Veo 動画シーンを計画する
Veo video scene planning と具体的なビジュアル目標から始めましょう。ビジュアルアクションとカメラフレーミングを説明し、オーディオの指示は選択したモードが対応している場合にのみ追加してください。
シーン計画用の Veo 3 Video Generator
CanvasSeed の Veo 3 video generator を使用して Veo シーン計画を探りましょう。ビジュアルブリーフとサウンドのアイデアを分けてください。オーディオコントロールは、選択したモデルが公開している場合にのみ使用し、結果のクリップとサウンドを確認しましょう。タスクを送信する前に、利用可能なモデル、対応する設定、現在のクレジット見積もりを確認してください。
テキスト、画像、または対応する動画タスクを選択
製品ストーリーをスケッチする
参照主導のアイデアの場合、使用許可のある素材をアップロードし、選択したモデルの要件を確認しましょう。何を認識可能なまま残し、何を変更するかを指定します。
シーンオーディオを検討する
カバー、製品コンセプト、ソーシャル投稿など、意図する用途に合わせてフレームを計画してください。視聴者が最初にどこを見るべきか、アクションがどのように終わるかを決めてください。
Veo プロンプトを閲覧
このサイトで公開されている事例やプロンプトライブラリを見て、ブリーフと出力の関係を理解しましょう。実際のモデルラベルを読み、役立つ構図のアイデアを選び、あなたの被写体用にプロンプトを書き直しましょう。
CanvasSeed の公開動画例
公開動画ギャラリーを使って、実際の結果をモデルラベルと利用可能なプロンプトとともに研究しましょう。クリップ全体を通してアクションとカメラの動きがどのように展開するかを視聴してください。このページの6つのプロンプトアイデアは、適応できる提案概要であり、それらの正確なシーンが生成されたという主張ではありません。
A humorous hybrid of live-action cinematography and flat 2D sticker
Seedance 2.0
プロンプトを表示
Visual Style: A humorous hybrid of live-action cinematography and flat 2D sticker animation, presented as a first-person ramen cooking vlog. The environment is filmed with realistic detail while the featured character remains a bold, paper-cut style cartoon sticker, creating an intentionally exaggerated contrast between reality and animation. Ultra-detailed 8K quality, vertical 9:16 composition, subtle handheld movement for a natural POV feel. Length 10 seconds Environment A cozy home kitchen viewed entirely from the cook's perspective. A black cooking pot filled with ramen gently simmers on the stovetop, sending steam into the air. Rich golden broth surrounds freshly cooked noodles. Nearby ingredients include sliced chashu pork, chopped scallions, half a soft-boiled egg, sheets of nori, sesame seeds, and a bottle of chili oil waiting on the counter. The background features white ceramic tiles, common kitchen condiments, a stainless-steel sink, and soft daylight entering from a nearby window. Character Use @ image 1 as the definitive character reference. Maintain the character's original proportions, facial expression, clothing, beanie, teal sling bag with frog accessory, thick black outlines, and flat illustrated appearance. The character should always look like a printed vinyl sticker placed inside a real kitchen—never receiving realistic shadows, reflections, or volumetric lighting. Do not include the baseball bat. The character sits on a small wooden stool beside the stove at roughly half the height of the ramen pot. Throughout the video, realistic human hands occasionally enter from the right side of the frame to interact with both the food and the character. 00:00–00:03 — Shot 1 | Too Much Heat A first-person view shows the cook gently stirring the ramen with a ladle. While the cook is distracted, @image1 quietly grabs an enormous bottle of chili oil that's almost twice its own height. With a smug expression and narrowed eyes, it tips the bottle forward, sending a continuous stream of deep crimson chili oil flooding into the pot. The broth rapidly shifts from a warm golden color to an intense fiery red as glossy ribbons of chili oil swirl across the surface. The character watches proudly, trying not to laugh. Audio Gentle bubbling broth Thick liquid pouring Quiet cartoon snickering 00:03–00:05 — Shot 2 | Caught in the Act The cook immediately reaches over and pulls the chili oil bottle away. Without hesitation, the ladle taps the top of @image1's head. A bold comic-style "DUANG!" pops above the beanie as a bright red bump instantly appears. The character's flat sticker body squashes downward before springing back into shape while clutching its head. Audio Metallic cartoon bonk Rubbery bounce sound 00:05–00:08 — Shot 3 | Instant Regret Still holding its head, @image1 begins sobbing dramatically. Its eyes transform into spinning spirals while exaggerated streams of blue cartoon tears shoot outward. The cook calmly scoops a full ladle of the blazing-hot spicy broth and pours it straight into the character's open mouth. Its cheeks immediately balloon outward. Its orange face gradually shifts to a deep glowing red. Thin trails of smoke curl from both ears as the heat takes effect. Audio Loud exaggerated crying Broth pouring Gulp Dramatic sizzling effect 00:08–00:10 — Shot 4 | Total Meltdown The character suddenly locks completely still. Its entire body glows with intense heat. Steam erupts from both ears while a tiny burst of cartoon fire escapes from its mouth. Its eyes flip into oversized X shapes. Completely stiff, it slowly tips backward off the stool before crashing flat onto the countertop. Small flames continue flickering from its mouth while colorful dizzy stars spin around its head. The final frame freezes on the defeated pose. Audio Loud steam release Tiny flame pop Heavy cartoon impact Classic comedic knockout sting
A 3D Disney-Pixar style animated scene. A young Polynesian-looking woman
Seedance 2.0
プロンプトを表示
A 3D Disney-Pixar style animated scene. A young Polynesian-looking woman with long, flowing dark brown hair and an off-white cotton dress is effortlessly lifting a massive, heavy modern sofa above her head with one hand. Her expression is confident and mischievous, with a proud smile. She is standing in a luxurious, sunlit living room with high ceilings, large windows, elegant crown molding, and polished marble floors that reflect the bright, warm sunlight streaming in. In the background, a tall, muscular man with short dark hair, wearing a white cable-knit polo shirt, stares at her with wide eyes and an open mouth in complete, comical shock. Vibrant, cinematic lighting, rich colors, ultra-detailed characters, 8k resolution, smooth animation style.
Create a 15-second vertical 16:9 UGC-style shampoo advertisement that feels #366186
Seedance 2.0
プロンプトを表示
Create a 15-second vertical 16:9 UGC-style shampoo advertisement that feels authentic, premium, and social-media ready. A confident young woman stands in a bright, modern bathroom with soft natural morning light. She holds the shampoo bottle close to the camera, smiling warmly as if recommending it to a friend. Her hair is long, healthy, shiny, and naturally bouncy. She speaks directly to the camera: "I've finally found a shampoo that leaves my hair feeling soft, strong, and incredibly shiny. It cleans without drying, smells amazing, and honestly makes every wash feel like a salon treatment. If you're looking for healthier-looking hair, you have to try this!" Storyboard: Scene 1: Close-up of the shampoo bottle in her hand as she introduces it. Scene 2: She dispenses the shampoo into her palm, creating a rich, creamy lather. Scene 3: Beauty shots of her gently washing and massaging her hair, with realistic foam and flowing water. Scene 4: After drying, she flips her silky, glossy hair while smiling confidently at the camera. Scene 5: Final hero shot holding the shampoo beside her face with a clean, premium bathroom background. She smiles and says, "Highly recommend!" The video should have realistic smartphone camera quality, natural handheld movement, genuine facial expressions, smooth transitions, accurate lip sync, premium product visibility throughout, and a polished yet authentic UGC aesthetic. The shampoo bottle label remains sharp, readable, and consistently visible in every product shot.
Unboxed Item Swap
Genjutsu
プロンプトを表示
Change the Produkt inside the Box too the one from the refrence, remove the text and overlays
A young Korean woman in her early 20s with a natural, everyday appearance.
Seedance 2.0
プロンプトを表示
Main Subject A young Korean woman in her early 20s with a natural, everyday appearance. She wears a faded charcoal-grey sleeveless crop top with soft, slightly worn fabric, loose high-waisted light-wash jeans with gentle natural wrinkles, black canvas sneakers showing subtle signs of regular use, and a thin black cord necklace with a tiny metallic pendant. Her black wavy hair is tied into a slightly messy side ponytail with loose wispy bangs framing her face. A few strands constantly escape and move naturally in the breeze. Her skin has realistic texture with visible pores, slight redness around the cheeks, tiny imperfections, and soft highlights from natural sunlight. She wears almost no makeup—only lightly moisturized skin and naturally tinted lips. Her expressions are subtle and genuine rather than exaggerated. She occasionally smiles to herself, reacts naturally to her surroundings, and never performs for the camera. Throughout the entire video, maintain exactly the same identity, clothing, hairstyle, body proportions, accessories, facial features, and personality. Location An authentic Korean residential neighborhood during a peaceful late morning around 10:30 AM. The area consists entirely of quiet narrow concrete alleys lined with modest two-story brick and stucco homes. Small metal gates lead into tiny front courtyards filled with ceramic pots containing peppers, herbs, chrysanthemums, and succulents. Laundry hangs from balconies and rooftop clotheslines, gently moving in the breeze. Utility poles carry dense overhead electrical wires crossing above the streets. Old bicycles lean against concrete walls. Small delivery scooters occasionally pass through the neighborhood. Mature maple and gingko trees create shifting shadows across cracked pavement. The convenience store is a tiny neighborhood shop integrated into the corner of an apartment building, with faded signs, a bicycle rack, a beverage refrigerator near the entrance, and a simple glass storefront. Everything feels lived-in and ordinary. There are no shopping districts, cafés, advertisements dominating the scene, tourists, or busy traffic. The atmosphere is calm, intimate, and unmistakably residential. Visual Style Ultra-realistic documentary realism. Genuine slice-of-life storytelling captured without staging. Every movement feels spontaneous and naturally motivated. Human behavior is subtle and believable rather than cinematic. Clothing folds respond accurately to body motion. Hair reacts realistically to wind. Walking speed is relaxed. Facial expressions are understated. Lighting remains entirely natural with no dramatic enhancement. Rich environmental storytelling comes from ordinary details—faint peeling paint, weathered concrete, slightly faded plants, uneven pavement, and everyday household objects. Nothing appears polished or stylized. Camera Style Recorded entirely on an early-2000s consumer MiniDV camcorder by a friend casually following her around. Heavy handheld shake throughout. Slightly awkward framing with frequent drifting off-center. Autofocus constantly hunts whenever foreground objects enter the frame. Lens breathing becomes noticeable during focus adjustments. Exposure pumps when moving between sunlight and shade. Slight motion blur during quick camera movements. Rolling shutter distortion appears during faster pans. Mild digital compression artifacts, soft contrast, faded colors, slight chromatic aberration, gentle sensor noise, and limited dynamic range create an unmistakable early-2000s home video look. Zoom movements are slow and slightly jerky. No stabilization. No cinematic camera moves. No modern HDR or color grading. 00:00–00:02 Outside her small house entrance, she steps through a narrow metal gate while holding a small brown leather wallet and her phone. She pauses to lock the gate with an old silver key. The camera operator starts recording slightly too early, briefly pointing toward the pavement before lifting the camcorder toward her. Focus hunts between the nearby gate and her face. A light breeze moves loose strands of her ponytail. She notices the camera, gives a small amused smile, then begins walking toward the alley. 00:02–00:04 The camera follows from several steps behind as she walks through the narrow residential alley. Potted plants line both sides of the path. Laundry sways overhead between neighboring houses. She steps aside to allow an elderly man riding a bicycle to pass. She politely bows her head with a quiet smile before continuing. The handheld camera struggles to keep her centered, occasionally framing more of the surrounding walls than her body. Shadows from nearby trees move gently across the pavement. 00:04–00:06 She reaches the small neighborhood convenience store. The glass refrigerator door reflects sunlight as she opens it. The autofocus repeatedly shifts between the reflections on the glass and her face. She scans the shelves briefly before selecting a chilled canned coffee. The refrigerator light casts a cool glow on her face. She quietly closes the door with a soft metallic click. 00:06–00:08 Standing near the entrance, she pays the cashier in cash. Their conversation is barely audible and completely casual. She receives a few coins and a receipt, placing both into her wallet. The camera momentarily loses focus as another customer walks across the foreground. Exposure brightens slightly when the entrance door opens behind her. 00:08–00:10 Outside the store, she opens the coffee can with a crisp metallic pop. She takes a slow sip while standing beneath a utility pole. Morning sunlight filters through nearby leaves, creating constantly shifting patches of light across her face and shoulders. She quietly watches two neighborhood children riding bicycles farther down the alley. She smiles naturally without acknowledging the camera. 00:10–00:12 Continuing home, she walks at an easy pace through another quiet residential lane. A small orange stray cat appears from beneath a parked scooter and briefly rubs against her leg. She crouches naturally to pet it with one hand while balancing the coffee can in the other. Autofocus repeatedly switches between the cat and her face. The camera operator steps closer, causing slight lens breathing and imperfect framing. 00:12–00:15 She stands again and resumes walking toward home. After several steps, she casually glances back toward the camcorder and gives a small genuine smile that lasts only a moment before looking ahead again. The camera slightly lags behind as if the operator stumbled while walking. The framing drifts toward the pavement before quickly correcting. Just as she reaches her front gate, the recording abruptly cuts to black mid-step, as though the camcorder was switched off without warning. Audio Natural ambient sound only. Morning birds singing from nearby trees. Soft wind moving through leaves. Distant scooter engines. Occasional bicycle bells. Quiet neighborhood conversation drifting from open windows. Footsteps on concrete. The metallic sound of a gate lock. Refrigerator humming inside the convenience store. The click of the refrigerator door. Cash register beeps. Coins lightly clinking. The crisp opening of a coffee can. Faint rustling of laundry hanging on clotheslines. A cat meowing softly. No music. No narration. No sound effects. No cinematic enhancement. Goal Create the feeling of discovering a forgotten MiniDV home video recorded sometime around 2003–2005 in a quiet Korean neighborhood. Every moment should feel candid, imperfect, warm, nostalgic, and completely believable—as if a friend casually documented an ordinary morning with no intention of making a film. The realism should be so convincing that viewers question whether it is genuine archival footage rather than AI-generated.
second cinematic POV video. Nighttime in a dark outdoor area. A bright
Seedance 2.0
プロンプトを表示
10-second cinematic POV video. Nighttime in a dark outdoor area. A bright flashlight beam slowly scans the ground and stops on a small brown plastic bucket with a tightly closed lid sitting on a dirt path surrounded by short grass. The camera slowly walks closer with subtle handheld movement, creating suspense. A human hand reaches down and lifts the lid. Inside the bucket is a cute fluffy white-and-orange kitten sitting upright, looking directly at the camera with big sparkling eyes. The kitten slowly raises one paw and gives a clear 👍 thumbs-up gesture while smiling adorably. Hold a close-up on the kitten for a moment. Audio: Quiet nighttime ambience with crickets and soft suspenseful music during the approach. As soon as the kitten gives the thumbs-up, the music turns cheerful and a natural voice enthusiastically says, "Wow, wonderful!" synchronized exactly with the thumbs-up gesture. Ultra-realistic, cinematic lighting, detailed fur, expressive eyes, realistic paw movement, shallow depth of field, smooth camera motion, highly believable, no subtitles, no text, no watermark.
Main subject from @ image1 lock her completely. Face, hairstyle, body
Seedance 2.0
プロンプトを表示
15 seconds, 16:9. Main subject from @ image1 — lock her completely. Face, hairstyle, body proportions, skin tone, outfit, accessories, and overall appearance must remain perfectly identical throughout the entire video. She is a sweet and naturally beautiful Indonesian girl, 18 years old, soft warm tan skin, expressive dark brown eyes, long black hair tied into a casual messy bun with loose bangs, youthful smile, minimal makeup, wearing a simple white oversized T-shirt, light blue denim jeans, white sneakers, and carrying a vintage brown canvas camera bag. Around her neck hangs a classic 35mm analog film camera. Theme: "A Day With My Camera" A relaxing weekend in 2026, following a girl who loves documenting ordinary moments with her analog camera. The video should feel authentic, nostalgic, and effortlessly beautiful. Everything takes place around modern Indonesia in 2026: quiet neighborhood streets, small coffee shops, city parks, bookstores, pedestrian sidewalks, and cozy residential areas. The entire video must look like it was filmed naturally by her best friend using a modern mirrorless camera. Absolutely no posing, no influencer behavior, no scripted acting. Every smile, glance, and movement feels spontaneous and real. Camera language is the highest priority. Natural handheld movement. Gentle camera sway. Occasional focus breathing. Real autofocus adjustments. Slight framing imperfections. Natural motion blur. Documentary-style tracking shots. Soft depth of field. Authentic available sunlight. Premium lifestyle vlog aesthetic. Sequence: She walks out of her house while adjusting the analog camera hanging around her neck, smiling softly as morning sunlight lights up her face. She stops beside a quiet street and photographs flowers, bicycles, passing people, and little everyday details with genuine curiosity. She enters a cozy camera store, happily choosing a fresh roll of 35mm film before carefully loading it into her camera. Walking through the city, she photographs random candid moments: children playing, street cats, trees moving in the breeze, reflections on café windows, and interesting architecture. She sits alone inside a cozy café reviewing her newly taken photos, smiling while enjoying an iced latte. Golden hour arrives. She slowly walks through a city park while continuing to shoot photographs, warm sunlight creating beautiful natural lens flares. She notices the person filming her, laughs shyly, lifts her analog camera toward the lens as if taking one final photo of the viewer. The camera gently lowers while she keeps smiling naturally. Recording suddenly cuts off mid-motion like a real weekend vlog ending. Lighting: Bright natural morning sunlight transitioning into warm golden hour. Color: Natural realistic skin tones. Soft warm colors. Subtle filmic contrast. No exaggerated grading. Audio is strictly natural. Birds. Footsteps. Camera shutter clicks. Film advance lever. Coffee shop ambience. Light wind. Distant traffic. People talking naturally. Leaves moving. No music. No narration. No subtitles. No logos. No watermark. Ultra-realistic. Looks exactly like a real lifestyle vlog filmed in 2026.
A photorealistic badminton vlog filmed like a real home video with a DV 16mm
Seedance 2.0
プロンプトを表示
A photorealistic badminton vlog filmed like a real home video with a DV 16mm handheld camcorder. Natural handheld camera shake, soft autofocus, slightly imperfect framing, subtle tape grain, muted colors, realistic indoor lighting, and authentic early-2000s camcorder quality. CHASE, a Korean woman in her 20s with long black hair tied in a ponytail, wearing a modest long-sleeve athletic top, loose black joggers, and white sneakers, walks into a quiet indoor badminton court carrying a racket and sports bag. She smiles naturally at the camera, props it on a bench, performs a few warm-up swings, then plays a short, realistic rally with one partner, making smooth and physically accurate badminton movements. After winning the final point with a clean shot, she laughs, wipes sweat from her forehead with a towel, picks up the camera, gives a thumbs-up, waves warmly, and says, "That was fun! See you next time. Bye!" The video should look completely real, with consistent facial features, natural body movement, accurate racket and shuttlecock physics, no visual glitches, no extra fingers, no duplicated objects, and smooth cinematic realism throughout.
A cinematic live action sequence starting in a dimly lit gritty courtyard. A
Seedance 2.0
プロンプトを表示
A cinematic live action sequence starting in a dimly lit gritty courtyard. A rugged warrior with dirt on his face meticulously grinds a thick wooden staff against a heavy stone wheel. Wood shavings and glowing sparks fly into the camera in extreme slow motion under a single shaft of natural sunlight. Suddenly the scene smash cuts to an explosive nighttime battlefield. A rapid fire cinematic montage of live action samurai warriors engaging in intense high speed sword fights. Massive bursts of practical fire and glowing orange embers explode from their clashing metal blades lighting up the dark foggy environment. Hyper realistic cinematic lighting with glowing particles swirling in the dark. Extreme close ups of the warriors with fierce determined expressions and sweat dripping from their faces. Dynamic sweeping camera movements spinning around the fast paced action. Shot on 35mm film with anamorphic lenses for natural lens flares and deep cinematic bokeh. Flawless photorealistic textures on armor skin and fire. Aspect ratio 16:9. Length 15 seconds. Seedance 2.0. Music prompt a heavy cinematic bass drop transitioning into a high energy orchestral rock hybrid with aggressive string staccatos and tribal war drums.
Style:** Realistic, lifestyle, cinematic UGC
Seedance 2.0
プロンプトを表示
**Style:** Realistic, lifestyle, cinematic UGC **Character:** 22-year-old female influencer **Setting:** Bright summer apartment kitchen with natural morning sunlight. ### **Scene 1 (0-2s)** **Shot:** Close-up of a hand opening the refrigerator. Bright colorful Poppi cans are lined up inside. *Camera:* Handheld POV. **Dialogue (smiling):** > "Wait... why do these make me so happy?" *SFX:* Can clinking. ### **Scene 2 (2-5s)** **Shot:** She grabs a Strawberry Lemon can, slowly turning it toward the camera. Condensation glistens on the can. *Macro shot of water droplets.* **Dialogue:** > "Okay... this one's calling my name." ### **Scene 3 (5-7s)** **Shot:** Slow-motion can crack open. Extreme close-up. Fizz erupts. *ASMR audio.* No dialogue. ### **Scene 4 (7-10s)** **Shot:** She takes a sip while standing by a sunny kitchen window. Camera slowly pushes in. She smiles naturally. **Dialogue:** > "Mmm... that's exactly what I wanted." ### **Scene 5 (10-13s)** **Montage** Quick aesthetic shots: * Can on marble countertop * Pouring Poppi into a glass with ice * Orange slice falling in * Holding the can while walking onto a balcony * Close-up of colorful branding No dialogue. Background music lifts. ### **Scene 6 (13-15s)** **Shot:** She cheers the can toward the camera. Natural laugh. **Dialogue:** > "Tiny moment... instantly better." She takes another sip. **End Frame:** Poppi can centered on screen with condensation. --- # 🎥 Camera Style * iPhone 16 Pro cinematic mode * Mostly handheld * Soft morning sunlight * Warm white balance * Slight lens flares * Shallow depth of field * Smooth slow-motion for the can opening * Premium beverage commercial color grading * Authentic influencer energy --- # 🎵 Background Music Light indie-pop with upbeat summer vibes, keeping the drink-opening sound and fizz crisp and prominent.
Matrix: HARIN vs Smith Clone Army
Seedance 2.0
プロンプトを表示
Matrix: HARIN vs Smith Clone Army Ultra-realistic IMAX cinematic rooftop fight in heavy rain, Matrix-inspired grey-green cyberpunk tone, wet reflective concrete, glass skyscrapers, stormy atmosphere, 35mm film look, no background music — only natural rain, impacts, debris, and wind sounds. HARIN: black leather long coat, black fitted outfit, oval sunglasses. Agent Smith clones: identical black suits, emotionless, hundreds of copies. Scene opens with HARIN flying violently across the rooftop and crashing into a concrete wall, creating cracks, dust, and rain shockwaves. She slowly stands, adjusts sunglasses, calm and focused. Rapid montage of hundreds of Smith clones flooding the rooftop through rain and puddles. Rooftop becomes fully covered by the clone army. Main fight sequence: HARIN launches into ultra-high-speed combat with superhuman martial arts. Flying kicks, spinning attacks, aerial strikes, shockwave punches, bullet-time rain ripples, clones thrown into AC units and off the rooftop. Black lightning motion trails, cinematic motion blur, dynamic aerial camera movement. The clone army overwhelms her, piling into a massive black-suited human mountain. Rain pounds the surface. A glowing white energy begins building from inside the mass. Concrete cracks, rainwater reverses upward, pressure intensifies. HARIN briefly appears through the glowing gap, sunglasses intact, exhales sharply: "하!!" Massive spherical energy explosion erupts outward, launching clones across the rooftop. Concrete tears apart, rain forms a temporary vacuum sphere before crashing back down. Final ultra-wide aerial shot: HARIN standing alone calmly in the destroyed rooftop under heavy rain, coat slowly settling, surrounded by storm and skyscrapers. Constraints: - Single rooftop environment only - No blood or gore - No costume changes - Sunglasses never break - No subtitles or text - No background music - Total duration: 15 seconds
Create a cinematic motion-previs board titled SHADOW RUN
Seedance 2.0
プロンプトを表示
Create a cinematic motion-previs board titled “SHADOW RUN.” Show 8 connected widescreen frames from one continuous 15-second sequence, with small timestamps beneath each frame. Focus on readable poses, camera movement, speed, transformation continuity, and impact. This is a storyboard for a sports-animation film, not a character sheet. Main subject: A simplified faceless freestyle skateboarder wearing a loose pale jacket, wide dark trousers, and riding a matte-black skateboard. The skater should remain clearly human-shaped, but minimal and faceless. No realistic facial anatomy, no detailed identity, no logos, no extra characters, no scene text. Important creature rule: The shadow creature must always be a giant black panther. It must never become a human, humanoid, monster-man, demon, ninja, warrior, or person-shaped figure. The creature must keep clear panther anatomy in every frame where it appears: four legs, feline body, long tail, low predator posture, panther head, ears, paws, claws, and animal movement. The panther is made from charcoal, graphite dust, smoke, and torn-paper fragments. It is not a black human silhouette. Concept: A freestyle skateboarder races through an endless warm-white void. The skateboard wheels leave rough charcoal tracks behind them. These tracks lift from the ground and transform into a giant black panther. At first, the panther appears to chase the skater. By the end, it is revealed as the skater’s animal shadow, moving in perfect sync with the skateboarder. Visual direction: Use dry charcoal, graphite dust, torn-paper fragments, smoky ribbons, hand-drawn speed marks, paper texture, and rough brush motion. Palette: warm white, black, and graphite grey. Add only one small crimson accent in the panther’s eye. Style: experimental sports campaign, manga motion, charcoal animation, stop-motion detail, paper texture, and extreme wide-angle cinematography. Timeline: FRAME 1 — 0:00–0:01.8 Overhead 28mm shot. The skater enters diagonally at high speed and carves a sharp turn, cutting a bold charcoal arc across the white surface. The camera descends toward the skater. Audio: wheel rumble, graphite scrape, restrained beat. FRAME 2 — 0:01.8–0:03.6 Low side-tracking shot. The skater performs a high ollie as the charcoal trail tears from the ground like a black ribbon. The trail is still abstract and not yet a creature. Audio: board pop, rushing air, beat locking in. FRAME 3 — 0:03.6–0:05.4 Rear chase shot. The skater lands and accelerates. The floating charcoal trail splits into four animal limbs, like the early structure of a panther. The limbs strike the ground and throw graphite dust outward. The shape should clearly suggest a four-legged feline forming, not a person. Audio: heavy landing, claw scratches, rising bass. FRAME 4 — 0:05.4–0:07.2 Fast circular camera orbit. The skater spins while the forming panther runs around them in the opposite direction. The creature has a clear animal body, long tail, low shoulders, and four running legs. Charcoal and torn-paper fragments spiral around them. Audio: spinning board, layered scratches, building tension. FRAME 5 — 0:07.2–0:09.0 Frontal tracking shot moving backward. The skater charges toward the lens while the fully formed giant black panther runs beside them. The panther is clearly an animal: four legs, feline head, tail, paws, claws, and predator stride. Their movements synchronize. The panther’s small crimson eye opens. Audio: rapid wheel impacts, heavy footfalls, intensified beat. FRAME 6 — 0:09.0–0:11.0 Under-board angle. The skater jumps over the camera as the board briefly breaks into graphite fragments. The panther passes under and around the skater like liquid animal-shaped shadow, still keeping its panther body, tail, head, and four legs. Audio: beat drop, low pulse, slicing air, shadow sweep. FRAME 7 — 0:11.0–0:13.0 Ultra-wide slow-motion shot. The skater lands in a low glide while the panther mirrors the motion beside them in a low feline run. Their silhouettes overlap as the panther folds into the skater’s ground shadow. The panther should remain animal-shaped while merging. Do not turn it into a human shadow. Audio: near silence, soft rumble, stretched graphite hiss. FRAME 8 — 0:13.0–0:15.0 Extreme frontal shot. The skater drives toward the camera and performs one final explosive turn. The panther, still clearly a panther, merges completely into the skateboarder’s ground shadow, then erupts into massive charcoal strokes that flood the frame to black. Audio: heavy bass hit, violent charcoal burst, abrupt cutoff.
試せる6つの実用的なプロンプトアイデア
製品ローンチのコンセプト
プロンプト例：ブランドのないスニーカーがミニマルなスタジオに置かれ、小さな雫がソールに当たり、カメラがサイドプロファイルを映し出します。製品を読み取りやすく保ち、ショット全体を通してインパクトと形状を確認してください。
自然の確立ショット
プロンプト例：夜明けの海岸沿いの小道が海に向かって曲がり、カメラはゆっくり前進し、フレーム端近くで草が穏やかに動きます。より多くの環境アクティビティを求める前に、シーンの奥行きとペースを判断してください。
クローズアップアクション
プロンプト例：スプーンがスープのボウルの中を動き、湯気が柔らかく立ち上ります。固定クローズアップ、暖かい光、シンプルな背景を使用してください。接触、液体の挙動、ボウルへの不要な変化を確認しましょう。
参照シーン
プロンプト例：ラウンジの対応画像を使用し、窓に向かって微妙なカメラプッシュを説明し、家具と部屋の形状を安定させます。冒頭だけを確認するのではなく、参照を複数のフレームと比較してください。
サウンドを考慮したブリーフ
プロンプト例：静かなプラットフォームに到着する列車を説明します。オーディオが提供される場合は、穏やかな車輪音と駅の環境音を別々に要求してください。実際の結果を聴き、すべてのモデルやモードがサウンドを生成すると仮定しないでください。
縦型ソーシャルクリップ
プロンプト例：花屋が 1 本の茎を花瓶に挿します。縦向きで撮影し、アレンジを中央に配置し、後でコピーを追加できるよう上に十分なスペースを空けます。編集で見出しを追加する前に、アクション全体と意図するクロップを確認してください。
Veo 3 Video Generator の使用方法
判断できるブリーフを書く
Veo video scene planning から始めましょう。被写体、設定、目的を名付け、ビジュアルアクションとカメラフレーミングを説明し、オーディオの指示は選択したモードが対応している場合にのみ追加してください。
入力とフレーミングを選ぶ
利用可能な動画モデルを選択し、タスクに提供されるコントロールを確認する。その入力がサポートされている場合にのみリファレンスを使用する。結果が表示される場所に合わせてフレーミングを選択し、後で追加するクロップやテキストのスペースを残す。
見積もりを確認して送信する
モデルと出力設定を選んだ後、現在のクレジット見積もりを確認しましょう。ブリーフと選択したコントロールを保存して、後で試行を比較できるようにします。入力が計画に合致したらタスクを送信し、同じリクエストを繰り返し送信せずにステータスを待ちましょう。
確認、調整、ダウンロード
完成した結果を History または Assets で開き、クリップのフレーミング、動き、実際に返されたオーディオを確認しましょう。クリップ全体を視聴し、始まり、中間、終わりを比較してください。
利用可能な動画モデルとクレジット見積もり
ジェネレーターに表示される実際のモデルラベルとコントロールを使用しましょう。ここでの焦点は Veo video scene planning です。入力対応、出力オプション、クレジットコストは選択によって異なります。入力が許す場合は、同じブリーフでモデルを比較してください。
- Veo 3.1
- Veo 3.1 Fast
- Veo 3.1 Lite
- Kling 2.1 Master
- Kling 2.6 Motion Control
- Kling 3.0 Motion Control
- Kling V3 Turbo
- Seedance 2.5
- Kling 3.0 Pro
- Kling 2.6 Pro
- Kling 2.5 Turbo Pro
- Wan 2.2 A14B Turbo
- Seedance 2.0
- Seedance 2.0 Fast
- Seedance 1.5 Pro
- Wan 2.6
- Wan 2.5
- Grok Imagine Video 1.5
- Hailuo 02 Standard
- Hailuo 02 Pro
- Hailuo 2 3 Pro
- Hailuo 2 3 Standard
- Wan 2.7
- MiniMax H3
- Google Gemini Omni Flash 1 1
- Kling 2.1 Pro
- Kling 2.1 Standard
- Seedance 2.0 Mini
すべてのクレジットでもっと作成
付属クレジットで始め、プランを比較し、必要なときにいつでもクレジットを追加できます。
価格を読み込み中…
アカウントなしで作成する
作成を開始する →- サインアップは必要ありません。生成にはクレジットを使用します。
- 対象となる 1 回限りのクレジット パックは、サインアップなしでご利用いただけます。サブスクリプションおよびサブスクリプション専用パックにはサインインが必要です。
- ゲストのクレジットと履歴はこのブラウザにリンクされています。 Cookie を有効にしておきます。
- 10 ログインによる無料クレジット
- 購入なしで公開例を閲覧できます。
安全なチェックアウトが利用可能です。 お問い合わせやサポートについては、こちらまでご連絡ください support@canvasseed.com.
Veo 3 Video Generator に関する質問
アカウントを作成せずに生成できますか？
はい。サインアップは不要です。生成にはクレジットを使用します。送信前に見積もりと残高を確認しましょう。ゲストクレジットと履歴はこのブラウザに紐づけられるため、Cookieを有効にしておきましょう。チェックアウトが利用可能な場合は、対象となる買い切りのクレジットパックを購入できます。サブスクリプションにはサインインが必要です。
Veo 3 video generator で何を作成できますか？
CanvasSeed を使用して Veo シーン計画を探りましょう。意図するタスクに対応するモデルを選択し、生成前に現在の入力オプションを確認してください。Veo video scene planning から始めましょう。
動画プロンプトはどのように書けばよいですか？
具体的な被写体、設定、ビジュアルの方向性から始めましょう。プロンプトのアイデア：ブランドロゴのないスニーカーがミニマルなスタジオに置かれ、小さな水滴がソールに当たり、カメラがサイドプロファイルを映し出します。製品を読み取りやすく保ち、ショット全体を通して衝撃と形状を確認しましょう。フレーミングと再生時間は、モデルに対して実際に表示されるオプションから選択してください。これは出発点となるブリーフとして扱いましょう：自分のプロジェクトに合わせて詳細を調整し、結果を確認した後に1つの指示を変更してください。
リファレンス画像から始められますか？
画像入力をサポートするワークフローを選択する。希望するアクションとカメラモーションを記述し、元の被写体への変化がないか出力を確認する。
クレジットはどのように計算されますか？
生成ツールは選択したモデルと設定の見積もりを表示します。送信前にその見積もりを確認しましょう。選択を変えるとコストが変わることがあります。
公開されている事例はどのモデルで作成されましたか？
各事例の実際のモデルラベルが使用されたモデルを示しています。事例は、新しいタスクで選択するモデルとは異なるモデルを使用している場合があります。
モデルが利用不可の場合はどうすればよいですか？
タスク用に現在表示されているモデルを使用するか、利用可否についてサポートに問い合わせてください。ページの見出しや公開されている事例は、現在そのモデルを選択できることを保証するものではありません。