Générateur vidéo IA Seedance 2.0
Créez des vidéos avec Seedance 2.0 sur flux3 video. Choisissez une entrée prise en charge, examinez les paramètres disponibles et vérifiez le devis de crédits avant de générer.
Créer des vidéosInvite vérifiée
TITLE: Premium Commercial Storyboard Presentation FORMAT: • Single-page premium storyboard • 3:4 Portrait ratio • Luxury advertising agency presentation board • Client-ready storyboard layout • 8 storyboard frames • Editorial Swiss grid system • High-end presentation quality • Print-ready infographic HEADER: • Large elegant serif title • Premium minimalist information bar • Information cards: - Duration - Style - Audience - Audio Suggestion • Rounded "Why This Style Works" section • Gold decorative doodles, stars, sparkles, hearts • Soft cream luxury background • Thin beige border • Clean editorial spacing STORYBOARD LAYOUT: • 8 equal storyboard panels • 2 rows × 4 columns • Rounded white cards • Soft realistic shadows • Perfect alignment • Equal margins • Professional grid layout • Large cinematic image in upper section • Information block below image EVERY STORYBOARD PANEL INCLUDES: • Scene number inside white outlined circle • Duration badge in top-right corner • Large commercial-quality photograph • Sections: - Visual - Action - Dialogue • Bold section titles • Perfect typography hierarchy • Consistent spacing • Premium card design PHOTOGRAPHY STYLE: • Ultra realistic commercial photography • Cinematic product shots • Natural daylight • Soft warm lighting • Luxury advertising look • Shallow depth of field • Smooth background bokeh • High-end product styling • Professional color grading • DSLR quality • Premium lifestyle photography GRAPHIC STYLE: • Apple keynote presentation aesthetic • Behance showcase quality • Modern editorial magazine design • Premium infographic • Clean UI composition • Luxury branding • Elegant typography • Minimalist design language • Print-quality layout FOOTER: • Total Duration • Format • Visual Style • Minimal line icons • Premium editorial finish QUALITY: Ultra detailed, 8K, razor sharp, perfectly aligned, symmetrical composition, luxury commercial presentation, agency-quality storyboard, realistic textures, flawless typography, premium client presentation.
TITLE: Premium Commercial Storyboard Presentation FORMAT: • Single-page premium storyboard • 3:4 Portrait ratio • Luxury advertising agency presentation board • Client-ready storyboard layout • 8 storyboard frames • Editorial Swiss grid system • High-end presentation quality • Print-ready infographic HEADER: • Large elegant serif title • Premium minimalist information bar • Information cards: - Duration - Style - Audience - Audio Suggestion • Rounded "Why This Style Works" section • Gold decorative doodles, stars, sparkles, hearts • Soft cream luxury background • Thin beige border • Clean editorial spacing STORYBOARD LAYOUT: • 8 equal storyboard panels • 2 rows × 4 columns • Rounded white cards • Soft realistic shadows • Perfect alignment • Equal margins • Professional grid layout • Large cinematic image in upper section • Information block below image EVERY STORYBOARD PANEL INCLUDES: • Scene number inside white outlined circle • Duration badge in top-right corner • Large commercial-quality photograph • Sections: - Visual - Action - Dialogue • Bold section titles • Perfect typography hierarchy • Consistent spacing • Premium card design PHOTOGRAPHY STYLE: • Ultra realistic commercial photography • Cinematic product shots • Natural daylight • Soft warm lighting • Luxury advertising look • Shallow depth of field • Smooth background bokeh • High-end product styling • Professional color grading • DSLR quality • Premium lifestyle photography GRAPHIC STYLE: • Apple keynote presentation aesthetic • Behance showcase quality • Modern editorial magazine design • Premium infographic • Clean UI composition • Luxury branding • Elegant typography • Minimalist design language • Print-quality layout FOOTER: • Total Duration • Format • Visual Style • Minimal line icons • Premium editorial finish QUALITY: Ultra detailed, 8K, razor sharp, perfectly aligned, symmetrical composition, luxury commercial presentation, agency-quality storyboard, realistic textures, flawless typography, premium client presentation.
Invite vérifiée
High-octane, hyper-realistic military action sequence in the style of Christopher Nolan, shot on actual 70mm IMAX cameras in bright, harsh midday sun. Fast-paced multi-shot editing with quick, cinematic cuts timed at exactly one shot every 2 seconds across a complete 15-second timeline. A disciplined squad of Navy SEALs in weathered tactical gear moves through a dense, sun-drenched Mexican jungle. High-contrast Nolan-esque color grading with deep, dark shadows, cold teals, and intense, bright highlights. Blinding, realistic shafts of midday sunlight pierce the thick canopy, creating stark overexposed light patches on the jungle floor. Rapid sequence of intense, rapid-fire cuts: •Shot 1 (0-2s): Eye-level tracking shot of SEALs advancing past thick vines in bright daylight. •Shot 2 (2-4s): Tight, detailed close-up of an assault rifle muzzle flash momentarily overpowering the bright sunlight. •Shot 3 (4-6s): Low-angle handheld camera whip-panning as a hidden cartel operator fires from ancient stone ruins under a clear blue sky. •Shot 4 (6-8s): Ground-level macro shot of splintering tree bark and flying dirt clods exploding in stark, sharp sunlight. •Shot 5 (8-10s): Fast tracking shot behind a SEAL diving for cover through heavy white gun smoke illuminated by harsh day rays. •Shot 6 (10-12s): High-angle wide shot of the intense firefight, showing the chaotic layout of the jungle skirmish. •Shot 7 (12-14s): Shaky handheld tracking shot following a SEAL tossing a tactical smoke grenade into a clearing. •Shot 8 (14-15s): Sudden hard cut to black with a lingering, thick cloud of white smoke dispersing into the midday sunlight. Raw documentary-style camera textures, organic lens flares, lifelike physics, authentic daytime motion blur, and a visceral, gripping sense of real-world peril. Ultra-detailed, 4k resolution.
High-octane, hyper-realistic military action sequence in the style of Christopher Nolan, shot on actual 70mm IMAX cameras in bright, harsh midday sun. Fast-paced multi-shot editing with quick, cinematic cuts timed at exactly one shot every 2 seconds across a complete 15-second timeline. A disciplined squad of Navy SEALs in weathered tactical gear moves through a dense, sun-drenched Mexican jungle. High-contrast Nolan-esque color grading with deep, dark shadows, cold teals, and intense, bright highlights. Blinding, realistic shafts of midday sunlight pierce the thick canopy, creating stark overexposed light patches on the jungle floor. Rapid sequence of intense, rapid-fire cuts: •Shot 1 (0-2s): Eye-level tracking shot of SEALs advancing past thick vines in bright daylight. •Shot 2 (2-4s): Tight, detailed close-up of an assault rifle muzzle flash momentarily overpowering the bright sunlight. •Shot 3 (4-6s): Low-angle handheld camera whip-panning as a hidden cartel operator fires from ancient stone ruins under a clear blue sky. •Shot 4 (6-8s): Ground-level macro shot of splintering tree bark and flying dirt clods exploding in stark, sharp sunlight. •Shot 5 (8-10s): Fast tracking shot behind a SEAL diving for cover through heavy white gun smoke illuminated by harsh day rays. •Shot 6 (10-12s): High-angle wide shot of the intense firefight, showing the chaotic layout of the jungle skirmish. •Shot 7 (12-14s): Shaky handheld tracking shot following a SEAL tossing a tactical smoke grenade into a clearing. •Shot 8 (14-15s): Sudden hard cut to black with a lingering, thick cloud of white smoke dispersing into the midday sunlight. Raw documentary-style camera textures, organic lens flares, lifelike physics, authentic daytime motion blur, and a visceral, gripping sense of real-world peril. Ultra-detailed, 4k resolution.
Invite vérifiée
A cinematic first-person POV journey through Paris, featuring autumn leaves, cozy cafés, romantic moments, and ending hand-in-hand before the glowing Eiffel Tower at night, in the style of a Makoto Shinkai anime film, vibrant colors, warm lighting, cinematic composition, highly detailed, 8K, smooth animation.
A cinematic first-person POV journey through Paris, featuring autumn leaves, cozy cafés, romantic moments, and ending hand-in-hand before the glowing Eiffel Tower at night, in the style of a Makoto Shinkai anime film, vibrant colors, warm lighting, cinematic composition, highly detailed, 8K, smooth animation.
Invite vérifiée
15-second intense action sequence, handheld camera tracking sideways at high speed alongside a black horse galloping through a dense foggy forest at dawn, low angle, mud splashing on the lens, camera shakes slightly with each horse's hoofbeat, branches of trees whip past the frame, sun rays piercing through the mist creating god rays. cinematic color grading teal-orange, dynamic and gritty feel.
15-second intense action sequence, handheld camera tracking sideways at high speed alongside a black horse galloping through a dense foggy forest at dawn, low angle, mud splashing on the lens, camera shakes slightly with each horse's hoofbeat, branches of trees whip past the frame, sun rays piercing through the mist creating god rays. cinematic color grading teal-orange, dynamic and gritty feel.
Invite vérifiée
Concept: "Girls' Night Out" Create a hyper-realistic self-recorded vlog filmed entirely on a modern flagship smartphone using the front-facing camera. The entire video is captured by the vlogger herself in one continuous recording, making viewers feel like they're part of the night. The footage should feel spontaneous and unscripted with natural handheld movement, subtle smartphone stabilization, realistic autofocus adjustments, automatic HDR exposure changes, authentic low-light performance, occasional framing imperfections, and genuine ambient sound. No cinematic shots, transitions, jump cuts, or edited montages. Visual Style Modern smartphone video with crisp detail, realistic HDR, natural skin tones, balanced exposure, authentic night lighting, and accurate colours. Club lights, warm decorative lighting, and city lights should illuminate the scene naturally without excessive bloom or stylized effects. No beauty filters, film grain, or cinematic grading. Character NARI, a Korean female idol in her twenties with long softly curled black hair, glowing natural makeup, expressive eyes, and a fun, energetic personality. She wears a fashionable party outfit suitable for an upscale rooftop celebration: a stylish black mini dress with a cropped leather jacket, delicate jewelry, comfortable heels, and a small shoulder bag. Her outfit remains consistent throughout the vlog. Location A stylish rooftop party overlooking the city skyline at night. Warm string lights, lounge seating, live DJ, dance floor, mocktail bar, decorative plants, and groups of friends enjoying the evening. The atmosphere is lively, elegant, and realistic rather than crowded or chaotic. The recording begins inside the elevator as NARI smiles into the phone. "Tonight is all about relaxing with my friends... no rehearsals, no schedules." The elevator doors open to reveal the rooftop venue glowing with warm lights and music. She walks through the entrance, greeting friends with hugs and laughter before introducing a few of them to the camera with playful reactions. She grabs a colourful mocktail from the bar. "This one looks way too pretty not to film." As the music gets livelier, she joins her friends on the dance floor. Still holding the phone naturally, she records short moments of everyone dancing, laughing, spinning together, and singing along to the music. The camera occasionally turns outward to capture the city skyline, decorative lights, and the joyful atmosphere before returning to selfie view. Between songs she catches her breath, smiling at the camera. "I forgot how much I needed a night like this." Her friends pull her back onto the dance floor. She laughs, records a few more energetic moments, then walks toward the rooftop edge where the skyline fills the background. Looking into the camera with a relaxed smile, she says, "Sometimes the best memories are the ones you never plan." Her friends call her name from behind. She turns around laughing, waves to the camera, "Okay... they're stealing me back. See you next time!" She runs back toward her friends as everyone continues dancing together. The recording ends naturally as she lowers the phone while rejoining the celebration. Generation Requirements Produce one continuous realistic smartphone recording with a consistent facial identity, natural body movement, believable dancing, accurate hand interactions, realistic low-light smartphone exposure, stable clothing continuity, authentic crowd behaviour, smooth camera motion, and natural environmental audio. Avoid AI artifacts, duplicated people, warped anatomy, floating objects, jump cuts, or unrealistic movements. The final result should feel like a genuine personal party vlog filmed by a real K-pop idol on her own smartphone.
Concept: "Girls' Night Out" Create a hyper-realistic self-recorded vlog filmed entirely on a modern flagship smartphone using the front-facing camera. The entire video is captured by the vlogger herself in one continuous recording, making viewers feel like they're part of the night. The footage should feel spontaneous and unscripted with natural handheld movement, subtle smartphone stabilization, realistic autofocus adjustments, automatic HDR exposure changes, authentic low-light performance, occasional framing imperfections, and genuine ambient sound. No cinematic shots, transitions, jump cuts, or edited montages. Visual Style Modern smartphone video with crisp detail, realistic HDR, natural skin tones, balanced exposure, authentic night lighting, and accurate colours. Club lights, warm decorative lighting, and city lights should illuminate the scene naturally without excessive bloom or stylized effects. No beauty filters, film grain, or cinematic grading. Character NARI, a Korean female idol in her twenties with long softly curled black hair, glowing natural makeup, expressive eyes, and a fun, energetic personality. She wears a fashionable party outfit suitable for an upscale rooftop celebration: a stylish black mini dress with a cropped leather jacket, delicate jewelry, comfortable heels, and a small shoulder bag. Her outfit remains consistent throughout the vlog. Location A stylish rooftop party overlooking the city skyline at night. Warm string lights, lounge seating, live DJ, dance floor, mocktail bar, decorative plants, and groups of friends enjoying the evening. The atmosphere is lively, elegant, and realistic rather than crowded or chaotic. The recording begins inside the elevator as NARI smiles into the phone. "Tonight is all about relaxing with my friends... no rehearsals, no schedules." The elevator doors open to reveal the rooftop venue glowing with warm lights and music. She walks through the entrance, greeting friends with hugs and laughter before introducing a few of them to the camera with playful reactions. She grabs a colourful mocktail from the bar. "This one looks way too pretty not to film." As the music gets livelier, she joins her friends on the dance floor. Still holding the phone naturally, she records short moments of everyone dancing, laughing, spinning together, and singing along to the music. The camera occasionally turns outward to capture the city skyline, decorative lights, and the joyful atmosphere before returning to selfie view. Between songs she catches her breath, smiling at the camera. "I forgot how much I needed a night like this." Her friends pull her back onto the dance floor. She laughs, records a few more energetic moments, then walks toward the rooftop edge where the skyline fills the background. Looking into the camera with a relaxed smile, she says, "Sometimes the best memories are the ones you never plan." Her friends call her name from behind. She turns around laughing, waves to the camera, "Okay... they're stealing me back. See you next time!" She runs back toward her friends as everyone continues dancing together. The recording ends naturally as she lowers the phone while rejoining the celebration. Generation Requirements Produce one continuous realistic smartphone recording with a consistent facial identity, natural body movement, believable dancing, accurate hand interactions, realistic low-light smartphone exposure, stable clothing continuity, authentic crowd behaviour, smooth camera motion, and natural environmental audio. Avoid AI artifacts, duplicated people, warped anatomy, floating objects, jump cuts, or unrealistic movements. The final result should feel like a genuine personal party vlog filmed by a real K-pop idol on her own smartphone.
Invite vérifiée
A 15-second photorealistic Korean beauty commercial for a premium cushion foundation. Use @image1 as the exact reference for the model, product, and visual style. A young Korean woman sits in a bright minimalist room with soft daylight. She looks at her reflection in the mirror, notices uneven skin, then opens a pearl-beige cushion compact. Show elegant macro shots of the cushion, puff, and smooth foundation texture. She gently taps the cushion onto her cheek and face. The skin becomes naturally fresh, luminous, and smooth while keeping realistic pores and texture. Show close-up beauty shots with soft Korean TV commercial cinematography. She walks outside under warm sunlight, looking confident and radiant. End with a premium product hero shot of the cushion compact with soft background blur. Audio: soft Korean beauty commercial music, subtle product sounds, gentle female Korean voice.
A 15-second photorealistic Korean beauty commercial for a premium cushion foundation. Use @image1 as the exact reference for the model, product, and visual style. A young Korean woman sits in a bright minimalist room with soft daylight. She looks at her reflection in the mirror, notices uneven skin, then opens a pearl-beige cushion compact. Show elegant macro shots of the cushion, puff, and smooth foundation texture. She gently taps the cushion onto her cheek and face. The skin becomes naturally fresh, luminous, and smooth while keeping realistic pores and texture. Show close-up beauty shots with soft Korean TV commercial cinematography. She walks outside under warm sunlight, looking confident and radiant. End with a premium product hero shot of the cushion compact with soft background blur. Audio: soft Korean beauty commercial music, subtle product sounds, gentle female Korean voice.
Invite vérifiée
do this for Spain World Cup 2026, void main() { string player = "[PLAYER]"; team = player. team; beast = infer_mascot_anatomy(team); // wolf, dragon, eagle, etc. manga_artist_style = infer_manga_style_for_team(team); // e.g., Takehiko Inoue for Japan, Moebius-inflected for France layout = "double-page manga spread, right-to-left action flow"; // Panel 1: Player about to strike the ball, eyes glowing panel1 = render_manga_panel(player, action="shooting", transformation_phase="0%", effect="glowing aura"); // Panel 2: Limbs elongating, kit tearing into fur/scales, face half-human half-beast panel2 = render_transition_phase(player, beast, phase="50%", style=manga_artist_style); // Panel 3: Full beast unleashed, roaring, ball transformed into a sphere of energy panel3 = render_full_beast(beast, action="pouncing on ball", style="detailed ink hatching, speed lines"); // Japanese onomatopoeia add_sfx("GOGOGO", panel1); add_sfx("DOOM", panel2); add_sfx("GRAAAAH", panel3); overlay_team_emblem_as_clan_mon(beast, team); // crest becomes a Japanese clan symbol }
do this for Spain World Cup 2026, void main() { string player = "[PLAYER]"; team = player. team; beast = infer_mascot_anatomy(team); // wolf, dragon, eagle, etc. manga_artist_style = infer_manga_style_for_team(team); // e.g., Takehiko Inoue for Japan, Moebius-inflected for France layout = "double-page manga spread, right-to-left action flow"; // Panel 1: Player about to strike the ball, eyes glowing panel1 = render_manga_panel(player, action="shooting", transformation_phase="0%", effect="glowing aura"); // Panel 2: Limbs elongating, kit tearing into fur/scales, face half-human half-beast panel2 = render_transition_phase(player, beast, phase="50%", style=manga_artist_style); // Panel 3: Full beast unleashed, roaring, ball transformed into a sphere of energy panel3 = render_full_beast(beast, action="pouncing on ball", style="detailed ink hatching, speed lines"); // Japanese onomatopoeia add_sfx("GOGOGO", panel1); add_sfx("DOOM", panel2); add_sfx("GRAAAAH", panel3); overlay_team_emblem_as_clan_mon(beast, team); // crest becomes a Japanese clan symbol }
Invite vérifiée
A fearless football superstar with electric-blue eyes and unstoppable confidence, rendered in ultra-premium Japanese anime rendering, manga-style visual language, MAPPA-level sakuga, vibrant cel shading, dynamic perspective distortion, glowing aura VFX 0–4s: enters a giant World Cup stadium while rival players from multiple nations emerge from opposite tunnels like anime bosses; 4–10s: an insane sequence of dribbles, bicycle kicks, tackles and impossible saves unfolds, camera whipping between players with explosive anime transitions and impact frames; 10–13s: the hero launches a gigantic energy shot toward the goal, the ball transforming into a blue comet crossing the entire stadium; 13–15s: the explosion from the goal morphs into a massive wave of blue energy revealing a giant Pepsi can, ending with the PEPSI logo floating above the crowd as the stadium explodes with celebration World Cup 2026 anime spectacle, dynamic sports action, blockbuster commercial energy.
A fearless football superstar with electric-blue eyes and unstoppable confidence, rendered in ultra-premium Japanese anime rendering, manga-style visual language, MAPPA-level sakuga, vibrant cel shading, dynamic perspective distortion, glowing aura VFX 0–4s: enters a giant World Cup stadium while rival players from multiple nations emerge from opposite tunnels like anime bosses; 4–10s: an insane sequence of dribbles, bicycle kicks, tackles and impossible saves unfolds, camera whipping between players with explosive anime transitions and impact frames; 10–13s: the hero launches a gigantic energy shot toward the goal, the ball transforming into a blue comet crossing the entire stadium; 13–15s: the explosion from the goal morphs into a massive wave of blue energy revealing a giant Pepsi can, ending with the PEPSI logo floating above the crowd as the stadium explodes with celebration World Cup 2026 anime spectacle, dynamic sports action, blockbuster commercial energy.
Invite vérifiée
FORMAT: 16:9 cinematic storyboard presentation, 1920×1080, ultra-detailed high-resolution STYLE: Hyper-realistic YouTube livestream horror, premium storyboard infographic, cinematic found-footage realism, dark documentary aesthetic PROJECT: PARIS CATACOMBS LIVESTREAM TITLE: “LIVE EXPLORING PARIS CATACOMBS (NOT CLICKBAIT)” DURATION: 15 Seconds LAYOUT: 5 large cinematic storyboard frames in top row Technical breakdown panels in bottom row Black premium background Thin white borders Red YouTube LIVE accents Minimal professional production-board layout ──────────────────── FRAME 01 (0:00–0:03) STREAM STARTS Wide handheld selfie shot. Streamer walking through narrow Paris catacombs tunnel. Walls built from skulls and bones. Headlamp and flashlight are only light sources. YOUTUBE UI OVERLAY: LIVE ● Viewers: 18,492 Chat visible on right side CHAT: “bro this is illegal” “turn back” “no way this is real” CAMERA: Handheld selfie cam Slight shake VISUAL: Wet stone walls Skulls Dark tunnel depth ──────────────────── FRAME 02 (0:03–0:06) DEEPER INSIDE Rear-facing camera. Tunnel becomes tighter and more claustrophobic. Streamer scans walls using flashlight. DIALOGUE: “Guys… I don’t think tourists come here.” CAMERA: Sony A7S III low-light look Shaky tracking shot VISUAL: Bones everywhere Moisture on walls Water puddles ──────────────────── FRAME 03 (0:06–0:09) CHAT NOTICES SOMETHING Streamer pans camera. Nothing visible to him. Chat suddenly floods rapidly. CHAT: “WAIT” “WHO IS THAT” “BRO BEHIND YOU” “RUN” CAMERA: Fast pan Digital compression artifacts VISUAL: Bitrate drop Glitch tearing Audio waveform distortion ──────────────────── FRAME 04 (0:09–0:12) ENTITY APPEARS Camera slowly turns toward deep tunnel. Far away: Tall pale humanoid figure. Standing completely motionless. No visible face. Unnaturally long limbs. CAMERA: Slow digital zoom Compression noise VISUAL: Flashlight flicker Deep darkness Entity silhouette ──────────────────── FRAME 05 (0:12–0:15) STREAM ENDS Entity suddenly much closer. Impossible movement. Streamer screams. Camera drops sideways. Final frame: Entity crouching near fallen camera. YOUTUBE UI: SIGNAL LOST STREAM ENDED VISUAL: Static noise Broken stream frame Corrupted pixels ──────────────────── KEY VISUALS: - Catacomb skull walls - YouTube live UI - Chat overlay - Flashlight beam - Compression artifacts - Pale humanoid entity - Moist tunnel reflections - Broken stream signal CAMERA STYLE REFERENCE: - IRL YouTube livestream - GoPro + Sony low-light footage - Found footage horror - Handheld realism - Sensor noise - Rolling shutter artifacts LIGHTING: - Headlamp beam - Flashlight spill - Cold blue shadows - Black void darkness - Moisture reflections - Flickering light COLOR PALETTE: Deep Black Bone White Wet Stone Gray Cold Blue Emergency Red AUDIO REFERENCE: - Dripping water - Heavy breathing - Footsteps - Chat notification pings - Digital glitch distortion - Sudden silence IMPORTANT NOTES: - Must feel REAL, not cinematic-polished - Zero supernatural glow - Entity should be subtle and terrifying - Horror comes from realism - Authentic livestream imperfections required TONE & ENERGY: Claustrophobic Unsettling Viral horror Psychological dread Realistic panic OUTPUT: Premium horror livestream storyboard Feels like a real viral YouTube stream gone horribly wrong
FORMAT: 16:9 cinematic storyboard presentation, 1920×1080, ultra-detailed high-resolution STYLE: Hyper-realistic YouTube livestream horror, premium storyboard infographic, cinematic found-footage realism, dark documentary aesthetic PROJECT: PARIS CATACOMBS LIVESTREAM TITLE: “LIVE EXPLORING PARIS CATACOMBS (NOT CLICKBAIT)” DURATION: 15 Seconds LAYOUT: 5 large cinematic storyboard frames in top row Technical breakdown panels in bottom row Black premium background Thin white borders Red YouTube LIVE accents Minimal professional production-board layout ──────────────────── FRAME 01 (0:00–0:03) STREAM STARTS Wide handheld selfie shot. Streamer walking through narrow Paris catacombs tunnel. Walls built from skulls and bones. Headlamp and flashlight are only light sources. YOUTUBE UI OVERLAY: LIVE ● Viewers: 18,492 Chat visible on right side CHAT: “bro this is illegal” “turn back” “no way this is real” CAMERA: Handheld selfie cam Slight shake VISUAL: Wet stone walls Skulls Dark tunnel depth ──────────────────── FRAME 02 (0:03–0:06) DEEPER INSIDE Rear-facing camera. Tunnel becomes tighter and more claustrophobic. Streamer scans walls using flashlight. DIALOGUE: “Guys… I don’t think tourists come here.” CAMERA: Sony A7S III low-light look Shaky tracking shot VISUAL: Bones everywhere Moisture on walls Water puddles ──────────────────── FRAME 03 (0:06–0:09) CHAT NOTICES SOMETHING Streamer pans camera. Nothing visible to him. Chat suddenly floods rapidly. CHAT: “WAIT” “WHO IS THAT” “BRO BEHIND YOU” “RUN” CAMERA: Fast pan Digital compression artifacts VISUAL: Bitrate drop Glitch tearing Audio waveform distortion ──────────────────── FRAME 04 (0:09–0:12) ENTITY APPEARS Camera slowly turns toward deep tunnel. Far away: Tall pale humanoid figure. Standing completely motionless. No visible face. Unnaturally long limbs. CAMERA: Slow digital zoom Compression noise VISUAL: Flashlight flicker Deep darkness Entity silhouette ──────────────────── FRAME 05 (0:12–0:15) STREAM ENDS Entity suddenly much closer. Impossible movement. Streamer screams. Camera drops sideways. Final frame: Entity crouching near fallen camera. YOUTUBE UI: SIGNAL LOST STREAM ENDED VISUAL: Static noise Broken stream frame Corrupted pixels ──────────────────── KEY VISUALS: - Catacomb skull walls - YouTube live UI - Chat overlay - Flashlight beam - Compression artifacts - Pale humanoid entity - Moist tunnel reflections - Broken stream signal CAMERA STYLE REFERENCE: - IRL YouTube livestream - GoPro + Sony low-light footage - Found footage horror - Handheld realism - Sensor noise - Rolling shutter artifacts LIGHTING: - Headlamp beam - Flashlight spill - Cold blue shadows - Black void darkness - Moisture reflections - Flickering light COLOR PALETTE: Deep Black Bone White Wet Stone Gray Cold Blue Emergency Red AUDIO REFERENCE: - Dripping water - Heavy breathing - Footsteps - Chat notification pings - Digital glitch distortion - Sudden silence IMPORTANT NOTES: - Must feel REAL, not cinematic-polished - Zero supernatural glow - Entity should be subtle and terrifying - Horror comes from realism - Authentic livestream imperfections required TONE & ENERGY: Claustrophobic Unsettling Viral horror Psychological dread Realistic panic OUTPUT: Premium horror livestream storyboard Feels like a real viral YouTube stream gone horribly wrong
Invite vérifiée
Style: STOP-MOTION ANIMATION — stepped, frame-by-frame motion brought to a HAND-PAINTED 2D look, a moving oil painting, NOT clay, NOT puppets, NOT 3D. True 12fps, ANIMATED ON TWOS: 12 distinct hand-painted drawings per second, each pose held two frames then snapping to the next, never gliding — even at full gallop the action steps pose to pose with the strobing cadence of hand-drawn animation. Constant painterly BOIL. NO smooth interpolation, NO motion blur, NO morphing, real frame-by-frame animation not AI slop. Style from <<<image_1>>>, the wolves from <<<image_2>>>, RIDER 1 from <<<image_3>>> riding HIS horse from <<<image_4>>> — the same lead rider and the same horse as one consistent pair throughout, never another horse, never another man. The dusk snowfield from <<<image_5>>>. Blizzard haze and blowing snow drift SMOOTHLY; figures, horses, wolves and drawn snow-spray effects step on twos with secondary action. DIRECTOR'S NOTES: 1/ THE SCENE — full-gallop chase in the dusk blizzard, brutal and fast. RIDER 1, the lead rider, chases a sprinting wolf, leans low off the saddle in the manner of a kok-boru player reaching for the ulak, seizes the wolf by the scruff — and the wolf twists and savages his arm. A second wolf hits him from his blind side. He is torn from the saddle at full speed and the pack swarms him. Savage, dynamic, with REAL PHYSICS and a visible causal chain — every wound has its on-screen cause. 2/ REAL PHYSICS AND CAUSALITY — the horse (<<<image_4>>>) gallops with true four-beat weight; RIDER 1 hangs low off the side of the saddle, one hand braced, reaching down; the wolf is a heavy animal — when seized it twists its WHOLE body mid-stride, and that twisting weight plus the clamping bite WRENCHES the rider off balance; the bite is shown on screen: jaws clamp and crush onto his forearm, tearing sleeve and flesh, dark blood — cause before effect, always; the second wolf launches from his blind side and slams full-body into his chest like a missile; torn from the saddle at gallop speed he hits the snow HARD and TUMBLES with momentum, rolling over and over, loose powder snow bursting around each impact (drawn snow-spray effects on twos), the riderless horse galloping on; the pack converges as a fast dark stream and swarms over him, a savage thrashing dark mass. 3/ BRUTALITY STAGED, NOT LINGERED — the violence is fast, hard and physical: the crunching bite, the dark blood across the snow, the swarming pack. Show the savagery through motion, dark mass and sound, not slow anatomical detail. 4/ AGGRESSIVE HANDHELD CHASE CAMERA — racing alongside at gallop, violently jolting with the speed, whipped by wind, jerky corrections, the horizon tilting and never level; on the fall a hard DUTCH TILT as the world goes over with him. Never gimbal-smooth, never tripod-locked. 5/ SECONDARY ACTION on twos — RIDER 1's chapan skirts and fur hat whipping with follow-through, the horse's mane and tail streaming, the wolves' fur rippling along their backs, harness swinging, breath-vapor of horse and man tearing off in the wind, snow bursting from hooves as drawn powder on twos. 6/ LIGHT — deep dusk in a blizzard, dim cold blue-grey storm light, soft, no rays, no beams, no god rays, the figures dark masses against the pale snow. Correct neutral white balance, NOT a blue filter, muted desaturated; the blood a dark muted red, stark on the snow but never glossy, never bright. SHOT 1 — FULL-GALLOP TRACKING, ~35mm, aggressive handheld racing alongside. COMPOSITION: RIDER 1 on his horse a large dark mass driving in from the RIGHT third, the sprinting wolf low ahead of him on the LEFT third, both tearing diagonally through the frame left-and-deeper — the diagonal of the chase as the line of dynamics; the pale storm-lit snowfield from <<<image_5>>> streaking past as negative space. RIDER 1 drops LOW off the side of the saddle in a kok-boru lean, one hand braced on the saddle, the other arm stretching down for the wolf's scruff, his chapan and the horse's mane whipping on twos, hooves throwing bursts of powder. He bares his teeth, hoarse over the wind, lips on twos: "Ustadym!.." His fist closes on the wolf's scruff — HARD CUT to SHOT 2 — CLOSE DYNAMIC, ~50mm, aggressive handheld slammed in tight: the wolf, seized, TWISTS its whole heavy body mid-stride in one violent stepped motion — and its jaws clamp CRUSHING onto RIDER 1's forearm, on screen, tearing through sleeve and flesh, dark blood whipping across the snow and the wolf's muzzle. His raw scream tears over the wind. The wolf's twisting weight and the bite WRENCH him sideways off his balance, his body dragged half out of the saddle, his fur hat ripping away with follow-through. Cause and effect brutal and readable, all stepping on twos. HARD CUT to SHOT 3 — MEDIUM WIDE with a hard DUTCH TILT, ~35mm, aggressive handheld: from his blind side a SECOND wolf launches — a dark missile — and slams full-body into his chest. Torn from the saddle at gallop speed RIDER 1 hits the snow HARD and TUMBLES, rolling over and over with real momentum, powder snow bursting at each impact as drawn effects on twos, the horizon tilted and reeling, his riderless horse (<<<image_4>>>) galloping on into the storm. And then the pack pours in — a fast dark stream of wolves from <<<image_2>>> out of the storm, varied coats, converging from all sides and SWARMING over him, a savage thrashing dark mass on the pale snow, dark blood spreading, snow scattering, his cries swallowed by the blizzard and the snarling. The dark mass of the pack traps and frames him. Hold one brutal beat in the howling wind. End. Audio: NO MUSIC — the roar of the blizzard, pounding gallop, the wolf's snarl and the wet crunch of the bite, the rider's raw scream, the heavy tumbling impacts, the converging snarls of the pack, the wind swallowing everything. No subtitles. Natural diegetic sound only, absolutely no music. Constraints: stop-motion stepped cadence on twos at 12fps with painterly boil even at full gallop, every action stepping pose to pose never gliding, NO smooth interpolation NO motion blur NO morphing, blizzard haze smooth while all figures animals and drawn snow-spray effects step on twos, hand-painted oil look from <<<image_1>>> not photoreal not 3D not glossy, three shots with hard cuts — full-gallop tracking with the kok-boru lean and the grab "Ustadym!..", close dynamic of the twisting wolf and the crushing on-screen bite with dark blood and the scream, dutch-tilted wide of the second wolf's full-body slam the hard tumbling fall at speed and the pack swarming him as a savage dark mass — RIDER 1 from <<<image_3>>> and his horse from <<<image_4>>> the SAME consistent pair in every shot never swapped, REAL PHYSICS AND VISIBLE CAUSALITY every wound caused on screen the wolf's twisting weight wrenching the rider the bite before the blood the slam before the fall the momentum carrying the tumble, AGGRESSIVE HANDHELD racing jolting wind-whipped horizon never level hard dutch tilt on the fall never gimbal-smooth, SECONDARY ACTION on twos chapan hat mane tail wolf fur harness breath-vapor all whipping with follow-through, wolves from <<<image_2>>> varied in coat tone size and stride never mirrored never cloned, deep dusk blizzard dim cold storm light soft no rays no beams, correct neutral white balance not a blue filter muted desaturated dark muted blood never bright never glossy, brutality fast hard and physical staged through motion dark mass and sound not lingering gore, spoken Kazakh in Latin transliteration pronounced as written, NO MUSIC only storm hooves snarls and screams.
Style: STOP-MOTION ANIMATION — stepped, frame-by-frame motion brought to a HAND-PAINTED 2D look, a moving oil painting, NOT clay, NOT puppets, NOT 3D. True 12fps, ANIMATED ON TWOS: 12 distinct hand-painted drawings per second, each pose held two frames then snapping to the next, never gliding — even at full gallop the action steps pose to pose with the strobing cadence of hand-drawn animation. Constant painterly BOIL. NO smooth interpolation, NO motion blur, NO morphing, real frame-by-frame animation not AI slop. Style from <<<image_1>>>, the wolves from <<<image_2>>>, RIDER 1 from <<<image_3>>> riding HIS horse from <<<image_4>>> — the same lead rider and the same horse as one consistent pair throughout, never another horse, never another man. The dusk snowfield from <<<image_5>>>. Blizzard haze and blowing snow drift SMOOTHLY; figures, horses, wolves and drawn snow-spray effects step on twos with secondary action. DIRECTOR'S NOTES: 1/ THE SCENE — full-gallop chase in the dusk blizzard, brutal and fast. RIDER 1, the lead rider, chases a sprinting wolf, leans low off the saddle in the manner of a kok-boru player reaching for the ulak, seizes the wolf by the scruff — and the wolf twists and savages his arm. A second wolf hits him from his blind side. He is torn from the saddle at full speed and the pack swarms him. Savage, dynamic, with REAL PHYSICS and a visible causal chain — every wound has its on-screen cause. 2/ REAL PHYSICS AND CAUSALITY — the horse (<<<image_4>>>) gallops with true four-beat weight; RIDER 1 hangs low off the side of the saddle, one hand braced, reaching down; the wolf is a heavy animal — when seized it twists its WHOLE body mid-stride, and that twisting weight plus the clamping bite WRENCHES the rider off balance; the bite is shown on screen: jaws clamp and crush onto his forearm, tearing sleeve and flesh, dark blood — cause before effect, always; the second wolf launches from his blind side and slams full-body into his chest like a missile; torn from the saddle at gallop speed he hits the snow HARD and TUMBLES with momentum, rolling over and over, loose powder snow bursting around each impact (drawn snow-spray effects on twos), the riderless horse galloping on; the pack converges as a fast dark stream and swarms over him, a savage thrashing dark mass. 3/ BRUTALITY STAGED, NOT LINGERED — the violence is fast, hard and physical: the crunching bite, the dark blood across the snow, the swarming pack. Show the savagery through motion, dark mass and sound, not slow anatomical detail. 4/ AGGRESSIVE HANDHELD CHASE CAMERA — racing alongside at gallop, violently jolting with the speed, whipped by wind, jerky corrections, the horizon tilting and never level; on the fall a hard DUTCH TILT as the world goes over with him. Never gimbal-smooth, never tripod-locked. 5/ SECONDARY ACTION on twos — RIDER 1's chapan skirts and fur hat whipping with follow-through, the horse's mane and tail streaming, the wolves' fur rippling along their backs, harness swinging, breath-vapor of horse and man tearing off in the wind, snow bursting from hooves as drawn powder on twos. 6/ LIGHT — deep dusk in a blizzard, dim cold blue-grey storm light, soft, no rays, no beams, no god rays, the figures dark masses against the pale snow. Correct neutral white balance, NOT a blue filter, muted desaturated; the blood a dark muted red, stark on the snow but never glossy, never bright. SHOT 1 — FULL-GALLOP TRACKING, ~35mm, aggressive handheld racing alongside. COMPOSITION: RIDER 1 on his horse a large dark mass driving in from the RIGHT third, the sprinting wolf low ahead of him on the LEFT third, both tearing diagonally through the frame left-and-deeper — the diagonal of the chase as the line of dynamics; the pale storm-lit snowfield from <<<image_5>>> streaking past as negative space. RIDER 1 drops LOW off the side of the saddle in a kok-boru lean, one hand braced on the saddle, the other arm stretching down for the wolf's scruff, his chapan and the horse's mane whipping on twos, hooves throwing bursts of powder. He bares his teeth, hoarse over the wind, lips on twos: "Ustadym!.." His fist closes on the wolf's scruff — HARD CUT to SHOT 2 — CLOSE DYNAMIC, ~50mm, aggressive handheld slammed in tight: the wolf, seized, TWISTS its whole heavy body mid-stride in one violent stepped motion — and its jaws clamp CRUSHING onto RIDER 1's forearm, on screen, tearing through sleeve and flesh, dark blood whipping across the snow and the wolf's muzzle. His raw scream tears over the wind. The wolf's twisting weight and the bite WRENCH him sideways off his balance, his body dragged half out of the saddle, his fur hat ripping away with follow-through. Cause and effect brutal and readable, all stepping on twos. HARD CUT to SHOT 3 — MEDIUM WIDE with a hard DUTCH TILT, ~35mm, aggressive handheld: from his blind side a SECOND wolf launches — a dark missile — and slams full-body into his chest. Torn from the saddle at gallop speed RIDER 1 hits the snow HARD and TUMBLES, rolling over and over with real momentum, powder snow bursting at each impact as drawn effects on twos, the horizon tilted and reeling, his riderless horse (<<<image_4>>>) galloping on into the storm. And then the pack pours in — a fast dark stream of wolves from <<<image_2>>> out of the storm, varied coats, converging from all sides and SWARMING over him, a savage thrashing dark mass on the pale snow, dark blood spreading, snow scattering, his cries swallowed by the blizzard and the snarling. The dark mass of the pack traps and frames him. Hold one brutal beat in the howling wind. End. Audio: NO MUSIC — the roar of the blizzard, pounding gallop, the wolf's snarl and the wet crunch of the bite, the rider's raw scream, the heavy tumbling impacts, the converging snarls of the pack, the wind swallowing everything. No subtitles. Natural diegetic sound only, absolutely no music. Constraints: stop-motion stepped cadence on twos at 12fps with painterly boil even at full gallop, every action stepping pose to pose never gliding, NO smooth interpolation NO motion blur NO morphing, blizzard haze smooth while all figures animals and drawn snow-spray effects step on twos, hand-painted oil look from <<<image_1>>> not photoreal not 3D not glossy, three shots with hard cuts — full-gallop tracking with the kok-boru lean and the grab "Ustadym!..", close dynamic of the twisting wolf and the crushing on-screen bite with dark blood and the scream, dutch-tilted wide of the second wolf's full-body slam the hard tumbling fall at speed and the pack swarming him as a savage dark mass — RIDER 1 from <<<image_3>>> and his horse from <<<image_4>>> the SAME consistent pair in every shot never swapped, REAL PHYSICS AND VISIBLE CAUSALITY every wound caused on screen the wolf's twisting weight wrenching the rider the bite before the blood the slam before the fall the momentum carrying the tumble, AGGRESSIVE HANDHELD racing jolting wind-whipped horizon never level hard dutch tilt on the fall never gimbal-smooth, SECONDARY ACTION on twos chapan hat mane tail wolf fur harness breath-vapor all whipping with follow-through, wolves from <<<image_2>>> varied in coat tone size and stride never mirrored never cloned, deep dusk blizzard dim cold storm light soft no rays no beams, correct neutral white balance not a blue filter muted desaturated dark muted blood never bright never glossy, brutality fast hard and physical staged through motion dark mass and sound not lingering gore, spoken Kazakh in Latin transliteration pronounced as written, NO MUSIC only storm hooves snarls and screams.
Invite vérifiée
古风美人立于红柱宫廊,绾发金步摇珠串垂落,绛红描金广袖汉服内搭白衣,右手执山水折扇,左手轻拈一枝白梅,侧首望向廊外;背景金色夕照、银杏叠瓦、远山宫宇、雨后湿石地倒影、落叶纷飞。
古风美人立于红柱宫廊,绾发金步摇珠串垂落,绛红描金广袖汉服内搭白衣,右手执山水折扇,左手轻拈一枝白梅,侧首望向廊外;背景金色夕照、银杏叠瓦、远山宫宇、雨后湿石地倒影、落叶纷飞。
Invite vérifiée
Part 1 (0–7s) A cinematic Pixar-style animated short film with feature-film-quality 3D animation, expressive stylized characters, a cozy warmly-lit coffee shop, golden afternoon light, shallow depth of field, fast dynamic cinematic camera cuts, upbeat urgent orchestral score, polished Pixar-quality rendering, expressive facial animation. A shy 20-year-old coffee shop boy with soft wavy brown hair, gentle hazel eyes, forest-green apron over a white shirt, finishes a coffee cup behind the counter. A 20-year-old girl with auburn ponytail, green eyes, oversized denim jacket, grabs the cup and bolts for the door. Shop Manager (shouting): "She didn't pay!" She collides with the boy, coffee splashing. Girl (rushed): "Sorry—I'll pay you back!" She's gone, weaving through the street crowd. Boy stands frozen, coffee-stained. Part 2 (7–15s) Continue seamlessly. Same characters, clothing, lighting, coffee shop, Pixar-style feature-film-quality 3D animation. Next morning, boy wipes the counter, distracted. Door chimes fast — the girl rushes back in, holding out cash and a small pastry bag. Girl (quick, breathless): "My brother — hospital. I still remembered!" She sets it down and turns to leave already. Boy (surprised, half-smile): "You didn't have to—" Girl (already at the door, grinning back): "Said I would!" Door chimes shut behind her. Boy stands there, smiling, coffee-stained sleeve forgotten. Camera quick pull-back. Cut to black.
Part 1 (0–7s) A cinematic Pixar-style animated short film with feature-film-quality 3D animation, expressive stylized characters, a cozy warmly-lit coffee shop, golden afternoon light, shallow depth of field, fast dynamic cinematic camera cuts, upbeat urgent orchestral score, polished Pixar-quality rendering, expressive facial animation. A shy 20-year-old coffee shop boy with soft wavy brown hair, gentle hazel eyes, forest-green apron over a white shirt, finishes a coffee cup behind the counter. A 20-year-old girl with auburn ponytail, green eyes, oversized denim jacket, grabs the cup and bolts for the door. Shop Manager (shouting): "She didn't pay!" She collides with the boy, coffee splashing. Girl (rushed): "Sorry—I'll pay you back!" She's gone, weaving through the street crowd. Boy stands frozen, coffee-stained. Part 2 (7–15s) Continue seamlessly. Same characters, clothing, lighting, coffee shop, Pixar-style feature-film-quality 3D animation. Next morning, boy wipes the counter, distracted. Door chimes fast — the girl rushes back in, holding out cash and a small pastry bag. Girl (quick, breathless): "My brother — hospital. I still remembered!" She sets it down and turns to leave already. Boy (surprised, half-smile): "You didn't have to—" Girl (already at the door, grinning back): "Said I would!" Door chimes shut behind her. Boy stands there, smiling, coffee-stained sleeve forgotten. Camera quick pull-back. Cut to black.
Plus de générateurs vidéo IA
Explorez notre collection de générateurs vidéo IA spécialisés conçus pour différents besoins et styles créatifs
Créer avec le générateur vidéo IA Seedance 2.0
Commencez par un brief créatif clair
Décrivez votre sujet, le décor et le style visuel. Gardez l'idée principale ciblée afin de pouvoir juger le résultat par rapport à votre intention.
Utilisez les entrées proposées par votre modèle
Choisissez un modèle avant d'ajouter un média de référence. Les modes d'entrée pris en charge, les limites de référence et les paramètres de sortie sont affichés dans le générateur.
Consultez le devis avant de générer
Le coût en crédits dépend du modèle et des paramètres sélectionnés. Vérifiez le devis affiché avant de soumettre une requête.
Comment utiliser le générateur vidéo IA Seedance 2.0
Choisissez votre modèle et votre entrée
Sélectionnez un modèle disponible. Rédigez un prompt ou ajoutez un média de référence lorsque le mode sélectionné le prend en charge.
Affinez votre brief et vos paramètres
Décrivez la composition et le mouvement. Sélectionnez les options de sortie disponibles et examinez les crédits requis.
Générez et vérifiez
Soumettez la requête et suivez-la dans l'Historique. Vérifiez le résultat terminé avant de le télécharger ou de le partager.
Planifier votre brief vidéo
Conseils de prompt
Définissez le sujet
Nommez le sujet principal et les détails qui doivent rester reconnaissables.
Générateur vidéo IA Seedance 2.0 : questions et réponses
Le générateur liste les modèles activés pour cet espace de travail et correspondant à cette page. Vérifiez le modèle sélectionné avant de soumettre.
La prise en charge des références dépend du modèle et du mode sélectionnés. Utilisez les contrôles de référence et les limites affichés dans le générateur.
Vérifiez les crédits requis après avoir choisi votre modèle et vos paramètres. Modifier ces choix peut modifier le devis.
Utilisez les paramètres de sortie proposés pour le modèle sélectionné. Les options varient selon les modèles.
Suivez la requête dans l'Historique. Ouvrez ou téléchargez un résultat terminé via les contrôles d'actifs existants.
Vous pouvez demander un remboursement dans les 10 jours suivant l’achat si vous disposez de crédits inutilisés issus de cet achat et si vous fournissez un motif clair, sous réserve de notre Politique de remboursement. Si vous êtes éligible, un achat inutilisé peut être remboursé intégralement ; un achat partiellement utilisé est remboursé au prorata des crédits inutilisés restants. Les achats entièrement utilisés ainsi que les crédits gratuits ou promotionnels ne sont pas remboursables.
La validité des crédits dépend du pack, de l’abonnement ou de la promotion qui les a émis. Consultez les conditions d’achat et les dates d’expiration dans Paramètres > Crédits. Un renouvellement ou un nouvel achat ne prolonge pas les crédits plus anciens. Utilisez les crédits avant leur date d’expiration indiquée ; ne partez pas du principe que les crédits d’abonnement inutilisés sont reportés indéfiniment.
Les crédits facturés pour une tâche confirmée comme échouée en raison d'une erreur système sont restitués automatiquement. Une tâche encore en cours de traitement n'a pas encore été confirmée comme échouée. Vérifiez son statut et l'historique de vos crédits avant de soumettre à nouveau. Si un échec confirmé affiche toujours un débit non résolu, envoyez un e-mail à support@flux3video.dev avec l'ID de tâche.
Les résultats de l'IA peuvent varier ; un résultat terminé qui diffère de vos attentes n'est donc pas automatiquement considéré comme un échec technique. Les tâches d'image terminées éligibles peuvent être soumises à une évaluation de remboursement en crédits via l'option de remboursement lorsqu'elle est disponible ; une approbation est requise. Pour une vidéo ou un autre problème, contactez support@flux3video.dev avec l'ID de tâche et les détails. Un remboursement en crédits restitue des crédits, et non de l'argent sur votre moyen de paiement.
Envoyez un e-mail à support@flux3video.dev. Pour la facturation, indiquez l'e-mail de votre compte et l'ID de commande ; pour la génération, indiquez l'ID de tâche, la description du problème et les captures d'écran pertinentes. Si vous avez acheté en tant qu'invité, conservez les données du navigateur d'origine et le reçu de paiement afin que nous puissions vous aider à retrouver l'achat.
Commencez votre prochaine vidéo
Choisissez un modèle pris en charge sur flux3 video, vérifiez ses paramètres et consultez le devis de crédits avant de générer.
Créer des vidéosflux3video.dev · Mis à jour
Consulter l’historique des mises à jour
- — Ajout de prompts modifiables, de brouillons distincts pour les modes texte et référence et d’une commande pour rétablir l’exemple.
- — Textes et contenu de la page mis à jour.
- — Contenu de la page publié. Textes et contenu de la page mis à jour.