, not the spoken claims. Nothing was tested; promotional or sponsored framing applies where stated. DSNX 2025 panel (published 2026-01-23). Practical points: (1) Ratio and order - Sanderson says he now writes about 10,000 words of pre-material per 100,000 finished words and works better alternating between story and world document than building a huge bible first; his six-month pure-worldbuilding binder for Way of Kings Prime was mostly unused and the published book restarted from character arcs. (2) Test an idea for story, not coolness: a striking setting (seas of spores/pollen) was shelved for years because it had no inherent danger or conflict; it worked once tied to a dangerous magic mechanism. (3) Concept-art pushes - a group brainstorm over a fixed period, often...
- articleA four-stage control ladder for AI video: one-line prompt, LLM-expanded multi-shot prompt, edited storyboard grid, then saved character/location assets
Creator-reported: statements attributed to the creator(s) come from discovery's reading of auto-caption transcript excerpts; the curator checked the video metadata (title, date, length) and any cited documentation pages, not the spoken claims. Nothing was tested; promotional or sponsored framing applies where stated. Youri van Hofwegen (Higgsfield link, 2026-08-11) holds model (Seedance 2.0), 1080p, 16:9 and the idea constant and changes only workflow: (1) one plain sentence - fast for testing, but camera, sound and look are the model's choices; (2) an LLM (Claude) writes a detailed three-shot prompt - deliberate cuts and camera, though a requested dialogue line was dropped; (3) a three-panel storyboard image from GPT Image 2, fixing a wrong detail (paved vs dirt road) by editing only the affected panels, then giving the storyboard plus an LLM prompt written from it - output followed the board shot-for-shot; (4) saved assets: a character sheet made from a COLLAGE of real photos (mul...
- articleHow does the LTX "layout to render" ComfyUI workflow turn a 3D blockout plus a style frame into a controlled local AI shot?
Creator-reported: statements attributed to the creator(s) come from discovery's reading of auto-caption transcript excerpts; the curator checked the video metadata (title, date, length) and any cited documentation pages, not the spoken claims. Nothing was tested; promotional or sponsored framing applies where stated. Mikkel Lassalle (LTX-promotional, 2026-10-02 UTC). Steps: install ComfyUI (desktop or browser), Manager > Custom Nodes Manager > install "ComfyUI-LTXVideo" by Lightricks, drag the published layout-to-render workflow JSON into ComfyUI, download the six LTX models listed in the workflow notes into the folders shown (the missing-model panel offers copy-link), restart and confirm the load-models node. Inputs: a blockout render from any DCC (he uses Cinema 4D; Blender/Unreal fine) with only enough geometry to lock camera, composition, perspective, layout and timing, plus a reference/style frame (AI style frame, concept art, photo or live-action still) and positive/negative p...
- articleI am new to preproduction: what is the difference between a storyboard, a shooting plan (overhead camera/blocking diagram) and a shot list, and which drawing symbols and fields do beginner-level sources use for each?
A director's teaching blog distinguishes storyboards (what each shot looks like), overhead shooting plans (placement and movement of actors and camera, with triangles as cameras whose angle suggests field of view) and shot lists (derived from boards or plan, valued by ADs), and warns boards can be unachievable on location while a shooting plan 'will help keep you honest'; the Penn State tutorial is CC BY 4.0 except where noted, while the blog shows no licence notice.
- articleWhat is a workable assembly-to-fine-cut workflow for an AI short: paper edit, selects, versions and interchange, tying Murch's priorities, J/L cuts and OTIO together?
Problem. AI shorts have many generated takes per shot and need an orderly path from script to locked picture. Conditions. A short with dozens of shots; steps are inference stitched from the findings 01-12 and prior ones (paper edits C2-B26-A4-06; J/L cuts and split edits C3-B137-S29-03/05, C3-B164-G58-01..05; dialogue cutting C3-B231-S58-05; pacing C2-B17-A3-02 and C3-B589-04). Method [inference]. (1) Paper edit: write the shot list with beat, emotional purpose, duration target and dialogue; pick the order before generating. (2) Generate to the shot list; name files SHOT-ID_take. (3) Selects: score takes with the six-criteria sheet (P-L1-6-02), mark one hero take per shot and keep alternates as 'B' takes; reject for artefacts early (C3-B586-11). (4) Assembly: lay hero takes in order with placeholder frames for shots not yet made (the OTIO use case suggests placeholder clips with unused names); no polish yet. (5) Rough cut: trim for rhythm, cut at lulls and onset of motion (P-L1-6-03...
- articleHow can an instruction image-edit model (Qwen Image Edit + next-scene LoRA) build a consistent storyboard/scene shot by shot, and how do you keep backgrounds consistent?
Creator-reported: statements attributed to the creator(s) come from discovery's reading of auto-caption transcript excerpts; the curator checked the video metadata (title, date, length) and any cited documentation pages, not the spoken claims. Nothing was tested; promotional or sponsored framing applies where stated. Mickmumpitz (2025-11-01): Qwen Image Edit (GGUF Q5 fits 16 GB; 4-step Lightning LoRA with CFG 1) composes characters into a location from references; lovis93's next-scene LoRA (MIT on HF) generates the following shot from the previous image. Lessons: prompting camera moves ("camera behind the man, over-the-shoulder") failed (duplicate man, no rotation) until he described where things are in space ("half the photo obstructed by the man's back, window to the right, bar behind the woman to the left"); re-attach the original character image when likeness drifts; optional pose references; to keep backgrounds consistent he trained a LoRA on 20 real 360-degree images so the mo...
- articleWhat planning framework and location-consistency method does a solo AI animation workflow use (SCENE, 3D world from images, shot-by-shot prompts)?
Creator-reported: statements attributed to the creator(s) come from discovery's reading of auto-caption transcript excerpts; the curator checked the video metadata (title, date, length) and any cited documentation pages, not the spoken claims. Nothing was tested; promotional or sponsored framing applies where stated. Youri van Hofwegen (2026-05-05, OpenArt affiliate) plans before generating with "SCENE": Story (inciting incident; decide the ending first), Characters (who and rough look), Emotion (decide the palette/mood arc up front, e.g. tension -> danger -> relief), Narrative beats (three clips = setup, escalation, resolution; one job per clip because the model does not know the next clip), Every-clip rules (a fixed style line in every prompt as a "production bible"). Location consistency: OpenArt's "3D World" builds a navigable world from 1-4 multi-angle images of a location (generate angle variants first, "Ultra" mode), then "take shot" anywhere with focal length 23-300 mm; char...
- articleHow are creators building their own AI filmmaking tools with coding agents and MCP connectors, and what are the practical limits?
Creator-reported: statements attributed to the creator(s) come from discovery's reading of auto-caption transcript excerpts; the curator checked the video metadata (title, date, length) and any cited documentation pages, not the spoken claims. Nothing was tested; promotional or sponsored framing applies where stated. Dan Kieft (2026-08-01) describes "vibe-coding" three tools with a coding agent (Claude Code; Fable 5 or cheaper Opus 5): define the problem (his AI-film workflow had too much back-and-forth between an LLM and a generation platform), answer three questions (what, why, which features), have an LLM turn them into a master build prompt ("meta prompting"), revise it heavily, then iterate in the coding agent. Results: (1) a story/character/location "world builder" web app where users connect their own Claude API key and their Higgsfield account via MCP (so the site runs at no cost to him), which writes a structured script PDF, generates character sheets (GPT Image 2) and loca...