Reference C · Checklists
Reference
The checks a director runs at each gate, gathered by the stage where they are run: before a frame is signed, before a clip is sent and after it returns, on a voice line, a cue or a lip-sync pass, in the cut, in the finish and at the handoff. Each list is copied exactly as its chapter prints it, and each says which section teaches it.
In this reference
A finder: every list in book order, with its chapter, its section and its place here
Seven groups, one for each stage of the production, each in chapter order
For every list: the box as its chapter prints it, and the section that teaches it; the lists of every tool section's "Checks before you sign" are here as well as in their chapters
How to read a list. A check is a question answered on a frame, a tile, a waveform or a measurement, and it is written before the job runs. A failed check stops the step it guards, and nothing accepts itself: the director's eye and ear pass the shot. A list is copied with the wording of its chapter, so the qualifications in the text around a list still apply. The check sheet of Chapter 8 is printed as a table in its chapter and is copied as printed; where a list points "below" or to a figure or a table, it points into its own chapter, so follow the pointer under the list.
C.0 Which check at which moment
List | Chapter | Section | Here |
A review pass that costs nothing | 1 What changes when the camera is a model | C.1 | |
Before the concept goes to the treatment | 3 The concept | C.1 | |
Before a treatment goes to a client | 4 The treatment and the pitch | C.1 | |
Before you sign a breakdown | 5 Shot design and camera language | C.1 | |
Before you sign the light of a frame | 6 Light, colour and the look | C.1 | |
The world note, for every location | 7 Production design and realism | C.1 | |
The realism check | 7 Production design and realism | C.1 | |
The check sheet | 8 Planning the production | C.1 | |
Before the first paid job | 8 Planning the production | C.1 | |
Before you sign a still | 9 The finished frame | C.2 | |
Before you sign a keyframe | 9 The finished frame | C.2 | |
Before a real person's frame leaves the room | 10 Identity, references and the world in the frame | C.2 | |
Before you sign a frame that carries words | 10 Identity, references and the world in the frame | C.2 | |
Checks before you sign | 11 Nano Banana Pro | C.2 | |
Before you sign a Nano Banana Pro frame | 11 Nano Banana Pro | C.2 | |
Checks before you sign | 12 GPT Image 2.5 | C.2 | |
The entry card for a shot with no start frame | 13 Choosing the route | C.3 | |
Before you send | 13 Choosing the route | C.3 | |
Before you run: read the text | 14 The moving shot | C.3 | |
The acceptance check for a performance | 15 Directing performance | C.3 | |
Before you sign a Kling clip | 16 Kling | C.3 | |
On the returned file | 17 Seedance 2.5 | C.3 | |
On the returned file | 18 Wan 3.0 | C.3 | |
Checks before you sign | 19 Veo 3.1 and MiniMax H3 | C.3 | |
Before you lock | 21 The voice department | C.4 | |
Before the plate goes to the pass | 22 The speaking shot | C.4 | |
The checks after the pass or the performance, in order | 22 The speaking shot | C.4 | |
Listening checks | 23 ElevenLabs | C.4 | |
Before you sign a pass | 24 Sync Lipsync 3 | C.4 | |
After a generated sound returns | 25 Music and sound for a commercial | C.5 | |
Before you sign the sound | 25 Music and sound for a commercial | C.5 | |
Listening checks | 26 Suno | C.5 | |
Before an Eleven Music cue goes near a client | 27 Eleven Music | C.5 | |
Checks before you sign | 28 Sound-effect and music generators | C.5 | |
The returned shot against the sheet of 8.9 | 29 Editing AI footage, and judging the work | C.6 | |
Before the job: the gates | 29 Editing AI footage, and judging the work | C.6 | |
Before a cut goes to review; Before picture lock | 29 Editing AI footage, and judging the work | C.6 | |
Before the finish is signed | 30 Finishing, captions and graphics | C.6 | |
Before a handoff leaves you | 31 Handing over | C.6 | |
An upscaled or boosted clip; A Generative Extend; Captions; An import or a final export | 32 Premiere Pro and the finishing tools | C.6 | |
After every job | 33 Higgsfield | C.7 | |
Money and rights, in order | 34 Money, rights and terms | C.7 |
C.1 Before the camera
Chapter 1 · What changes when the camera is a model
A review pass that costs nothing
Pause at random moments during movement and look for a broken frame.
Zoom into the extremities: ears, fingers, eyes, hairlines.
Step frame by frame through every transition and wherever a hand touches an object.
Watch once with the sound off; visual flaws stand out more.
Slow the clip to quarter speed to check eye movement and small expressions.
Check that reflections match the room, that no crowd figure repeats, and that logos on clothing have not distorted.
Taught in 1.3 Where it still fails.
Chapter 3 · The concept
Before the concept goes to the treatment
It can be said in one sentence, on the phone, without a voice-over.
It rests on a tension, not an observation, and names an enemy that is not a competitor.
The refusal list was written before the ideas, and the five expected answers are banned.
It breaks under both tiers of the brand swap, or the brand has been given something to own.
The mechanic is understood with the sound off or with the picture off, and you know which.
Three endings were compared and one tone anchor is written as a filmable instant.
Every unverified claim is a question, not a line; every local truth is checked by a native reader.
Each discarded idea has a one-line reason; the recommendation and the strongest alternative are named.
Its production commitments are written down as information, not as a reason to shrink it.
Taught in 3.9 The concept page, and handing it on.
Chapter 4 · The treatment and the pitch
Before a treatment goes to a client
A fresh reader can retell the idea, the progression of events, the payoff and the brand's role without your notes.
Every image agrees with its caption and with the text beside it (posture, wardrobe, props, lights, the number of things), and is identified as what it is: a frame study, a reference, a proposal or atmosphere.
Every state change (a wardrobe decision, a new frame, a corrected prop) has travelled through every page that depends on it.
The exact lines are correct in the film's language, and each gloss is marked as a gloss.
Timings add up, and every claim, figure and offer has an authoritative source, or is not on the page.
No prompts, model names, working codes or internal decision labels appear in the client edition.
The exported file has been opened and checked page by page: fonts, overflow, clipped labels, residue from other projects.
The last page asks for a decision.
Taught in 4.9 The fresh read, the records and handing on.
Chapter 5 · Shot design and camera language
Before you sign a breakdown
Every shot has a job in one sentence, and no shot repeats another's job.
Every frame is described in prose, and every move has a verb, a mechanism, a destination and a hold, or the shot says "The camera is locked." and why.
One dominant camera intention per shot; any device has all five parts.
At finished grade, height, distance, lens and stop are in the prompt, each beside the result it should give; the reasons are in the shot record.
Every slow move is sized by what it does to the frame; a Kling move carries one approximate magnitude per moving system, a duration and a speed profile.
Every motion prompt ends on a composition you can cut on, then a hold.
The scene has a geometry note, and every shot keeps the camera on one side of the axis.
Every object that matters is planted before it pays off.
Generation risk and its plan are written for every shot; the riskiest have a fallback.
The scene has chosen where it is bold, and it has a memorable shot.
Vertical versions of speaking and travelling shots are planned as their own frames.
Taught in 5.11 The checks, the gate and the records.
Chapter 6 · Light, colour and the look
Before you sign the light of a frame
You can point to the source of every face's light, and the shadows agree with it.
Every source is written whole: what it is, where, hard or soft, its Kelvin, what it does to a named surface. No equipment appears in the frame.
The fill is a surface you can point to; no light appears that has no cause.
The far cheek shows the ratio you wrote, and the record says why.
Skin keeps its texture where the brief said it would; only what may clip, clips.
Each source reads in its own colour on skin; no blue cast, no teal in the shadows, no orange wash.
The palette reads as shares of named surfaces; the protected colour reads as it does on the product.
Downcast eyes are readable; a speaking mouth is lit.
The finish describes capture, with the grain kept fine, and nothing asks for "old film"; the delivery texture is decided once for the film.
The light matches the neighbouring shots across the cut.
Taught in 6.10 The checks, the gate and the records.
Chapter 7 · Production design and realism
The world note, for every location
Who lives or works here, and what can they afford?
What is new, and what was inherited or bought second-hand?
What gets repaired, and what gets replaced?
What do the sun, the climate and the city do to its surfaces?
Which objects drift into view naturally in the course of a day?
What kind of mess do these people leave behind?
What would never be here? (One exclusion against the genre's cliché.)
Taught in 7.6 The world.
The realism check
The set has a point of view, not just a style.
The room shows use at its touch points.
Objects cluster by function and by owner.
Wardrobe names material and construction, not only colour and mood.
The frame's edges are purposefully quiet or purposefully interrupted.
The product is part of the action and of the surfaces.
At least one small imperfection survives the clean-up.
Taught in 7.9 The check before you sign a frame.
Chapter 8 · Planning the production
The check sheet
Write the quality-check sheet at planning time and fill it in shot by shot. It is the last check before a shot's assets lock: four blocks, and any failure stops the lock.
Block | What it asks |
Prompt truth | are the elements complete and in order; do camera and light carry their results; are the exclusions few and earned |
Identity truth | does the call carry the locked wording or the approved frame; are the masters present and named identically; is the result judged against the masters, never the previous output |
World truth | is the geography consistent with the plates; is every noun legal for the period; is the world's text honest to its distance; are the must-show items ticked |
Delivery truth | is the mid-action status true and the endpoint a cuttable composition; are the watch items cleared frame by frame; are parameters and spend logged; was a hero keyframe approved before its motion was made |
The last check is the one no machine runs, and it outranks the rest: the shot answers its intention line. The returned file gets its own checks after the job (Chapter 29); the director's eye and ear pass the shot.
Taught in 8.9 Names, folders and the workbook.
Before the first paid job
The project decisions card and the decision log exist; the treatment and the plan are locked and dated.
The obligations list is approved; every shot serves one, or says why not.
Every shot has a row and a shot record with its mid-action status, declared band and levers.
The continuity kit is planned from the shots; each picture has one job and a manifest row.
Rights are cleared for every real person, voice, brand asset, track and clip the batch uses.
Names, folders, the file manifest and the run record's home are set up.
The spending packet is written, with a cap, stop conditions and the price read on the day.
Taught in 8.10 The spending packet and the budget.
C.2 Stills
Chapter 9 · The finished frame
Before you sign a still
The person reads as themselves at the size the frame will be seen; face, hands, teeth and closures are checked at full size, and a later frame's face at 200 % against the master.
Age, wardrobe and jewellery match the words.
Every frozen system the record names is visible, in the phase the prompt gave.
Every light is in the state the prompt asked for, and the shadows fall as the ratio says.
Objects are in the state the shot starts in.
No stray printing or logos on "plain" objects and screens.
The frame came back in the aspect and resolution you set.
Taught in 9.8 Reading what comes back.
Before you sign a keyframe
The frame is the first instant of the shot, not its end; for a handover, the state before contact.
Every moving system has a phase, written as positions and participles, with its direction readable; no open verb, no camera-movement word.
Every frozen system in the shot record is also in the prompt, and the start state is written in one sentence.
Contacts are readable and possible; the hands are counted and each wrist traced to a person.
If the shot speaks: one face, lips neutral or barely parted and written into the prompt, the mouth unobstructed and evenly lit, any listener outside the frame or still.
The frame leaves room for the move, its edges are named, and it was made at the video route's aspect and resolution.
Taught in 9.10 Keyframes for motion.
Chapter 10 · Identity, references and the world in the frame
Before a real person's frame leaves the room
The release covers AI likeness and platform training.
No name in the prompt.
The forensic clause is written from the photographs and approved by the subject.
The frame is checked against the photographs at 200 per cent.
The subject or the family has signed it off.
Taught in 10.8 Real people, and an actor's name as a rights decision.
Before you sign a frame that carries words
The string was approved outside the model, by a qualified reader if it is Arabic.
It is quoted once, with position and typography, and "nothing else is written".
The letters are lit to read, at a size honest for the distance; distant text is texture.
The closing line is the fixed one, not "No text".
Every glyph was read on the returned original; no painted quotation marks; packaging and screens checked for stray printing.
Taught in 10.12 Text in the frame: two layers.
Chapter 11 · Nano Banana Pro
Checks before you sign
Chapter 9 teaches how to read a returned frame, at the size it will be seen and then at full size. These are the checks that belong to this tool, in the order to make them.
The file. Open it at 100 %. The size and aspect must be the ones you set: a 2k 16:9 frame is 2752 × 1536. Every output carries Google's invisible SynthID watermark; there is nothing to see and nothing to remove.
The picture at 100 % and 200 %. Eyes, ears, teeth, hands (count the fingers and trace each wrist to a person), closures, jewellery, labels.
The frame against its prompt, element by element. Every frozen system is visible in the phase written. Every light is in the state asked for, and the shadows fall as the ratio says. The depth of field looks like the stop you wrote. The edges you named are cut as named.
A frame made from pictures. Put the face at 200 % beside the master, never beside another frame made from it, because faces drift in small steps and a copy of a copy hides the drift. Look for what leaked from a reference: its ground, its light, its clothes, its pose, a second face.
Stray marks. Faint printing or a logo on an object described as plain, or on a screen. In-frame text is read letter by letter, and an Arabic string is compared with the approved string: a final ى where ي was asked fails, and so does a broken join.
Products. Compare with the real product photographed: proportions, closure, label position.
An edit. Flick the parent and the result at full size and list what moved. Decide whether the cut can live with it.
A composite. Look at the seam at 100 % and match the grain.
A keyframe. The mouth state and the room left for the move (Chapter 9).
A real person. A face that has drifted from the consented photograph is a hard failure, however good the rest is.
Taught in 11.7 Checks before you sign.
Before you sign a Nano Banana Pro frame
The size and aspect are the ones set; the job label is logged beside the model asked for.
The person reads as themselves at viewing size; at 200 % the face matches the master.
Every frozen system, light and named edge is as the prompt wrote it.
Nothing leaked from a reference: no second face, no borrowed room, light or clothes.
No stray printing, logo or text; every in-frame string is exact.
Any product matches the real one; brand and legal text is set in post.
After an edit, what moved has been listed and accepted or repaired.
Taught in 11.7 Checks before you sign.
Chapter 12 · GPT Image 2.5
Checks before you sign
Look at 100 % first, then 200 %, then flick the frame against its source where there is one.
Hands and contacts first. Every grip, support and gaze target, in any frame that hinges on a touch.
Invented marks. Lettering, logos or texture on any object you called unbranded, plain or blank. A panel you asked blank must be blank.
Copy. Each quoted word present once, spelled as given, in its place, and no other text anywhere. For Arabic, every letter, dot and join against the approved string, and the reading order.
Quiet zone. The surface you kept bare for type is bare.
Alpha. Open the returned file and look at the alpha over black, over white and over a saturated colour: shoulders, glass, liquid, fine detail. A drawn checkerboard is a failure. Then judge the element composited over the real plate, and again after it has been through your editor and your export. Note which file type came back.
Edits. Original and result at the same size across the whole frame: faces, hands, lettering, edges, colour, crop. Anything the edit was not asked to touch that moved is a fail; composite the approved region onto the original.
Product truth. A generated product is a stand-in. The label and the geometry that ship come from the real thing.
Size. Record the returned size and aspect against what you set.
Taught in 12.7 Checks before you sign.
C.3 Motion
Chapter 13 · Choosing the route
The entry card for a shot with no start frame
Variance budget. List what may vary (an anonymous face, the background layout, a crowd's arrangement) and what may not. If composition, identity, product geometry, geography or exact text cannot vary, use a start frame or post.
One-shot truth. Describe the shot in one sentence with one dominant action and one camera behaviour. If the sentence needs "then cut", it is several shots (13.5).
Identity route. Recurring people enter only by reference. Anonymous or archetypal figures are the natural citizens of this operation.
Text route. No final titles, captions, counters or logos; in-world lettering needs a per-letter check and a repair plan (Chapter 10).
Exit condition. Name the cuttable final composition, not merely the end of an event.
Taught in 13.4 When to leave the start frame behind.
Before you send
The route line is written, with a grade and a fallback.
The number of people in the prompt matches the frame.
The attachment order matches the numbers in the text.
The start frame shows the instant before the action (14.3).
For speech, the line in the prompt and the recorded take agree.
No setting (aspect, duration, resolution) is written in the prose.
Taught in 13.7 The checks, the gate and the records.
Chapter 14 · The moving shot
Before you run: read the text
One dominant camera move, verb first, its rig named; or a declared fixed frame with the motion given to the world.
Nothing the frame carries is described again; protection is by name, after the action.
The action runs through time with at most two secondary actions; the world has life.
The endpoint is a composition you can cut on, and the hold is written.
No "from frame one", no hedge-state camera words, no contradictory spatial demands, no off-frame object named.
The magnitude fits the tool: one approximate figure per system on Kling, sized from the subject's distance (14.5); pacing words and stamps elsewhere.
The vocabulary is legal for the project's period; exclusions are three or fewer on a clip (five is the ceiling), each earned; the prompt closes on the hygiene line and the sound switch is set.
For a start-and-end clip, the two frames are relatives.
Taught in 14.16 Checking a moving shot, the ladder, and when to stop.
Chapter 15 · Directing performance
The acceptance check for a performance
Watched with the sound off: a viewer can say what changed, and when, without the prompt.
Every emotion word is paid for by a cue; no face acts a feeling.
The listener has a task and reacts when the meaning lands, not when the line ends.
Hands and props follow the ledger: weight taken before release, one instance of each prop.
The look order is right, and the last frame is a cuttable composition.
The exit state (grip, gaze, breath) is written down as the next shot's entry state.
Taught in 15.10 Repairing a performance, and the gate.
Chapter 16 · Kling: 3.0, and 4.0 as announced
Before you sign a Kling clip
Probe the file for raster, frame rate, frame count, length and audio stream. Expect std 1284 × 716 (the job record says 1280 × 720), pro 1912 × 1080, 24 frames a second, 121 frames for five seconds (5.04 s) and 241 for ten. Sound off gives no audio stream; sound on gives AAC stereo at 44.1 kHz. Turbo's "1080p" in 9:16 was 1076 × 1928, with a stereo track on all four clips (12 Sep 2026). Quote the probed figures, never the label.
Frame 0 against the keyframe, at 200 %: face, hands, label, lettering, the count of props. It is the keyframe scaled, so small print softens, and what was wrong in the still is still wrong.
The first second. Something visible moves at once; there is no dead second before the photograph wakes.
The move, measured (below).
The middle, at 20, 40, 60 and 80 per cent: the protected things (the spires, the badge, the label, the fingers), one prop where you asked for one, and nothing that entered from the frame edge. For a start and end pair, the path between the frames.
Lettering at full crop in the first, middle and last frames. Arabic must be exact letter for letter (Chapter 10). A letter that drifts twice goes to the compositing layer.
The last frame against the endpoint you wrote, and the hold. The hold after the action is your handle; nothing exists beyond the ends of the file.
Period and place. Nothing modern in a period frame; the light is still the frame's light.
Sound. Absent when the switch was off. When it was on, listen: a plate's sound is replaced by the pass, and a spoken line in a clip is a test.
A talking plate, watched as a performance before it goes to the pass, with its talk window measured (22.4).
Taught in 16.7 Checks before you sign.
Chapter 17 · Seedance 2.5
On the returned file
Probe it: raster, frame rate, length, audio stream (Chapter 30).
The opening: everyone who should be there already is, the people counted match the cast, and no one and nothing is duplicated.
Faces at 200 % against the master or the in-look anchor; the costume; the product's shape and marks.
Leaks: no reference's backdrop, light or grade; no sheet panels or grey ground; no fingerprint-like pattern in grass, foliage or fabric.
The move, at the start, the middle and the end: one dominant camera action, real parallax, the subject's height first against last.
The ending: a composition you can cut on, then a live hold.
Hands, closures, labels and lettering at 100 % and 200 %; lettering is replaced in post from the real artwork. No subtitles, captions, logo or interface.
Sound by ear: what owns the room, no music if excluded, no other voices, no step at a join.
A speaking shot, heard word by word: the mouth moves with the words and is still in the pauses. Note the second the line landed and the length of the hold.
An edit: the length against the source; everything outside the scope, frame by frame; colour and brightness against the original. Keep the original beside it, never over it.
An extension: the join at normal speed and frame by frame: pose or prop, a restarted action, a step in the volume, inherited subtitles.
Taught in 17.7 Checks before you sign.
Chapter 18 · Wan 3.0
On the returned file
Probe it: raster, frame rate (30), length, audio stream (Chapter 30).
The opening: everyone who should be there is, the count matches the cast, nothing is duplicated.
Faces at 200 % against the master or the in-look anchor; the costume; the product's shape and marks.
Leaks: no reference's backdrop, light or pose; no invented lettering.
The framing is the one written, not the keyframe's.
The move, at the start, the middle and the end: one dominant camera action, real parallax.
The ending: a composition you can cut on, then a live hold.
Hands, closures and labels at 100 % and 200 %.
Sound by ear: what owns the room; no music if excluded; no speech where "No dialogue" was written.
A speaking shot, heard word by word: the mouth moves with the words, is still in the pauses, and the track is compared with the sample.
Taught in 18.7 Checks before you sign.
Chapter 19 · Veo 3.1 and MiniMax H3
Checks before you sign
Probe the returned file before you look at it: size, frame rate, length and audio stream.
The track, by ear. Does the sound sit on the contact frame? Is the track usable as it comes, or ambience you would strip? Did music or a voice arrive that you did not ask for?
Veo: the length you asked for (4 s), the aspect, and the resolution.
H3, at 200 %: is the 2K real detail, or soft pixels? Do identity and geography hold on the key frames?
The start frame's look. Did the clip restyle it?
A file that must arrive silent has its track stripped afterwards; the sound was paid for either way.
Taught in 19.7 Checks before you sign.
C.4 Voice and speaking faces
Chapter 21 · The voice department
Before you lock
The line record is complete and approved, with the canonical line and the engine text in separate columns.
The model and source class are on the take-ledger row, and the failing word was named, with where it falls, before any repair.
Repairs climbed rung by rung; every mark approved by the dialect reviewer; ق to hamza only in that word and only for this voice.
The whole sentence was compared with the pass before after every repair.
Four scores at 4 or above and no hard fail.
The lock is normalised, named, measured and checksummed, and the old takes, cuts and clips are marked stale.
The consent record is filed, and a library voice's notice-period status is filed.
The contract is written, exact take or new performance.
Taught in 21.11 Checks, the gate and the records.
Chapter 22 · The speaking shot: two routes
Before the plate goes to the pass
"Talks quietly … for about [n] seconds", with no words; business before, a landing after (Chapter 15).
One face, fully visible and lit; nothing crosses the mouth.
The plate 0.3 to 0.5 s longer than the whole padded take, head included.
The talk window measured, and the take's head padded (or the plate trimmed) so the speech starts where the talk starts.
The plate watched, and approved as a performance, before the pass.
Taught in 22.4 The keyframe and the talking plate.
The checks after the pass or the performance, in order
Normal playback: watch at real speed before anything else.
File: the frame size is the plate's; the length about the take's; 24 fps.
Audio: on Route A, decoded and compared with the upload for content and timing (expect a re-encode that matches closely, not a new reading); on Route B, listened to as new audio: every word present and right, ع ح ق ج, stress and vowel length, the same voice, no extra sounds.
Onsets: the first visible articulation against the first audible sound.
Closures: the lips meet on every ب and م.
Pauses and the hold: no mouth movement in the silences; the mouth closes after the last word.
Anatomy: no tearing at the corners, no blurred teeth, no pasted-on mouth.
Identity: the face still matches the master; on Route A the eyes, head, breath and hands are the plate's.
First and last frames, and the handle: where the plate's own tail can carry the landing, noted.
Side by side with the plate (Route A), then the native ear on the audio.
Again in the final export, in the player the client will use.
Taught in 22.7 Checks after the pass or the performance.
Chapter 23 · ElevenLabs: v4 and v3
Listening checks
Every word. The words are the canonical words: none added, none dropped, none swapped for an easier one. A different word is a failed line, however well it is read.
Dialect and register. A native reviewer of the variety hears the vowels, the ق, the stress. A clearly wrong dialect fails whatever the average (21.6).
The performance. The bracket was obeyed: the state, the attitude, the address. Breath and pace fit the picture the line will meet.
Nothing else in the file. No click, hiss or second voice, and no sound a tag was taken for.
The whole sentence after a repair. Compare it with the pass before, at the same level: a corrected word can bring a new stress or pause elsewhere.
The record. Model, voice ID, source class, settings, seed and the engine text are on the take-ledger row (21.11), for the rejected takes too.
A dialogue. Each turn is in the right voice, no name is read aloud, and the overlaps are ones you would keep. Then each line is remade alone.
A conversion. The words are the performer's, unchanged; the timbre is the target's; the room is not audible.
A sound effect. Alone, at 100 %: the object, material and force are right for the picture, the tail is as long as asked, no music or voice leaked in, and a loop's seam has no click. All four variations are kept until one is chosen.
The file. Probe its format and sample rate; the download may be MP3 where you expected WAV.
Taught in 23.7 Checks before you sign.
Chapter 24 · Sync Lipsync 3
Before you sign a pass
Probe the file: the frame size is the plate's; the length is the take's, in frames (112 frames, 4.667 s, for a 4.649 s take); 24 fps; one audio stream, AAC 48 kHz mono.
Normal playback at 100 %, with the sound, before anything else.
Frame-step at 100 %: the first visible articulation against the first audible sound; the lips meet on every ب and م; the last consonant; no movement in a pause; the mouth closed in the hold.
At 200 %: teeth and mouth corners, the skin and jaw line around the redrawn region, light and grain matching the plate, no blur and no pasted-on look.
Side by side with the plate: the eyes, head, breath and hands are the plate's, and the face still matches the master.
The audio, decoded and compared with the upload for content and timing, then the native ear; then the first and last frames, and again in the final export.
Taught in 24.7 Checks before you sign.
C.5 Music and sound
Chapter 25 · Music and sound for a commercial
After a generated sound returns
One contact, not several.
The object's size and material, not a bigger one.
The room and the distance fit the shot.
No music, voices or whoosh.
Raw file kept; settings recorded.
Taught in 25.13 Repairing a placed sound.
Before you sign the sound
The sheets match the cut you are signing: every event has one owner and a frame read on the selected take.
Candidates were compared at matched level with the dialogue unchanged; exact hits sit on the effects track.
One bed runs under every cut; no layer masks a line; no intelligible voices unless scripted and approved.
Loudness is measured over the whole mix against the delivery owner's specification, and the specification is recorded.
Every file has its route, settings, raw version and rights line; you listened on speakers and on headphones, at delivery loudness.
Taught in 25.17 Checks and the gate.
Chapter 26 · Suno
Listening checks
Alone, on headphones, the whole length. No voice, hum or breath under the mix, and no ghost of a vocal you excluded.
The figure. Hum it back after one hearing. It returns where the paragraph said it returns, and it is not stretched into a tune.
The ending. It stops as written: a button, a held note, a decay. Count the tail. If it fades or loops, the ending was not written strongly enough (26.8).
Against the picture, with the scratch voice-over laid on. The speech range is open; nothing masks a syllable; the cue enters and leaves on the beats the cut asked for.
Across every join. After Extend, Replace Section or a boundary drag, listen to the seam twice: no click, no jump in tone, the downbeat has not moved.
The tempo, measured from the file. Write the cue map from the file, not from the prompt's BPM: tempo, accents and section starts in seconds, checked at the start, the middle and the end.
Stems, if any. Alone and recombined against the full mix.
The file. Probe the format, sample rate, bit depth and length of the first file of each kind you export; Suno's pages disagree on Studio's export format (26.9).
The record. The rights line is filled (34.10; template in 26.4; terms in 26.9); the watermark and metadata are untouched; the title carries no brand.
Taught in 26.7 Checks before you sign.
Chapter 27 · Eleven Music
Before an Eleven Music cue goes near a client
The delivery is online, or an Enterprise Music plan is in hand and ElevenLabs has confirmed in writing that its terms cover Music 2.5 (27.9).
The plan's eligibility row fits whoever holds it.
Listen alone on headphones: no voice, no palette leak into the ending, the figure where the chunk says, and clean chunk joints and repair seams.
Measure where each phrase and the ending land. Probe the file: format, sample rate, length. Loudness is measured in the mix (25.14).
The record holds the plan, the song ID and the rights line (34.10).
Taught in 27.7 Checks before you sign.
Chapter 28 · Sound-effect and music generators
Checks before you sign
Listen on headphones and on speakers, at delivery volume, with the picture.
The transient is on the contact frame, and the release (or the last note) lands where the sheet says (25.10).
One event, not several; the object's size and material, not a bigger one; the tail is what you asked for.
No music, voices or unintelligible vocal texture in an effect or a bed; a bed is even for its whole length.
Beside a recording, the generated file is better for what was missing; if not, the recording ships.
A cue ends as briefed, and the middle register is open for the voice.
The raw file and the settings are on the row, with the rights line (34.10) filled.
Taught in 28.7 Checks before you sign.
C.6 Edit, finish and delivery
Chapter 29 · Editing AI footage, and judging the work
The returned shot against the sheet of 8.9
Prompt truth: the file is what the prompt asked, in its order, closing on its endpoint and its sound switch; camera and light gave the results written beside them.
Identity truth: judged against the signed masters, never the previous output; every reference did its one job; a real person shows no drift at all, which is the hard fail.
World truth: the geography agrees with the location masters and every noun belongs to the place and time; in-world text is honest to its distance and the editorial layer is absent from the pixels.
Delivery truth: the frozen systems held and the endpoint landed as a cuttable composition; the watch items are clear frame by frame at the contact points; duration, aspect, size, references and spend are logged; the shot answers its intention line, which no machine checks and which outranks the rest.
Taught in 29.10 Judging the work in the running cut.
Before the job: the gates
Spend gate: cost read on the day, and the spend authorised for this batch, with its cap.
Rights gate: rights status of every input recorded.
Sound switch, aspect and resolution set in the settings, not in the prompt.
Your checks for this shot written down.
Taught in 29.10 Judging the work in the running cut.
Before a cut goes to review
Every interval logged in frames at the file's own rate, defect frames noted; the order matches the obligations list.
Hard cuts only; no grade, graphics or upscale yet; the dialogue that ships at its own timing; one room bed; missing coverage slugged.
Every join shows one transfer, nothing mirrored, no dialogue moved to fake an overlap, no looped listener.
Runtime measured on the render; the applied cut list matched against it; the slate carries its version and, if a decision is wanted, the question.
Before picture lock
Every timeline item links to its source; temporary text and sound are gone.
Every speed change, reframe, stabilisation and interpolation is listed, with its range.
A rollback to the previous lock exists.
The director has accepted the cut.
Taught in 29.14 Locking the picture.
Chapter 30 · Finishing, captions and graphics
Before the finish is signed
The picture was locked, and accepted, before any finishing money was spent.
Every file probed; rate and raster conformed on purpose, nothing stretched.
Defects repaired by cut, trim, bridge or child shot before any global transform.
Each transformation judged alone, in motion, on a difficult interval; any upscale compared with the native version at the same grade; generating at the target size priced first.
No identity or lettering changed; the native original kept beside every labelled copy.
Colour: the source interpreted and recorded, no camera-log transform, shots matched to the masters, the look applied separately, viewed through each output transform.
Texture added last, at final resolution, and never asked of a generator.
Unchosen native tracks stripped; one bed per scene; loudness, true peak and downmix measured against a named specification.
Captions from approved copy, timed to the audio that shipped, checked in the real player; every Arabic run in the frame compared letter by letter with its source.
Every target overlaid, every shot classified, every version with a manifest line and its own quality check.
Every graphic's route (native, generated or composite) recorded with its reason.
Taught in 30.10 Which tool for which job, and the gate.
Chapter 31 · Handing over
Before a handoff leaves you
The native project was saved by Premiere, on a recorded build; the media is collected, flat and ASCII-named, with a checksum for each file.
Stems, title sources and a reference render of the same version are in the package.
Every promised revision was performed on a copy, saved, reopened and rendered; the package was moved and relinked, manual locates counted.
The editability table was filled from results; no "expected" is left.
Every export carries its slate and version; delivery masters are in their own folder, reopened and probed; every asset carries its origin label.
An interchange file is included only for a destination that has been tested.
Taught in 31.5 Building and verifying a handoff.
Chapter 32 · Premiere Pro and the finishing tools
An upscaled or boosted clip
Probed against the source: same duration and frame count (unless a boost was ordered), same aspect, colour tags unchanged, audio kept.
Compared with the native original at the same grade, in motion, at 100 % and 200 %: faces, labels and every Arabic letter unchanged; no waxy skin, edge shimmer or lost grain; after a boost, the mouth frame by frame.
Labelled "upscaled (tool, version, date)", with the native original kept.
A Generative Extend
Every new frame inspected at 200 %; no new hands, no drift of label or product; extended audio heard through its splice.
Listed in the transforms with its range, tool and version.
Captions
Every Arabic run compared with the canonical line letter by letter.
Direction, joining, punctuation and numerals right in the real player, on the audience's device.
Timed to the audio that shipped, against the lips.
One file per language per version, each opened.
An import or a final export
The translation log read; first, middle and last frame of each placement seen.
Duration within one frame of the plan; loudness measured against the named specification (30.6).
The export probed and reopened.
Taught in 32.7 Checks before you sign.
C.7 Running the production
Chapter 33 · Higgsfield
After every job
Read the ledger first. Its line is the only proof of the charge. Where the price you saw and the debit differ, write both.
Download the original, wait until the file has finished writing, and archive it. A checksum taken from a half-written file is wrong.
Probe it: frame size, frame rate, duration, frame count, sound. A successful request proves nothing about the file.
Make a contact sheet (six stills at 0, 20, 40, 60, 80 and 100 per cent of the clip), then look at the key frames at 100 % and 200 %, then listen. The sheet finds problems; only the director's eye and ear pass the shot.
Write the run record (the run record line, 33.4); then judge, or label the result a technical read.
Taught in 33.7 Checks before you sign.
Chapter 34 · Money, rights and terms
Money and rights, in order
Before a paid session: the packet signed, with a cap and an end date within the month; the balance read; the ledger reconciled by job.
Before each job: today's quote on the exact request, media attached; the quote plus what is settled inside the cap.
Before an upload: Auto-publish off; every asset classified; public, yours or released, or a stand-in; every face and voice released for AI use and training; a written decision wherever a real name is used.
Before delivery: a rights line for every voice, cue and effect, its terms read and saved; no library voice unless all four conditions hold; the client told what is synthetic; the seven contract points in place.
After delivery: masters and anchors, prompts, settings and references archived; the client's material deleted from the platform; the dated terms filed.
Every month: the terms and policies re-read against the dates in 34.4 to 34.9 and in each tool's Limits, prices and rights (N.9).
Taught in 34.12 The gates, the records and where each answer lives.
Comments