FLUX.3 Video Prompting Guide: 16 Use Cases, 74 Tested Prompts
Updated · 74 examples · tested on FLUX.3 in Martini
Write a plain description that names who, where and what happens, keep it near 1,400 characters, quote every line of dialogue and every word on screen, and end on a named event. Format barely matters; the nouns do.
This guide comes from 971 FLUX.3 takes across 13 controlled experiments, not from a style sheet. Each use case below gives the rules that held up, then real takes with their full prompts: the one that works, variations, and where it breaks. Every use case links to the full report with every other take from that test. Each prompt is shown exactly as it was sent, and each clip is a take its report cites, straight out of the model: nothing is cut, graded or retouched. Try it in ChatGPT or Claude hands the exact brief to the Martini connector.
The FLUX.3 prompt formula
Keep SUBJECT, SETTING and ACTION; delete any other line you don't need. Losing a noun was the only failure mode the prompt-style test found.
SUBJECT: who, with one detail that makes them specific. SETTING: where and when, with the light source named. ACTION: beat → beat → beat → named ending. DIALOGUE: SPEAKER (language): "exact line." CAMERA: framing and movement, or "one continuous take". AUDIO: the sound sources, and what each one causes. TEXT: caption: "EXACT WORDS ON SCREEN"
FLUX.3 prompt cheat sheet
- Length
- About 1,400 characters. Gains flatten there; past 2,400 is texture.
- Format
- Barely matters. Plain paragraph, labelled fields or shot list all work.
- Nouns
- Who, where, what happens. Losing one is the only failure mode we found.
- Edit
- Shot list = 3–5 cuts. Timecode blocks = one take. Prose = cuts multiply with words.
- Ending
- Name a terminal event. Unnamed endings are the beat you lose.
- Text
- Exact strings in quotes. Never ask a graphic to count.
- Sound
- Source → person → reaction verb. No beat-synced cutting.
- Keyframes
- Four or five pins. The ends are targets, the middle is a suggestion.
- Rerolls
- Change the face, lens and ending. Never the place, light or look.
01 · 3 examples · full report
A single shot from one paragraph
Write a plain paragraph that names who, where and what happens. It won or tied nearly everywhere across ten prompt styles.
- Lead with the nouns: the subject, the place, the action. Every bad take in the prompt-style test had lost one of them.
- Lighting comes from lighting words. "Sodium" gave orange night; no time of day gave calm blue daylight.
- Camera language is a bonus on top of the nouns, never a replacement for them.
186 characters, no camera language, and the deckhand still hauls her aboard by the arm.
01 · 10s · 21:9 · draft · 186 chars · report
Cinematography language on top of a named scene: through the pass, snap insert on the lid, back to the master. Obeyed to the letter.
02 · 10s · 21:9 · draft · 196 chars · report
Locked 50mm through the pass; the flare blows highlights for two frames; snap-zoom insert on the lid-and-towel kill; hold the chef's single breath in close-up; return to the wide as the bell hits.
All technique, no nouns. Asked for "a place losing its light" and got an empty apartment.
03 · 15s · 21:9 · draft · 196 chars · report
One wide master throughout; light does the editing — practicals out in a frame, phone screens in ones and twos, then a single warm source blooming. Subject: a place losing and refinding its light.
02 · 3 examples · full report
A structured prompt with labelled fields
Use SUBJECT / SETTING / ACTION / CAMERA / AUDIO / MOOD when you want a checklist that makes forgetting the subject impossible.
- Labelled fields and the numbered shot list were the only two styles to land all five payoffs.
- Write ACTION as a sequence of beats with an ending, not a mood.
- Timestamps ([00:00–00:04]) pin the duration to your last timestamp — use them only when you want that length.
The cleanest payoff on the board: tight single, spotlight, dove settling on his head.
04 · 15s · 21:9 · draft · 307 chars · report
SUBJECT: an escaped dove and the magician it embarrasses. SETTING: an old proscenium theater, full house. ACTION: misfire → spotlight chase → return → landing on his head → bow. CAMERA: house master, spotlight-led sweep, tight single. AUDIO: gasps, wingbeats, vamping orchestra, applause. MOOD: comic grace.
The same fields on a night market: a blacked-out market lit by a sea of phone screens. Scale nothing else reached.
05 · 10s · 21:9 · draft · 276 chars · report
SUBJECT: a night market surviving a blackout. SETTING: crowded open-air market, city night. ACTION: power cut → hush → phone lights bloom → gas lamp relit → cheer. CAMERA: one wide master, light as the edit. AUDIO: full → silence → single sounds → flood. MOOD: communal, warm.
A numbered shot list instead of fields: the only take that executed a four-shot list in order, with real cuts at the right moments.
06 · 10s · 21:9 · draft · 217 chars · report
Shot 1 — wide: a packed kitchen line at service, a wok erupts in flame. Shot 2 — insert: lid and wet towel slam down in sequence. Shot 3 — close: the chef's face, one breath. Shot 4 — wide: service resumes, expo bell.
03 · 5 examples · full report
How long to make the prompt
Aim for about 1,400 characters. FLUX.3 reads every word out to 4,700, but the film stops getting better at about 1,400, and past 2,400 the extra writing buys texture nobody sees.
- Spend characters on who is watching, what's on the sign and what's in frame besides the subject: the facts that change what the shot means.
- Write past 2,400 only when the film is actually bigger: a second character, an exterior, a cut.
- Pick the format for the edit you want. Timecode blocks gave one unbroken take at every length; a shot list gave 3–5 shots; prose let cuts multiply with the word count.
The diner at 1,349 characters: cook, nurse, CLOSING — THANK YOU sign. The whole scene, for a quarter of the words.
07 · 20s · 21:9 · draft · 1,355 chars · report
ACTION — A short-order cook makes one last meal on the diner's final night. He scrapes the flat-top clean before laying the eggs down. The regular at the counter watches him work and says nothing. SETTING — An all-night diner on the edge of a state highway, nearly empty. A long counter with chrome stools, two of them patched with tape. A hand-lettered sign in the window reads: CLOSING — THANK YOU. SUBJECT — A cook in his sixties, forearms scarred with old griddle burns. White tee, white apron gone grey, a paper hat he still bothers with. The customer is a night-shift nurse still in her scrubs. DIALOGUE — He says: "Kitchen's closed. Sit down anyway." She says: "You know I only came for the coffee." He says: "Then the eggs are on the house." CAMERA & LIGHT — One slow dolly along the counter at seated eye height, 40mm. Warm tungsten practicals inside against blue rain-dark windows. The pass light throws a hard warm rectangle across the flat-top. SOUND & MUSIC — Rain on glass, a compressor hum, eggs hitting the hot flat-top. The scrape of the spatula comes in long, practiced strokes. A radio in the kitchen plays AM country, half-tuned and low. GRADE — Warm tungsten interior against cool blue night, gently faded. Skin tones amber, the whites of the apron allowed to go cream. Neon red given a soft bloom without ever clipping to pink.
1,434 characters. Three empty chairs turn a dancer into an audition.
08 · 15s · 21:9 · draft · 1,440 chars · report
ACTION — A dancer performs an audition solo and is stopped forty seconds in. She is mid-phrase when a voice from the dark tells her to stop. She holds the position she was stopped in rather than dropping out of it. SETTING — A bare rehearsal studio with a sprung floor and a wall of mirrors. Fluorescent tubes overhead, half of them switched off. A folding table at the far end with three chairs behind it. SUBJECT — A dancer in her early twenties, compact and very strong through the back. Dark hair pulled into a bun that has already started to come loose. Practice clothes: black leotard, grey tights with a hole at one knee. DIALOGUE — A voice from behind the table says: "Stop. Thank you." She says: "Sorry — do you want it from the top?" The voice says: "Do it again. Same thing." Nothing else. CAMERA & LIGHT — One locked-off wide on a 35mm from behind the table, static throughout. Overhead fluorescents only — flat, green-tinged, no shaping, no fill. The mirrors double her, so the frame holds two of her at all times. SOUND & MUSIC — A tinny phone speaker plays the audition track from the floor. The track is a solo piano piece, mid-tempo, slightly too quiet for the room. Bare feet on sprung floor: a hollow thud with a faint resonance after it. GRADE — Flat, cool, unflattering fluorescent white. Slightly green in the midtones, the way rehearsal rooms actually look. Skin allowed to go sallow rather than corrected warm.
4,110 characters, and the last frame is exactly what the last sentence of the prompt asked for. It reads to the end.
09 · 10s · 21:9 · draft · 4,110 chars · report
An office throws a birthday party with the wrong name on the cake. The planner sees it first and puts her body between cake and room. Her whisper-fight with the intern happens entirely behind balloons. The song starts too early and cannot legally be stopped. Mid-song, the honoree reads the icing and his smile freezes solid. A manager attempts a rescue toast that makes everything worse. The intern goes to work on the icing with a plastic knife. A trick candle relights twice and nobody names the omen. Cake is served into a silence broken by one loud yum. At the end, the honoree sincerely thanks the room for Gary's party. It all happens in a beige break room dressed with three sad balloons. A banner droops at one corner over the fridge. The cake holds the table's centre: white icing, blue script, wrong name. Napkins fan beside plastic forks standing in a cup. Fluorescents hum over carpet tiles in two shades of grey. The good conference chair has been wheeled in as a throne. A whiteboard still shows last week's sales funnel. The window gives onto a parking structure and one brave tree. A diet soda sweats a ring beside the cake board. The microwave clock and the wall clock disagree by nine minutes. The honoree is a mild man in a checked shirt, turning fifty today. The planner runs the room like a crisis command post. The intern is twenty-two and visibly rehearsing apologies. The manager carries the confidence of a man about to make it worse. A dozen coworkers arrange themselves between cake and exits. One woman films everything on her phone for no stated reason. HR stands at the back, sipping, saying absolutely nothing. The honoree's glasses catch the fluorescents when he blinks. The planner's smile and her eyes run two different meetings. Everyone present will describe this day differently, and wrongly. The planner tells the camera that everything is completely under control. The intern insists they said Gary on the phone, twice. The manager toasts a man who needs no introduction — Gary. The honoree corrects him — it's Doug — and the toast pivots without shame. Someone in the back asks who Gary is; someone answers: exactly. The planner hisses to scrape faster; the intern notes it is fondant. The honoree assures the camera that fifty is fine, twice. HR wants it noted, for the record, that they ordered nothing. A speech is demanded; the honoree begs, quietly, for no. Alone with the camera, the intern asks if this job is forever. It is shot like a documentary that got lucky: handheld, late zooms. The light is flat office fluorescent with no cinematic help. Push-ins hunt reactions: the freeze, the wince, the sip. Talking heads sit against the beige wall between scenes. The cake gets loving product close-ups it does not deserve. One slow zoom crosses the doorway during the whisper-fight. Whip-pans connect the song and the scraping knife. HR haunts the frame edge like a Greek chorus. Once, from outside the window, the party plays as a terrarium. The final image is a locked extreme close-up of the ruined name. The soundtrack is room tone: fluorescent hum, fridge, distant phones. The song arrives ragged and in two different keys. Whispers meant to be private land hot on the boom. The fondant scrape is horribly, perfectly audible. A party horn deflates somewhere off camera. Forks click on paper plates in the silence. The trick candle's reignitions get their own tiny foley. There is no score; the comedy is dry and unassisted. The microwave beeps four times inside the manager's toast. Under the last shot, one air vent whistles a thin note. The grade is flat corporate daylight, true to the fluorescents. Beige sits on beige; colour management by facilities. Skin stays honest, shiny foreheads and all. The cake's white icing is the brightest object by far. A slight video sharpness reads broadcast, not cinema. The balloons' red is the only cheerful pixel. Interviews run a half-stop darker, accidentally moody. No grain, no halation, no mercy. The exterior shot cools to grey around the warm sad party. The final close-up is clinical, evidence-photo neutral.
The full 4,359: locks the door, turns the sign, kills the neon. The top rung pays off when the film is genuinely bigger.
10 · 20s · 21:9 · draft · 4,365 chars · report
ACTION — A short-order cook makes one last meal on the diner's final night. He scrapes the flat-top clean before laying the eggs down. The regular at the counter watches him work and says nothing. He plates eggs, hash and toast without being asked for an order. He refills her coffee at the exact moment the cup goes empty. She eats slowly, deliberately making the meal outlast closing time. He starts the closing list anyway: grill off, hood fan off, lights. He folds his apron once and sets it on the shelf below the register. She leaves the money under the cup although he already waved it off. He locks the door behind her and turns the sign over for the last time. SETTING — An all-night diner on the edge of a state highway, nearly empty. A long counter with chrome stools, two of them patched with tape. A hand-lettered sign in the window reads: CLOSING — THANK YOU. The flat-top and fryer sit behind a pass with a bell nobody rings. A pie case rotates slowly with one slice of cherry pie left in it. Booth upholstery gone shiny at the edges from fifty years of use. A wall of photographs: staff, regulars, one framed first dollar. Rain on the parking-lot glass, one semi idling under the lot light. Boxes stand half-packed along the back wall where shelves were. The neon OPEN sign buzzes, its O flickering at its own tempo. SUBJECT — A cook in his sixties, forearms scarred with old griddle burns. White tee, white apron gone grey, a paper hat he still bothers with. The customer is a night-shift nurse still in her scrubs. Her coat stays on but open, her bag parked on the next stool. His hands do everything in an order decided decades ago. He wipes surfaces that are already clean without noticing. She has the eyes of someone at the end of a twelve-hour shift. His glasses ride low and get pushed up with the back of a wrist. A small tremor in his hand shows only when he pours. Neither of them is in any hurry to let this end. DIALOGUE — He says: "Kitchen's closed. Sit down anyway." She says: "You know I only came for the coffee." He says: "Then the eggs are on the house." She asks: "What happens to this place on Monday?" He says: "They take the sign first. Sold it to a collector." She says: "That sign is the only landmark this road has." He says: "Forty-one years. My father had it eighteen before me." She says: "Best eggs in the county. That was never a secret." He says: "Everybody says so the week you close." She says: "Goodnight, Ray." He says: "Goodnight. Drive slow." CAMERA & LIGHT — One slow dolly along the counter at seated eye height, 40mm. Warm tungsten practicals inside against blue rain-dark windows. The pass light throws a hard warm rectangle across the flat-top. A static two-shot holds the cook and the nurse across the counter. Cutaways are close and unhurried: eggs, coffee, the taped stool. Neon from the window lays red along the chrome stool caps. Steam off the grill catches the pass light and hangs there. The final setup is from outside, through glass beaded with rain. Reflections layer the neon over both of them in the window shot. Hold the exterior wide as the lights go off in two stages. SOUND & MUSIC — Rain on glass, a compressor hum, eggs hitting the hot flat-top. The scrape of the spatula comes in long, practiced strokes. A radio in the kitchen plays AM country, half-tuned and low. Coffee pours long into the mug and the pot returns to the burner. Their voices sit close-miked and low, almost under the room. The pie case motor ticks each rotation like a slow clock. A semi passes on the wet highway, rising and falling away. The bell over the door rings once when she leaves. Keys, then the deadbolt, then the neon cutting out with a click. No score anywhere; the compressor is the last sound over black. GRADE — Warm tungsten interior against cool blue night, gently faded. Skin tones amber, the whites of the apron allowed to go cream. Neon red given a soft bloom without ever clipping to pink. Shadows lean brown rather than black, like an old print. Faint halation on the practicals, in the way of pushed film. Grain fine but present, heavier in the blue window areas. The pie case fluorescent stays slightly green, uncorrected. Rain highlights on the glass kept specular and tight. Contrast eases up gently for the final exterior wide. The last frame cools as the interior warmth shuts off.
A shot list at rung 5: at the halfway mark it shows the same overhead spiral as rungs 1 and 10. Only the grade moved.
11 · 10s · 21:9 · draft · 2,065 chars · report
SHOT 1 — Wide: a lighthouse on a bare rock, sea on all sides, fog closing in. Static tripod, 32mm, the tower centred and small against the murk. The beam sweeps a bright bar through the fog every five seconds. Hold the frame long enough that the sea starts to feel patient. No movement but water, beam and fog; the shot outwaits the viewer. SHOT 2 — Interior mid-shot: the keeper winding the mechanism, methodical. A knock lands below — three beats, patient — and he stops. 50mm at chest height; he holds dead centre, hands stilled. He listens without breathing; the kettle steams behind him. The second knock arrives exactly as before, no louder. SHOT 3 — Overhead down the spiral: his lantern descends into black. The whitewashed stairs coil like a shell below the camera. His shadow climbs the curved wall, huge and wrong-jointed. Iron steps ring under his boots, each note distinct. The lantern shakes only a little, and he watches it shake. SHOT 4 — Close on the iron door handle, lantern light from off frame. He asks who is there; the fog outside says nothing. The handle turns once, slowly, and returns to rest. Macro patience: thread of rust, old paint, his reflection warped. His hand enters frame, hovers over the bolt, and withdraws. SHOT 5 — Lamp room: he looks down as the sweep shows the rock ledge empty. His reflection stands beside him in the black glass. The beam strobes the room: light, dark, light, dark. Wide enough to hold the window behind his shoulder. He exhales; twenty-two years of rocks say it was wind. SOUND — Sea on rock under everything, patient and enormous. The mechanism's clockwork tick fills the tower's spine. Three knocks, evenly spaced, neither loud nor gentle. The fog horn moans at long, irregular intervals. Held breath, then its release, mixed close. GRADE — Cold slate blues and lamp-oil amber, nothing neutral. Fog flattens the exterior; the tower stays hard inside. Blacks absolute in the stairwell's centre. The beam burns clean white and leaves ghosts on the eye. Skin waxen in lantern light, warm but wrong.
04 · 3 examples · full report
A dialogue scene
Quote the lines exactly. Three lines of dialogue will build the location, the props they mention and shot/reverse-shot coverage on their own.
- The cut tends to land on the line change. If you want a cutaway, name the object in the dialogue.
- Give speech room: at 5 seconds expect to be cut off mid-sentence. Ten seconds or more for a full exchange.
- Silence is hard to get. In the sound test every "hush" came back at full level; a timecoded silence inside a full brief (The Clock, below) did hold.
Three lines about a letter produce a woman, an envelope insert, a close-up and a reverse. Nothing in the prompt describes a room, a prop or a shot.
12 · 8s · 21:9 · draft · 134 chars · report
Swedish dialogue with English subtitles. Two faces, one pendulum, and a scripted silence that arrives at 0:11 and holds.
13 · 20s · 21:9 · draft · 2,072 chars · report
A 20-second Scandinavian chamber drama, fully directed. Dialogue in Swedish with English subtitles. Stillness is the style; the faces are the plot.
LOGLINE — Two sisters divide their late mother's belongings. Everything is settled except the clock.
SHOT 1 (0:00–0:05) — Interior, a spare farmhouse room, winter light. A wooden table with small objects sorted into two rows: candlesticks, linen, a Bible, photographs. KARIN (50s, severe bun) and ANNA (40s, coat still on) sit opposite one another. On the wall between them, a pendulum clock ticks.
KARIN: 'Då är det bara klockan.' ('Then there is only the clock.')
SHOT 2 (0:05–0:11) — A tight two-shot in profile, their faces half in shadow, the clock out of focus between them.
ANNA: 'Ta den du.' ('You take it.')
KARIN: 'Du drog upp den varje besök.' ('You wound it every visit.') A long pause. ANNA, barely audible: 'Jag kom aldrig.' ('I never came.') Neither face moves; only Karin's eyes.
SHOT 3 (0:11–0:16) — The clock alone, filling frame. The pendulum slows and stops. The tick ends. The silence has physical weight. Neither woman enters frame to wind it.
SHOT 4 (0:16–0:20) — Back to the two-shot. In the new silence, Karin reaches across the table — past the clock's row, past the candlesticks — and closes her hand over Anna's. Anna does not look up, but her thumb moves, once, over her sister's knuckles. Hold. Cut to black.
LIGHTING — Low white winter sun through one lace-curtained window, camera-left; grey bounce, no artificial sources; faces modelled like Vermeer, one side bright, one lost.
CAMERA — 50mm and 85mm, locked off; no camera movement anywhere in the clip; compositions frontal, the two-shot so close the frame holds only faces.
SOUND — The clock is the score: tick, room tone, the shift of a wool coat, breath. When it stops, true silence except wind under the eaves.
MUSIC — None until the final second: a single sustained cello note under the cut to black.
GRADE — Muted, near-monochrome color — grey, bone, umber; soft grain; skin pale and truthful; blacks gentle, never crushed."Have you tried being taller?" / "No, I forgot to do that before I left the ground." The lines land, but there is a hard location cut at 6.8s in a shot told not to cut.
14 · 20s · 21:9 · draft · 333 chars · report
A climber hangs at the crux of a hard route, talking herself through it out loud. Her belayer, far below, shouts up advice that is confident, constant and completely useless. The exchange keeps going as her forearms fail, funnier and more desperate the longer she stays on the wall. Let the back-and-forth continue and build. No cut.
05 · 5 examples · full report
Sound that drives the action
Write sound as an event with a consequence: the thing that makes the noise, then the person, then the verb they react with.
- Name the reaction — flinches, freezes, turns. The model animates the verb you write; it does not infer one.
- The reaction lands about halfway through the take, so a 5-second shot spends two seconds on setup.
- Don't ask for cuts on the beat — they land no closer than chance. A light or colour change on a musical event does land.
"A door slams hard. She flinches and looks up": +17 dB into the reaction, and the frames show exactly the flinch.
15 · 5s · 21:9 · draft · 108 chars · report
"A distant gunshot. The whole flock erupts at once": a 20 dB jump in one second, and the square goes to motion blur on the same frame.
16 · 5s · 21:9 · draft · 79 chars · report
A quiet square with pigeons. A distant gunshot. The whole flock erupts at once.
"The room's color warms with the first chord": the light starts to rise 60 ms after the chord. A lighting change, not a cut.
17 · 8s · 21:9 · draft · 89 chars · report
A needle drops on vinyl: crackle first, then the room's color warms with the first chord.
"Until one sharp stop — held silence": the dancer freezes on cue, but the final second is the loudest in the take. It can stop the picture, not the sound.
18 · 8s · 21:9 · draft · 95 chars · report
A flamenco dancer and guitarist trade accelerating phrases until one sharp stop — held silence.
Rain and motion build together, then the clip just ends at maximum. It can build. It can't land.
19 · 8s · 21:9 · draft · 90 chars · report
Rain intensifies in crescendo with a string section; both stop together on the same frame.
06 · 5 examples · full report
A 20-second scene that keeps going
FLUX.3 writes to the runtime you ask for. Give it an engine sentence and a named ending, and twenty seconds stays alive to the last second.
- Add an engine: "Let the exchange keep escalating." The one 20s prompt without one produced twenty seconds of nothing.
- End on a terminal event — "…until the ferry is small." Named endings landed at 18–19 seconds.
- A 5s take isn't a shorter story, it's the first five seconds of a longer one. Write one complete beat for short takes.
Breaks: Three of twenty-nine 20s takes broke a "no cut" instruction, and one jumped to a different location. That needs a reroll, not a rewrite.
Sixteen notes from the director, each one worse than the last, exactly as briefed. The engine: "Let the exchange keep escalating."
20 · 20s · 21:9 · draft · 352 chars · report
A dark grading suite. A colorist nudges one shot from cold to warm while the director beside her keeps changing his mind: warmer, no, back, no, somewhere between those two. Her patience holds and then does not. The notes get more abstract and less useful the longer it goes. Let the exchange keep escalating over the same single frame. Continuous take.
A named ending: the first customer walks into frame at 19.5s and someone says "Morning." Delivered on the last second of runtime.
21 · 20s · 21:9 · draft · 431 chars · report
Pre-dawn, a street food cart under a single bulb. A veteran vendor is training a nervous new apprentice, and the apprentice is terrible: wrong order, wrong knife, wrong everything. The vendor's corrections start patient and become a running comic monologue about respect for the griddle. Let the lesson keep escalating with new mistakes and new lectures until the first customer of the morning appears. One continuous take, no cut.
The guard's line lands at 12.0s and the critic recovers at 14.0s. The whole scene is in the back half.
22 · 20s · 21:9 · draft · 399 chars · report
A white gallery. A critic in an expensive coat stands before a completely blank canvas and explains it, at length, to a security guard who did not ask. The reading starts pretentious and climbs: absence, the void, the artist's silence. The guard offers one flat sentence that derails everything, and the critic recovers and goes even bigger. Let the monologue keep unfolding with new claims. No cut.
One sentence and no engine: nineteen seconds of a man sitting still.
23 · 20s · 21:9 · draft · 92 chars · report
A man finishes telling a story at a dinner table and stops talking. The camera does not cut.
The crowd builds beautifully, but the song sings "Then everybody sings along" four times. Extra seconds don't reward a repeating action.
24 · 20s · 21:9 · draft · 365 chars · report
A busker opens his guitar case on a busy pavement and starts a song. A passerby stops and sings the second line, badly. Another joins. Within the shot it becomes a small, chaotic, unrehearsed street performance the busker did not ask for and cannot stop. Let it keep building: more voices, more people, the busker's face doing all the work. Continuous shot, no cut.
07 · 5 examples · full report
A multi-shot short film in one generation
Write a logline, then numbered shots with timecodes. 27 of 32 twenty-second briefs came back with the four shots they asked for.
- SHOT 1 (0:00–0:05), SHOT 2 (0:05–0:11)… — a shot list gave 3–5 shots at every prompt length we tried.
- Put subtitles and narration in quotes; they came back verbatim.
- Want one unbroken take instead? Write timecode blocks without SHOT labels — that format held a single shot at every length.
Breaks: It will not break physics or fake a frame rate, however the brief is written.
Nine cuts, aerial to interview to reenactment to end card, and it found "a pumpkin-shaped absence in the vines, a perfect flattened circle."
25 · 20s · 21:9 · draft · 2,637 chars · report
A 20-second prestige true-crime documentary, fully directed and played entirely straight. The stakes are a pumpkin. LOGLINE — The night before the county fair, the heaviest pumpkin in county history vanished from Gerald Husk's field. SHOT 1 (0:00–0:05) — Aerial drone at dawn, mist over flat farmland, ominous score. Slow push toward a lone field with a pumpkin-shaped absence in the vines — a perfect flattened circle. Lower-third title, prestige-grey serif: 'HARROW COUNTY. POPULATION 1,940.' NARRATOR (V.O., gravel): 'By morning, all that remained... was the stem.' SHOT 2 (0:05–0:11) — Kitchen-table interviews, shallow depth, subjects lit like Vermeer. NEIGHBOR (70s, cardigan, hands around a mug): 'Everyone knew what that pumpkin meant to Gerald.' Cut to: RIVAL GROWER (60s, cap, defensive): 'Was I jealous? Sure. Nine hundred pounds of jealous. But I was at the fish fry. Forty people saw me at the fish fry.' Archive photo zoom with a subwoofer hit: Gerald beside the pumpkin, both looking proud. SHOT 3 (0:11–0:16) — Dramatic reenactment, cold blue night grade, faces never shown: a wheelbarrow silhouette struggling across a moonlit field at 3 a.m., wheel squeaking under impossible weight; a rope snaps taut; someone whispers 'lift with your legs.' Intercut: the evidence board — red string connecting a seed catalogue, a fair schedule, a receipt for 'one (1) engine hoist,' and a blurry photo of a scarecrow. SHOT 4 (0:16–0:20) — Slow push on GERALD HUSK himself (60s, overalls, eyes wet) at his kitchen table, a single pumpkin seed in a small evidence bag before him. GERALD: 'I don't want names. I just want to know she went to a good pie.' Cut to black. Title card, white serif: 'The pumpkin was never found.' Beat. A second line fades in: 'The scarecrow was released without charge.' LIGHTING — Interviews in single-window Vermeer key against dark kitchens; reenactment in cold blue moonlight with flashlight beams; drone dawn golds. CAMERA — Slow drone push; locked interview frames with prestige headroom; handheld reenactment paced like dread; macro slider across the evidence board and the seed. SOUND — Doc-clean interview audio; reenactment foley heavy on wheelbarrow squeak and rope strain; subwoofer hits on archive zooms; a kettle far off in Gerald's kitchen. MUSIC — Full prestige true-crime score played straight: low single piano notes, string harmonics, a pulsing synth under the reenactment, silence for Gerald's line, one final piano note under the last title. GRADE — Prestige desaturation: teal-slate interviews, blue reenactment night, archive photos warmed and vignetted; heavy but tasteful.
Broadcast multicam grammar — gantry wide, low rail, pocket cam — and the audio hits all four scripted events.
26 · 20s · 21:9 · draft · 2,626 chars · report
A 20-second live sports broadcast, fully directed as television. Snooker world final, deciding frame, one red left. The tension is entirely hush and procedure. LOGLINE — Twenty years of losing finals come down to one red ball, and someone in the dark coughs. SHOT 1 (0:00–0:05) — Broadcast main camera: the table an island of brilliant green light in a black arena, two thousand people invisible and utterly silent — the air-conditioning is audible. Lower-third broadcast graphic: 'WORLD FINAL — DECIDING FRAME. ONE RED REMAINS.' HALLORAN (50s, waistcoat, silver hair) circles the table, chalking his cue with a slow screwing motion, eyes never leaving the red. COMMENTATOR 1 (whisper): 'Twenty years he's waited to be back here.' COMMENTATOR 2 (whisper): 'And the red sits safe.' SHOT 2 (0:05–0:11) — Broadcast coverage grammar: cut to the low rail camera in gentle slow motion as he bends, bridges, settles — the cue sliding twice through the bridge in feathered rehearsal. Cut to the pocket camera: the red in the foreground, the distant white, the geometry laid bare. The arena holds its breath so completely the commentary stops too. SHOT 3 (0:11–0:16) — A single COUGH from somewhere high in the dark. Halloran stops. Stands up to his full height and — instead of irritation — smiles faintly toward the darkness, a man forgiving the world its nerves. Scattered relieved laughter dies instantly. He re-chalks: the same slow screwing motion. COMMENTATOR 1 (whisper): 'Composure. That's the twenty years talking.' He bends again. SHOT 4 (0:16–0:20) — An extreme slow dolly along the cue line to the tip hovering behind the white; the feathering stops; a held half-second of absolute stillness — and he strikes. The white rolls away into the green. Cut to black on the pure click of contact, before any ball arrives anywhere; the roar begins under the black and is cut off. LIGHTING — Tournament rig: brilliant flat white over the baize, absolute black beyond the table's edge; faces half-lit at the table's border; the red glowing like a jewel. CAMERA — True broadcast multicam: main gantry wide, low rail slow-mo, pocket cam; the final dolly the only cinematic move, and earned. SOUND — Arena hush with air-conditioning hum, chalk squeak, the cough enormous in the silence, the cloth-slide of the bridge hand, the terminal click; commentary whispered like men in church. MUSIC — None until the cut: a single timpani-and-strings hit under the black with the roar, instantly cut off. GRADE — Broadcast-clean: saturated baize green, true whites, deep arena black, minimal grain; the slow-mo shots slightly creamier.
Cel-look 2D animation with painted backgrounds, and three Japanese lines subtitled word for word.
27 · 20s · 21:9 · draft · 3,827 chars · report
A 20-second hand-drawn 2D anime sequence, fully directed. Dialogue in Japanese with English subtitles. LOGLINE — A girl runs for the last train in the rain. She misses it. It is the best thing that happens to her all year. STYLE — Traditional cel-look 2D animation on twos, painted watercolour backgrounds, visible brush texture in the skies, hand-inked character line with slight weight variation. Rain drawn as animated white streaks over the background plate, not a particle effect. No 3D, no digital gloss. SHOT 1 (0:00–0:05) — A provincial station approach at night, painted in deep blues and wet blacks, sodium lamps blooming in the rain. YUKI (17, school uniform, satchel, no umbrella) runs into frame from the bottom left, feet throwing up spray, hair plastered flat. Held cel animation on her run cycle; the background pans hard behind her to sell the speed.
YUKI: 「間に合え、間に合え、間に合え——!」 ("Make it, make it, make it—!") SHOT 2 (0:05–0:10) — She takes the stairs three at a time, satchel swinging, one hand on the rail. The camera is locked at the top of the stairs looking down, so she runs directly at us and grows in the frame. The station's fluorescent light hits her face as she rises out of the dark stairwell — the moment her face becomes fully lit is timed to a single animation frame.
STATION ANNOUNCEMENT (off, tinny, calm): 「ドアが閉まります。ご注意ください。」 ("The doors are closing. Please stand clear.") SHOT 3 (0:10–0:15) — She reaches the platform. Wide, flat, held. The train is already moving. She stops running. Her shoulders drop. Two frames of her hair and skirt continuing to move after her body stops — the small physical detail that sells the animation.
The last carriage passes. Behind where it was, on the opposite platform, a BOY her age is standing alone with an umbrella, also having missed it, also soaked.
They look at each other across the tracks. Neither moves. SHOT 4 (0:15–0:20) — Two-shot, split by the empty track between them. He raises the umbrella slightly and tilts it — an offer, ridiculous across four metres of rail. She laughs, once, and it is audible and unguarded and completely changes her face.
YUKI: 「届かないよ。」 ("It won't reach.")
BOY: 「知ってる。」 ("I know.")
The rain keeps falling. The frame holds on both of them, small, at opposite edges of a wide painted background.
Cut to black on the sound of the next announcement beginning. LIGHTING — Night, wet, sodium and fluorescent. Two light qualities only: the warm orange of the station lamps outside, and the flat cold green-white of the platform fluorescents. Rain catches both. Her face is lit by whichever she is standing under, and the transition between them in Shot 2 is the visual event of the clip. CAMERA — Shot 1: lateral tracking pan with the run. Shot 2: locked high angle down the stairs. Shot 3: wide, static, held long. Shot 4: locked wide two-shot, absolutely still, both figures small in frame. No camera moves in the second half at all. SOUND — Rain on concrete, on the platform canopy, on her satchel — three distinct textures. Running footsteps in water. Her breathing, hard and unglamorous. The train's departure: motor whine rising, then the specific rhythmic clack fading. The station announcement is tinny and slightly distorted. Both lines of dialogue are close and dry against all of it. MUSIC — Solo piano, entering at 0:03, simple and slightly hesitant, playing under the run. It stops dead at 0:10 when she stops running. Complete musical silence for five seconds. At 0:17, on her laugh, it returns with strings underneath and resolves warm. GRADE — Rich saturated night blues, sodium orange, fluorescent green-white. Painted-background warmth. No filmic grain — instead a very fine cel-and-paper texture over the whole frame. The Japanese must sound natural and the subtitles must be correctly spelled and timed.Written as one shot: zero cuts, twenty seconds of backward steadicam, and the scarf, the dog and the glass arrive on their scripted seconds.
28 · 20s · 21:9 · draft · 3,446 chars · report
A 20-second restaurant farce, fully directed. One continuous take, no cuts, no dialogue except orders. LOGLINE — A waiter crosses a small dining room carrying three plates. Everything that can go wrong does, and he does not drop a single one. SHOT (0:00–0:20) — ONE UNBROKEN STEADICAM TAKE, moving backwards ahead of him at walking pace for the full twenty seconds. 0:00–0:04 — MARTA, the chef, slams three plates onto the pass and hits the bell. LUCA (20s, waistcoat, one hand already occupied with a wine bottle) loads all three onto his left arm in a single practised movement and turns into the room. MARTA: "Table nine! Go!" 0:04–0:08 — He steps into the dining room. A CHILD at table four chooses this moment to reverse his chair directly into Luca's path. Luca pivots on one foot, plates level, and continues without breaking stride. The child's mother does not look up. 0:08–0:12 — A COUPLE at table six stand up simultaneously to swap seats. Luca goes between them, turning sideways, the bottle passing under one raised arm and over the other. Somebody's scarf drags off a chair and catches his ankle. He steps out of it mid-walk, still level. 0:12–0:16 — A DOG under table seven, previously unseen, stands up. Luca goes up onto the step of the raised section to avoid it, and at that exact moment a tray of empty glasses being carried the other way by a COMMIS clips his shoulder. Two glasses go off the tray. Luca catches one against his chest with his free forearm. The other one falls. It does not break. It bounces, twice, and rolls under a table. 0:16–0:20 — He arrives at table nine. He sets down all three plates, in order, perfectly, without a sound. He straightens, tops up a water glass, and says the only line of the clip. LUCA: "Sorry about the wait." Behind him, out of focus, the entire dining room is a slow-motion disaster: the child is now under the table, the couple are still standing, the commis is on his knees, the dog is eating something. Luca does not turn around. Cut to black. LIGHTING — Warm restaurant practicals: low pendants over each table, candles, a bright hard shaft from the pass as he leaves the kitchen. He passes through pools of light and shadow as he crosses the room, so his exposure changes visibly four or five times during the take. Nothing lit for the camera. CAMERA — 28mm on a gimbal, chest height, travelling backwards continuously. It must never stop, never whip, never speed up to catch anything — it simply retreats at his pace, and everything else happens around the edges of the frame. Focus stays on Luca throughout; the chaos behind him is always soft. SOUND — A full, live restaurant: cutlery, forty overlapping conversations, a coffee grinder, the pass bell twice. Every physical event has its own precise sound — the chair scrape, the scarf, the shoulder clip, the two glasses leaving the tray, the bounce, the roll. His footsteps are steady and never break rhythm, which is the joke. MUSIC — A light, fast, unobtrusive bossa nova playing on the restaurant's own speakers, tinny and slightly too quiet, entirely indifferent to what is happening. It does not change, swell, or acknowledge anything. It is still playing at the cut. GRADE — Warm and rich, amber-forward, deep shadows between the light pools. Skin tones flattering. Slight halation on the pendants. Fine grain. No stylisation — this should look like a well-shot dinner service, which makes the choreography funnier.
One cut it shouldn't have made in the first second, then nineteen unbroken seconds of street.
29 · 20s · 21:9 · draft · 3,790 chars · report
A 20-second single-take musical number, fully directed. The music is the spine — every cut, step and camera move must land on it. LOGLINE — A woman comes out of a bodega with a coffee, and the entire street falls into step behind her for eight bars, then releases her and goes back to normal as if nothing happened. MUSIC — This is the master track and everything else is subordinate to it. A brass-led, mid-tempo soul groove at 104 BPM in F minor. Bar 1 begins at 0:00. Drums and bass only for bars 1–2. Horns enter on the downbeat of bar 3 (0:04.6). A four-bar vocal phrase from the lead runs bars 3–6. Bar 7 is a full-band break — one hit on beat one, then silence for three beats. Bar 8 is the whole band back in for the final walk. The clip ends on the downbeat of bar 9. SHOT (0:00–0:20) — ONE CONTINUOUS TAKE, no cuts anywhere. 0:00–0:04 (bars 1–2): We start tight on a bodega door as it swings out. MAYA (late 20s) steps into the frame holding a paper coffee cup, sunglasses on, entirely unbothered. The camera pulls back with her at walking pace. Two men playing dominoes on an upturned crate look up. On the last beat of bar 2, both of them stand. 0:04–0:11 (bars 3–6): The horns hit and the street commits. As Maya walks, everyone she passes joins on the beat and in her direction — the domino players, a woman with a laundry cart, three kids on a stoop, a man unloading a van. They do not surround her; they fall in BEHIND her, so the shot builds a growing wedge of people at her back while she never once looks around. Her vocal is live, and her breathing is audible in it because she is walking. MAYA (singing): "I ain't looking back for nobody / not on a Tuesday, not in this heat / y'all can follow if you keeping up / but I ain't slowing down this street" 0:11–0:15 (bar 7): The band breaks. EVERYONE freezes mid-step except Maya — twelve people held in a physically plausible pose, weight on one foot, cart tipped, laundry mid-air. Maya keeps walking through the silence for three beats, drinking her coffee. The camera holds with her. The only sound is her footsteps and traffic. 0:15–0:20 (bar 8): The band returns on the downbeat and everybody unfreezes into normal life — not dancing, just walking, working, talking, exactly as before. The camera lets Maya walk out of frame right and settles on the ordinary street behind her. Final downbeat: cut to black. CAMERA — One take, gimbal-stabilised, on a 32mm, held at chest height, moving backwards at exactly Maya's walking pace for the full twenty seconds. It never rises, never dips, never whips. The only camera event is that it slows slightly during the bar-7 freeze so the audience feels the change before they understand it. CHOREOGRAPHY — Everything must read as real people moving well, not as trained dancers. Steps are simple: a shoulder, a turn, a two-step. Every joining beat lands exactly on a downbeat. The wedge behind Maya grows from one to twelve without ever obscuring her. LIGHTING — Hard mid-afternoon summer sun coming down the street from behind camera, so faces are lit clean and the shadows are short and dark. Practical bounce off a white van at 0:09 lifts the fill for a moment. No lights that read as film lights. SOUND — Street ambience present under the music the whole way: traffic, an air conditioner, a distant siren that never gets closer. Footsteps of the whole group audible and synced. During the bar-7 break, the music drops to nothing and the street ambience comes fully up — that contrast is the moment the clip is built around. Maya's cup lid clicks when she drinks. GRADE — Warm, saturated, contrasty summer look. Rich skin tones held carefully across a range of complexions. Deep blue sky, hot white highlights on the pavement. Slight halation on the sun-side edges. Fine grain.
08 · 3 examples · full report
Period and archival looks
Name the year and the medium — "a 1929 newsreel", "a 2004 flip-phone video". FLUX.3 changes the frame shape, title cards and cut rhythm, not just the grade.
- Its sense of period is real back to 1901 and thins out after 1996.
- A future date buys you nothing the prompt did not already name. Describe the future instead of dating it.
- Ten words are enough. The era carries the look; spend the rest on the subject.
Eleven words. Opens on FOOTBALL THRILLS!, closes on THE END. The era changed the edit, not the grade.
30 · 10s · auto · draft · 53 chars · report
"1900 imagines 2000" moves as a chromolithograph. It knows the medium of a prediction better than any prediction.
31 · 15s · auto · draft · 429 chars · report
A 1900 illustrated postcard series come to life, depicting how Victorians imagined the year 2000. Personal flying machines drift between ornate towers, mechanical servants in livery carry trays, pneumatic tubes deliver letters directly into drawing rooms. A gentleman steps aboard a winged omnibus, raises his hat to the camera — and the whole contraption sinks slowly and gently out of frame while he continues to raise his hat.
An anachronism: real showroom, real price tags, real restaurant counter, and Neanderthals at full quality in all of it.
32 · 20s · auto · draft · 409 chars · report
A Neanderthal family moves through an IKEA showroom, testing sofas with genuine appreciation and examining a flat-pack instruction leaflet with deep concentration. They select a shelving unit, open the box on the showroom floor, and assemble it correctly and efficiently without ever looking at the instructions again. They stand back and regard it. Then they abandon it entirely and go and eat the meatballs.
09 · 4 examples · full report
CCTV, drone, bodycam and broadcast footage
Name the format and FLUX.3 takes that format's frame shape, runtime and grain. You can override the content inside it, but not the pace of the cutting.
- On auto, the format picks the frame shape (VHS, noir and CCTV come back 4:3), but auto can vary between takes. If the shape matters, set the aspect ratio or name the frame ("anamorphic widescreen").
- Contradict the setting, subject or lighting freely ("a submarine documentary staged as a picnic"); those instructions win.
- If you need a different cutting speed than the format implies, cut it yourself in the edit.
A format plus a contradiction, and it didn't choose: daisies and a checked blanket inside the sonar compartment, tea cups lit by the green scope.
33 · 10s · auto · draft · 92 chars · report
It re-skinned its own esports overlay for a Victorian parlour: "VICTORIAN CHESS OPEN / ROUND 3", nameplates, LIVE badge, chat rail.
34 · 10s · auto · draft · 92 chars · report
An esports livestream with overlay: a chess match — but set in a candlelit Victorian parlor.
Drone footage "filmed in a small bathroom": a hiker walking past a bathtub, shot from a gliding aerial camera. The location went; the camera stayed.
35 · 10s · auto · draft · 82 chars · report
Drone footage: a coastal cliff walk — but filmed entirely inside a small bathroom.
Asked for a hard cut every second, delivered zero. The format word owned the edit outright.
36 · 10s · auto · draft · 108 chars · report
Slow cinema, one static long take: an old man drinking tea by a window — but a hard cut every single second.
10 · 6 examples · full report
Title cards, captions and on-screen text
Write the exact string in quotes. 132 of 145 requested strings came back exactly — but anything that has to count, tick or total goes wrong.
- Grids are its strength: a six-row departure board is safer than two labels floating on a map.
- Give a start string and an end string rather than a rule ("the score goes up by one").
- "Captions, upper third" gets you the model's words. caption: BIGGEST BAG ALL SEASON gets you yours.
- Spell-check proper nouns, and keep strings short enough to sit inside their box.
35 fields, every one exact, and only the two the prompt allowed to change actually changed.
37 · 10s · 21:9 · draft · 902 chars · report
An airport departure board, 12 seconds, with exactly specified typography. BOARD — Fills the frame, shot slightly off-axis. Matte black #0C0C0C panel, split-flap style. Column headers in amber #FFB300, Univers Bold, all caps: TIME, DESTINATION, FLIGHT, GATE, STATUS. ROWS — Six rows in the same amber, monospaced, evenly spaced: 06:40 LISBON TP1373 A12 BOARDING 07:05 OSLO SK4821 B03 ON TIME 07:20 CASABLANCA AT811 A07 DELAYED 07:45 TBILISI GE202 C11 ON TIME 08:10 REYKJAVIK FI455 B18 GATE CLOSING 08:30 ALGIERS AH2041 — DELAYED ACTION — At 6 seconds the OSLO row's STATUS field begins to flip, the split-flaps clattering through intermediate characters before settling on "BOARDING". Two seconds later its GATE field flips from B03 to B09. Travellers pass in soft foreground silhouette. Every flight code and destination must be legible and correctly spelled, and only the specified fields may change.
End credits: 16 roles and names correct through a live scroll, accents intact.
38 · 10s · 21:9 · draft · 958 chars · report
A film's end credits, 12 seconds, with exactly specified typography. BACKGROUND — Pure black #000000, full frame. CREDITS — Two columns, centred as a block occupying 62% of frame width. Left column right-aligned, in Trajan Pro, #C9C9C9, all caps, listing roles: DIRECTED BY, PRODUCED BY, WRITTEN BY, DIRECTOR OF PHOTOGRAPHY, EDITED BY, PRODUCTION DESIGNER, COSTUME DESIGNER, MUSIC BY. Right column left-aligned, same face, #FFFFFF, slightly larger, listing names: NOOR HADDAD, PILAR ESTEVEZ, TOMASZ REY, ADAEZE NWOSU, MARGIT HALVORSEN, JUN-HO PARK, CLARA BENÍTEZ, SAMSON ADEYEMI. MOVEMENT — The block scrolls upward at a steady readable pace, roughly one row leaving frame per 1.4 seconds. No easing, no stutter, perfectly linear. AUDIO — A single sustained orchestral chord under it, decaying. The two columns must stay in strict horizontal alignment row for row, the gutter must not drift, and every name must be correctly spelled with its accents intact.
Tale of the tape: 17 strings including 6'1", 74" and 28-4-1, rock-steady from build to hold.
39 · 10s · 21:9 · draft · 1,018 chars · report
A boxing broadcast tale-of-the-tape graphic, 12 seconds. GRAPHIC — Full-frame graphic over a darkened arena plate. Split vertically down the centre by a 2-pixel #D4AF37 rule. Left half tinted #7B1113 at 55% opacity, right half #10316B at 55% opacity. LEFT — "RUBEN 'THE CLOCK' MARTELL" in Impact, all caps, #FFFFFF, upper third. Beneath, five stat rows in Helvetica Bold white, right-aligned toward the centre rule: AGE 29, HEIGHT 6'1", REACH 74", WEIGHT 168 LB, RECORD 24-2. RIGHT — "IDRIS KANE" in the same treatment, left-aligned from the rule: AGE 33, HEIGHT 5'11", REACH 71", WEIGHT 167 LB, RECORD 28-4-1. CENTRE — Stat labels running down the rule in #D4AF37 Helvetica Bold small caps: AGE, HEIGHT, REACH, WEIGHT, RECORD. ACTION — The graphic builds: rule draws top to bottom, then both halves wipe in from their outer edges, then the stat rows fade up in sequence from top to bottom over four seconds. Announcer voice over arena ambience. All figures must be legible and the two columns must align row for row.
Burned-in subtitles: four full sentences with correct punctuation, timed to the dialogue, never over a face.
40 · 10s · 21:9 · draft · 987 chars · report
A foreign-language scene with burned-in subtitles, 12 seconds. SCENE — Two women argue quietly across a kitchen table, in Portuguese, keeping their voices down because someone is asleep in the next room. SUBTITLES — Centred, bottom, sitting at 11% frame height above the lower edge. Arial Bold, #FFFFFF, with a 3-pixel #000000 outline and no background box, maximum two lines, never more than 42 characters per line. Line breaks fall at natural clause boundaries. TIMING — Four subtitle events across the twelve seconds, each appearing on the speaker's first syllable and clearing within 4 frames of their last: "You told her before you told me." "I was going to tell you tonight." "You were going to tell me tonight." "Don't repeat what I say back to me." The subtitles must be correctly spelled, correctly punctuated, never overlap each other, never sit over a face, and must change exactly on the dialogue rather than drifting early or late. Natural kitchen light, handheld, no music.
Five UTC timestamps, all correct to the minute, and one title plate that rendered completely empty.
41 · 20s · 21:9 · draft · 123 chars · report
An archival mini-documentary about the Apollo 11 landing, with period footage and dated title cards marking each milestone.
Perfectly legible and wrong four different ways: 175 ft, then 120 ft, then 200 ft, then 852 ft.
42 · 20s · 21:9 · draft · 135 chars · report
An archival mini-documentary about the Wright brothers' first flight, with period footage and dated title cards marking each milestone.
11 · 5 examples · full report
Multilingual scenes and non-English dialogue
Label each speaker with their language and write their line in that language's script. Five languages in one room held together.
- Coverage improves with more speakers — the model answers more speakers by cutting to more of them.
- Handwriting and signs inside the frame often come back mirrored. Put anything that must be read in an overlay.
German, Turkish, Arabic, Russian and English, each speaker labelled. The take cuts to a pen going down on the page: the shot the script was aiming at.
43 · 15s · 21:9 · draft · 909 chars · report
A Berlin primary school parents' evening. One teacher, a small table, five sets of parents. TEACHER (German): "Ihre Tochter liest sehr gut. Wirklich sehr gut." TURKISH FATHER: "Çok teşekkür ederim. Evde de okuyor." ARABIC-SPEAKING MOTHER: "هل يحتاج إلى مساعدة في الرياضيات؟" TEACHER: "Ein bisschen. Nicht viel." RUSSIAN MOTHER: "А по-немецки он говорит хорошо?" TEACHER: "Sehr gut. Besser als er denkt." The last father sits down. He does not ask about reading, or maths, or German. FATHER (English): "Is she happy here?" The teacher stops. She puts down her pen. It is nearly nine o'clock and this is the first time all evening anyone has asked. TEACHER: "…Ja. Sie ist glücklich." FATHER: "Good. That's all I wanted." He stands and shakes her hand. She stays sitting for a moment after he has gone. Small chairs, children's paintings, evening light. The story: one parent asks the only question that matters.
Greek, English, Albanian and Russian through one window, and the scripted ending delivered whole.
44 · 15s · 21:9 · draft · 887 chars · report
A ferry ticket office at Piraeus in the morning rush. A queue, a clerk behind glass, a delay. CLERK (Greek, to a colleague): "Το οκτώ έχει καθυστέρηση." TOURIST (English): "Is the eight o'clock delayed?" CLERK: "Forty minutes. Sorry." ALBANIAN TRAVELLER: "Kur niset anija tjetër?" CLERK: "Në dhjetë." RUSSIAN TRAVELLER: "Один билет, пожалуйста." CLERK: "Двенадцать евро." At the back, an elderly woman has been standing very still for some time, holding a ticket. The clerk notices the ticket's colour. CLERK (Greek, standing up): "Κυρία μου — αυτό ήταν χθες." OLD WOMAN: "Ναι." CLERK: "Χθες το ακύρωσαν. Δεν σας το είπε κανείς;" OLD WOMAN: "Όχι." The clerk closes her window, comes out from behind the glass, and takes the woman's bag. The queue watches and nobody complains. Scuffed counter, harbour light. The story: someone has been waiting a whole day for a boat that was cancelled.
Code-switching: Cantonese lyrics with a working karaoke highlight, English underneath, both scripts on screen and both spelled right.
45 · 15s · 21:9 · draft · 177 chars · report
A karaoke duet: she sings the Cantonese verse of a 90s ballad, he answers with an English verse, both sets of lyrics highlighting on the screen behind them in their own scripts.
Good coverage and real staging, but the opening insert is a notebook written in mirror image.
46 · 15s · 21:9 · draft · 682 chars · report
A university library in Sydney, close to midnight. Three postgrads at one table. A (Korean, muttering at her own page): "이거 왜 이렇게 안 풀리지…" B and C exchange a very brief look and say nothing. She works. Two full seconds of nothing but pen on paper. Then her hand stops. A: "…아. 부호." She fixes one sign and the whole thing collapses into place. A (English, suspicious): "How long have you two had this?" B (English): "Had what?" C (Mandarin, not looking up): "我们什么都没说。" A: "You've had it for an hour." B: "Forty minutes." A: "…진짜 너무하네." She is laughing. C pushes a coffee across to her without comment. Desk lamps, laptops, empty cups. The story: two friends let her get there herself.
The one that flattens: one wide, six men where the script wrote five, and the beat that carries the scene never happens.
47 · 15s · 21:9 · draft · 927 chars · report
A construction site canteen in Dubai at the end of a shift. Five men at one long table, arguing about a goal. A (English): "The second goal was offside. It was clearly offside." B (Hindi): "अरे नहीं यार, वो गोल कमाल का था।" C (Bengali): "গোলটা ভালো ছিল, কিন্তু গোলকিপারের দোষ।" D (Nepali): "गोलकिपरको गल्ती होइन! डिफेन्सको हो!" E (Tagalog): "Depensa talaga. Palagi na lang depensa." They are shouting over each other and enjoying it enormously. Then B checks the time and stands up, and the table goes quiet. A: "What time's your flight?" B (Hindi, picking up his tray): "चार बजे।" Three years. Nobody says it. Instead: C (Bengali, loudly, sitting back): "যাই হোক — গোলকিপারের দোষ।" D: "होइन भन्या!" And the argument starts again, louder than before, and B sits back down with his tray. Plastic trays, strip lighting, a small wall-mounted TV. The story: they keep arguing because it is the only way any of them can say goodbye.
12 · 6 examples · full report
Writing the prompt in another language
The prompt's language is a casting and location decision. Change it and FLUX.3 recasts the actors, rebuilds the street and rewrites the signs — but only where the scene has a street.
- Offices, buses and karaoke rooms came back identical in all seven languages. Streets and homes did not.
- English is not the neutral option: the English street-food take landed in East Asia.
- If you want a specific place, name it; don't rely on the language to pick one.
The prompt names the tent. It did not name the Korean signage on every shop, the utility poles or the blue stools.
48 · 10s · 21:9 · draft · 57 chars · report
"Un puesto de comida callejera", a generic phrase, and the model built a Latin American street market around it.
49 · 10s · 21:9 · draft · 120 chars · report
Un puesto de comida callejera en plena hora punta: vapor, pedidos a gritos y clientes habituales que no necesitan pedir.
Shoes by the door, a shoe rack, fusuma panels. The prompt only said "small apartment."
50 · 10s · 21:9 · draft · 68 chars · report
平日の朝、小さなアパートで家族の朝食。誰かが遅刻しそうでトーストをつかんで飛び出し、ドアがバタンと閉まる。母はため息をついてお茶を飲む。
Haussmann stone, iron balconies and a French-format plate on the truck, from one sentence about a box that won't fit.
51 · 10s · 21:9 · draft · 109 chars · report
Jour de déménagement : le dernier carton ne rentre pas dans le camion, et tout le monde a son avis là-dessus.
Cantonese, fully directed: the same barbershop as the other six, plus a Hong Kong street outside and a vertical Chinese sign on the glass.
52 · 10s · 21:9 · draft · 223 chars · report
理髮師退休前最後一鋪,十秒,完整導演指示。 動作 —— 一個老師傅剪完最後一個頭。掃返個頸,一嘢抖開條圍布,攞住面手鏡照返個客後尾枕。個客點頭。老師傅掃地,轉個牌變「休息」,然後企喺自己間空舖中間,手仲揃住條掃把。 鏡頭同光 —— 50mm,固定,由等位嗰邊影過去。鏡面頂嗰條燈管暖黃色,後面窗口透入嘅日光係冷色。 聲 —— 較剪聲,抖圍布嗰下,頭髮跌落地磚,掃把聲,門口個鈴,然後乜都冇。 氣氛 —— 唔煙情。佢冇留低慢慢惏。就係咹所以先入心。
The English street-food take lands in East Asia. Whatever you think English defaults to, check it.
53 · 10s · 21:9 · draft · 115 chars · report
A street food stall at evening rush hour: steam, shouted orders, and regulars who don't need to say what they want.
13 · 3 examples · full report
Vertical social clips (9:16)
Write it as a phone clip with timed beats, and supply the caption text word for word. Vertical follows the same rules as widescreen.
- Describe the phone, not just the scene: one-handed, spray on the lens, horizon swinging.
- Ask for captions without text and the model invents its own. Supply the words and they burn in verbatim.
- Naming a phone-era format can pick 9:16 for you on auto, but set the aspect ratio when you need it.
Two-second timed beats from the deckhand's phone. The caption "BIGGEST BAG ALL SEASON" is supplied, so it renders verbatim.
54 · 10s · 9:16 · draft · 2,800 chars · report
0:00–0:02 — A young deckhand's phone clip opens on a heaving trawler deck at dawn. He films one-handed, other arm hooked through the rigging. The winch starts and the cable snaps taut out of frame. Spray hits the lens and leaves running droplets. The camera lurches with the boat; the horizon swings past vertical. His hood fills half the frame, orange and streaming. Deck lights flare white streaks across the wet lens. 0:02–0:04 — The net breaks the surface below and the crew roar goes up. He leans the phone over the rail to catch the boiling water. A swell shoulders the boat and the frame drops half a metre. Green water sweeps the deck across the bottom of the shot. He whoops, and the wind rips the sound to pieces. The winch screams somewhere above the frame. Gulls flash through the top of the vertical frame. 0:04–0:06 — The cod end swings inboard overhead, huge and streaming. He tilts the phone straight up to fit it in the vertical frame. It blots out the deck lights and rains on the lens. The mesh bulges silver with the weight of the catch. Someone yells to stand clear and he backs up fast, still filming. The frame clips the skipper watching from the wheelhouse door. A caption lands: BIGGEST BAG ALL SEASON. 0:06–0:08 — The catch releases and fish flood the deck pound in a silver wave. The phone nearly goes down with him as his boots skate. He catches the rail, laughing, camera swinging past his knees. Fish slap around his ankles across the bottom of the frame. The crew wade in with gloves already moving. A caption stutters on: I'M FINE LOL. The eldest deckhand deadpans straight into the lens. 0:08–0:10 — He flips the camera to selfie, soaked and grinning ear to ear. Behind him the crew cheer and hold up two fish like trophies. The dawn splits grey-gold along the horizon over his shoulder. He shouts: season's done, we're going home. The skipper leans out of the wheelhouse and finally smiles. Spray beads roll down the lens through the whole shot. A caption settles: 127 DAYS. DONE. STYLE — Vertical 9:16 phone footage, handheld, ultra-wide GoPro feel. Water droplets and smears live on the lens the whole clip. Auto-exposure hunts between deck lights and the dark sea. Bold white captions with a slight drop shadow, upper third. Digital stabilisation warps the edges on the big hits. Colours raw and cold; oilskin orange burns against the grey. Occasional dropped frames when spray smacks the camera. SOUND — Wind hammers the phone mic into crackle on every gust. The winch and diesel grind underneath everything. His whoops distort, clipped by the tiny mic. The catch lands as a roaring drum of fish on aluminium. Crew voices come through in salty half-heard fragments. Gulls shriek somewhere above the frame. A muffled thump and laughter when he nearly goes down.
"A 2004 flip-phone video" came back vertical on auto, because that's how you hold a flip phone. Nobody asked.
55 · 15s · auto · draft · 44 chars · report
A 2004 flip-phone video of a football match.
IMAX "framed like a shaky vertical phone video": the only vertical file in its family, but still an IMAX-clean aerial no phone could have taken.
56 · 10s · auto · draft · 100 chars · report
IMAX aerial cinematography: a mountain range at dawn — but framed like a shaky vertical phone video.
14 · 6 examples · full report
Cause and effect: chains, machines and physics
List the steps in order and FLUX.3 follows them: a seven-step breakfast machine holds to the plate. Keep quantities out of it — ten coins land as thirteen.
- Write the chain as a comma-separated sequence of verbs, each step causing the next.
- End on a resting state ("the plate slides to a stop") so the take has somewhere to finish.
- Never rely on counts. If the number matters, show it in an overlay.
Every beat in order: toast launches at 5.78s, the kettle tips at 8.54s, the plate arrives at the chair at 19.59s.
57 · 20s · 21:9 · draft · 184 chars · report
Six steps from door slam to pigeons: the orange takes the ramp, tips the scale pan, seed pours at 10.49s.
58 · 15s · 21:9 · draft · 138 chars · report
A door slam shakes a shelf; an orange rolls off, down a ramp, across the floor, into a scale pan that tips and pours seed; pigeons arrive.
A spoon, inverted correctly: concave optics done right.
59 · 5s · 21:9 · draft · 67 chars · report
A spoon reflects the diner upside down, correctly, as it is raised.
Three of four steps perfect, then the marble vanishes between 9.1s and 9.4s.
60 · 10s · 21:9 · draft · 76 chars · report
A ball topples dominoes that trip a lever that drops a marble into a teacup.
Ten coins knocked off a stack. Thirteen on the table, counted on the final frame.
61 · 20s · 21:9 · draft · 72 chars · report
A pizza's eight slices taken one by one until the tray is exactly empty.
The canal reflects the bike, not the rider.
62 · 5s · 21:9 · draft · 80 chars · report
A canal mirrors a cyclist riding along it; both cross a bridge's shadow at once.
15 · 6 examples · full report
Keyframes: first frame, last frame and timed pins
Use four or five pins, not ten, and put what you cannot lose on the first and last frame. Four pins landed 70% of the time; ten landed 39%.
- First and last pins come back almost exactly. Interior pins are suggestions.
- Space pins evenly. Front-loading a burst then long gaps is the one uneven schedule that worked.
- Below about a second between pins you get cuts; above it, dissolves — whatever the prose says.
- Two pins can beat ten when the endpoints differ (dawn to fog). The same picture at both ends produces a twenty-second still.
Two pins and a locked frame invent a whole day of traffic, weather and neon — better than the ten-pin version of the same corner.
63 · 20s · 21:9 · draft · 574 chars · report
2 frames pinned before generating
010:00
020:20
Twenty-four hours on one locked-off city corner as a single time-lapse — the minimum case: only the first frame (4:45 AM blue dark) and the last (4:00 AM fog) are pinned, twenty seconds apart. The model must invent the ENTIRE day between two nearly-identical night frames: dawn, rush hour, noon, storm, downpour, golden hour, neon dusk, deep night — and return to stillness. The camera NEVER moves; fixed elements pixel-locked. 35mm film look: grain, halation, crushed blacks. SOUND — a whole invented day: birds, traffic, thunder, rain, chatter, then wind and fog silence.
Ten pins, front-loaded: six worlds in five seconds then four long dissolves. Nine of ten pins on screen at their second.
64 · 20s · 21:9 · draft · 532 chars · report
10 frames pinned before generating
010:00
020:01
030:02
040:03
050:04
060:05
070:10
080:15
090:18
100:20
A match-cut chain with warped rhythm: the first six worlds — eye, eclipse, coffee, vinyl, clock, manhole — strobe past in the first five seconds, a cut a beat; then the chain decompresses, and moon, ferris wheel, porthole and galaxy get long luxurious dissolves across fifteen seconds. Fast cutting then slow morphing in one film — the contrast is the experiment. Circle dead-center, constant scale, always. 35mm film look: grain, halation, crushed blacks. SOUND — rapid percussive world-flashes that open into long oceanic drones.
Ten even pins, clay to dust: eight of ten states within a second, but it skipped the crack and went straight to shatter.
65 · 20s · 21:9 · draft · 844 chars · report
10 frames pinned before generating
010:00
020:02
030:04
040:06
050:08
060:11
070:13
080:15
090:17
100:20
One object lives and dies on a potter's wheel in a single meditative shot. A wet lump of grey clay is slapped down, centered under wet hands, opened and pulled into a rising cylinder, refined into an elegant vase, dried leather-hard and trimmed, painted with a cobalt wave, reborn glossy from the kiln, cracked by a hairline flaw, shattered mid-air, and settled into a quiet cone of dust — while the camera drifts slowly clockwise around the wheel the whole time, the studio and its window light unchanged and indifferent. Each state must grow physically out of the last — continuous transformation, not cuts; hands appear and vanish naturally. 35mm film look: grain, halation, crushed warm blacks. SOUND — the wheel's whir, wet clay under palms, brush strokes, kiln tick, a crack like ice, one sharp shatter, then settling dust and room tone.
Two pins, pupil to galaxy: one unbroken zoom, no worlds in between, and it reached the galaxy four seconds early.
66 · 20s · 21:9 · draft · 471 chars · report
2 frames pinned before generating
010:00
020:20
The minimum match cut: a human eye at frame one, a spiral galaxy at frame 480, twenty seconds apart — pupil to galactic core. The model owns the entire journey between the most intimate circle and the largest; it may pass through any circular worlds it invents, but the circle must stay dead-center at constant scale from first frame to last. 35mm film look: grain, halation, crushed blacks. SOUND — a single slow crescendo from a heartbeat to the roar-silence of space.
Four pins inside one second broke the film: the heist finishes at 15.8s and the last four seconds are an empty room.
67 · 20s · 21:9 · draft · 807 chars · report
10 frames pinned before generating
010:00
020:04
030:08
040:10
050:10
060:11
070:11
080:16
090:19
100:20
A one-room jewel heist where the EDIT is the rhythm — pins placed at their authored timecodes: slow creep for ten patient seconds (door, laser tightrope, kneel at the case, the cut, the lift), then a half-second cluster of violence — GRAB, ALARM, FLATTEN — inside a red strobing detonation, then five unbearable frozen seconds of standoff, then the sprint and the empty room. Pacing must follow the pin timing exactly: languid, explosive, held, released. One continuous shot, no cuts. 35mm anamorphic thriller look: grain, halation, crushed blacks, red strobe. SOUND — near silence with breath and cloth, one glass squeak, the sapphire's tap — then a piercing klaxon and strobing hum, held tense through the standoff, then running footsteps swallowed by the vault door and the alarm alone in an empty room.
The same picture pinned at both ends: a twenty-second still. Nothing moves at all.
68 · 20s · 21:9 · draft · 494 chars · report
2 frames pinned before generating
010:00
020:20
The purest loop test: the SAME image pinned at frame 0 and frame 480 — a sleeping cat on a sunlit windowsill — and twenty unpinned seconds between. Does the model keep the cat asleep, breathing gently in the sun? Does it invent a journey and return? Anything is allowed except a visible seam: the clip must land back exactly where it began. Camera locked, room untouched. 35mm film look, warm grain, dust motes drifting. SOUND — room tone, purring, distant street — identical at head and tail.
16 · 6 examples · full report
Rerolls: what changes between takes
Same prompt, four takes: FLUX.3 keeps the place, the light and the look, and rerolls the face, the lens and whether the action finishes.
- Reroll for a face you don't like, a lens that sat too close, or an action that didn't finish.
- Rewrite for the location, time of day, grade or casting type — four takes give you the same bar and the same lawn.
- Whatever you leave unsaid gets recast every time. Name it or it's a dice roll.
- A mid-length prompt plus a reroll is cheaper than a longer prompt.
A paragraph, first take: opens it, pours out, jar on its side by 7s. The paragraph beat the full brief.
69 · 8s · 21:9 · draft · 444 chars · report
An octopus opens a screw-top jar from the inside. A common octopus is sealed inside a glass jar on a sandy tank floor. It spreads its arms flat against the inner wall, finds the lid, and works it around a quarter-turn at a time until the seal breaks and it pours itself out. Aquarium light from above, blue-green water, fine particulate drifting. Macro lens on the suckers. Audio: muffled underwater room tone, the dull squeak of glass turning.
Full brief, third take: trampoline, hose, worn patches, backlit low sun. Every prop, fourth try as first.
70 · 10s · 21:9 · draft · 1,588 chars · report
A dog runs through a garden sprinkler on a hot afternoon, in one continuous 8-second take. ACTION — An oscillating sprinkler sweeps left to right across a suburban back lawn. A golden retriever, already soaked, charges into the arc at full speed, jaws snapping at the water and missing. It overruns, skids on the wet grass with all four legs sliding, wheels around in a spray of water and torn turf, and comes straight back through the arc the other way — this time catching a mouthful and shaking its head violently as it emerges. Water sheets off its coat with every stride. SUBJECT — A young golden retriever, coat darkened and spiked with water, absolutely committed, mouth open, ears flying. Not a trained performance — a genuinely overstimulated dog. SETTING — An ordinary back garden: mown grass with two worn patches, a wooden fence, a trampoline in the far corner, a hose snaking back to a tap. Nobody else in frame. CAMERA & LIGHT — 35mm at grass height, camera low enough that the dog crosses above the lens, tracking laterally to hold it in frame. Hard low sun from behind the sprinkler so every droplet is backlit and the spray reads as a wall of white light; the dog is largely in silhouette on the way in and fully lit on the way back. SOUND — The sprinkler's mechanical tick and the rising hiss of each sweep, paws slapping wet grass, the heavy shake of a wet coat, one short bark, and the constant background of a summer afternoon. GRADE — Saturated summer green, hot white specular highlights on every water droplet, slight lens flare from the low sun, fine grain.
One line, third take: identical prompt to the takes either side, and this time the reporter is a man.
71 · 8s · 21:9 · draft · 56 chars · report
A 1987 local news report about a runaway parade balloon.
The most directed prompt in the test, and the lid is still on at the last frame.
72 · 8s · 21:9 · draft · 1,670 chars · report
An octopus opens a screw-top jar from the inside, 8 seconds, in close observational detail. ACTION — A common octopus is sealed inside a large glass jar resting on a sandy tank floor. It begins pressed into the bottom third, then unfurls: arms spreading flat against the curved inner wall, suckers sequentially adhering with visible individual grip. Two arms locate the lid and take purchase around its inner rim. It applies torque — the whole animal counter-rotates slightly against the glass as it works — and the lid moves a quarter turn, stops, and moves again. On the third effort the seal breaks with a visible pulse of bubbles, and the octopus immediately pours itself through the gap, changing colour from mottled red-brown to pale as it exits. SUBJECT — Every sucker acts independently and visibly. The skin texture changes continuously — papillae rising and flattening — and the animal's colour shifts twice during the sequence. SETTING — A research aquarium tank: fine pale sand, one piece of coral rubble, a bare glass back wall. CAMERA & LIGHT — 100mm macro, locked off, focused on the lid and the arms working it, with the body soft behind the curved glass. Overhead aquarium light only, so the sand is bright and the water column above goes to deep blue-green. Refraction through the jar visibly distorts everything behind it. SOUND — Muffled underwater room tone with a low filtration hum, the dull granular squeak of glass turning against glass, a soft rush of bubbles at the moment the seal breaks. GRADE — Cool blue-green water against warm sand, high clarity, fine particulate catching the light, slight chromatic aberration at the jar's edges.
The lower third reads "[REPORTER NAME]". It rendered the placeholder.
73 · 10s · 21:9 · draft · 1,687 chars · report
A 1987 local news report about a runaway parade balloon, 8 seconds, in the exact grammar of a period news package. ACTION — A field reporter stands mid-frame in a wind-blown high street holding a stick microphone with a station flag on it, delivering a piece to camera. Behind her, an enormous inflatable cartoon character — three storeys tall, straining sideways — is dragging eight handlers bodily down the road, their ropes at forty-five degrees. One handler lets go and sits down hard. The reporter's hair is being flattened across her face by the same wind. She glances over her shoulder at exactly the moment the balloon's head strikes a lamp standard, turns back to camera, and carries on without breaking sentence. SUBJECT — Late thirties, shoulder-padded red blazer, big hair losing its battle with the wind, holding the mic exactly the regulation distance from her chin. Utterly professional; the only tell is that she raises her voice a notch after the glance. SETTING — A provincial high street, period shopfronts, bunting, a crowd pressed to both kerbs, police in period uniform waving people back. FORMAT & CAMERA — Shot on a 1987 broadcast tube camera: soft image, smeared reds, highlights blooming and trailing, slight geometric distortion at the frame edges. Locked-off shoulder-height framing that reframes once, late and clumsily, to keep the balloon in shot. A period lower-third name strap fades in and out. SOUND — Heavy wind buffet directly on the microphone capsule, crowd noise, distant marching band, the reporter's level trained delivery riding above it all. GRADE — Washed-out video colour, low contrast, slightly green in the greys, visible tape noise.
Framed almost to the pixel like the other takes, with three olives instead of two.
74 · 20s · 21:9 · draft · 561 chars · report
A bartender builds a martini behind a dark wood bar at night. He fills a mixing glass with cracked ice, pours gin and a short measure of vermouth, and stirs for a slow ten seconds with a bar spoon, never letting the spoon rattle. He strains into a chilled coupe held at an angle, drops in two olives on a steel pick, and slides it forward without looking up. Warm low key light from a single pendant above the bar, bottles glittering out of focus behind him. Handheld medium close on his hands. Audio: ice ringing on glass, the strain, the pick against the rim.
Draft first, then render up
Rough every take in Draft: 0.5 olives a second against 2.6 for a full 1080p render. Once the action and timing are right, Draft Enhance renders that same take at 1080p instead of rolling a new one. The render tag under each example shows how it was made. Per-second prices are on the model page.
FLUX.3 prompting FAQ
How long should a FLUX.3 video prompt be?
About 1,400 characters — roughly three sentences each on action, setting, subject, dialogue, camera, sound and grade. FLUX.3 reads every word out to 4,700 characters, but across 129 takes the film stopped getting better at about 1,400, and past 2,400 the extra writing only added texture and more cuts.
What is the best prompt format for FLUX.3?
Format barely matters. We wrote the same five scenes ten ways and eight of the ten styles were interchangeable. What matters is that the prompt still names who, where and what happens. A plain paragraph is fastest; labelled fields (SUBJECT / SETTING / ACTION / CAMERA / AUDIO) make it impossible to forget the subject.
Can FLUX.3 render text on screen?
Yes. 132 of 145 requested strings rendered exactly when the prompt spelled them out in quotes. It fails on anything that has to count — clocks, scores and totals — so give a start string and an end string instead of a rule.
How many keyframes should I use with FLUX.3?
Four or five. Four pins landed 70% of the time and ten landed 39%. The first and last frames come back almost exactly; interior pins are treated as suggestions.
How do I get multiple shots in one FLUX.3 generation?
Write a numbered shot list with timecodes (SHOT 1 (0:00–0:05)…). 27 of 32 twenty-second briefs written that way came back with the four shots they asked for. To force one continuous take, use timecode blocks without shot labels.
Does rerolling a FLUX.3 prompt change the location?
No. A reroll changes the face, the lens and often whether the action finishes. It keeps the location, the light and the look. If the location or light is wrong, rewrite the prompt instead of rerolling.
Can FLUX.3 sync cuts to music?
No — cuts landed no closer to the beat than chance. Sound events do drive action (an off-screen noise reliably arrives just before the reaction), and a light or colour change on a musical event lands to the frame.
Open every take on the canvas
All 971 takes and their prompts, on one Martini canvas. No sign-in.