規劃 Veo 影片場景
從 Veo 影片場景規劃與具體的視覺目標開始。描述視覺動作與攝影機取景，僅在所選模式支援時加入音訊指示。
用於場景規劃的 Veo 3 影片生成器
使用 CanvasSeed 的 Veo 3 影片生成器來探索 Veo 場景規劃。將視覺簡報與你的聲音構想分開。僅在所選模型提供音訊控制時使用它們，並檢視產生的短片與聲音。在提交任務前，檢視可用的模型、支援的設定與目前的點數報價。
選擇文字、圖片或支援的影片任務
CanvasSeed 上發布的影片範例
使用已發布的影片庫，將實際結果與其模型標籤和可用提示詞一起研究。觀看動作和鏡頭方向在整個片段中如何發展。本頁的六個提示詞想法是你可以調整的建議簡報，而非這些確切場景已生成的聲明。
Authentic 1980s European documentary on vintage Kodak 16mm
Seedance 2.0
檢視提示
Authentic 1980s European documentary on vintage Kodak 16mm. 0–4s: A slim beautiful Scandinavian woman sits alone beside the window inside an old overnight train crossing the Alps. Rain softly hits the glass while distant mountain villages pass outside. 4–9s: A middle-aged passenger across the aisle quietly smiles and says, "Long trip?" She laughs softly and replies, "Not long enough." 9–15s: The train stops at a tiny snowy station. She steps onto the platform, buys a hot coffee from an old vendor, thanks him with a smile, then disappears back into the moving train.
Text to video #6
FLUX 3
D Cute Adventure Story A stylized 3D animated fantasy adventure with a cute
Seedance 2.0
檢視提示
D Cute Adventure Story A stylized 3D animated fantasy adventure with a cute brave young explorer, big expressive eyes, small backpack, colorful outfit, magical forest environment, playful cinematic lighting, high-quality 3D animation, charming family-friendly tone, exciting action, clear storytelling, dynamic framing, cute but epic mood, hard cuts only, no fade, no dissolve, no morph transition Shot 1: Wide shot of a cute young adventurer entering an enchanted forest, glowing plants, floating fireflies, curious expression Cut to Shot 2: The hero finds an old treasure map glowing on a stone altar, eyes lighting up with excitement Cut to Shot 3: Medium shot of the hero running through the forest, jumping over roots and ducking under branches Cut to Shot 4: The hero arrives at a mysterious cave hidden behind vines, golden light glowing from inside Cut to Shot 5: Inside the cave, a funny but dangerous witch appears in a swirl of green magic, blocking the treasure chest Cut to Shot 6: Action shot, the hero dodges a magical spell and uses a glowing crystal slingshot or magic charm to fight back Cut to Shot 7: The witch is defeated in a burst of sparkles, her broom spinning away harmlessly Cut to Shot 8: The hero opens the treasure chest and finds a glowing magical gem and piles of gold Cut to Shot 9: Final heroic shot of the cute adventurer holding the treasure proudly at the cave entrance as sunlight breaks through the trees
Create a high-end 4:3 fragrance pitch deck storyboard in 3x4 grid (12
Seedance 2.0
檢視提示
Create a high-end 4:3 fragrance pitch deck storyboard in 3x4 grid (12 frames), editorial layout, Aesop/Byredo style, beige + lavender palette. Structured flow: intro → ritual → transformation → resolution → closure. Each frame split: top cinematic image (no text) + bottom storyboard notes. Minimal European aesthetic, calm femininity, slow living mood. Candle is the emotional center throughout.
Futuristic AI Robot Commercial Storyboard
Seedance 2.0
檢視提示
TITLE: Futuristic AI Robot Commercial Storyboard FORMAT: • Single-page premium storyboard • 3:4 Portrait • Next-generation technology campaign • Editorial presentation • 8 cinematic storyboard scenes HEADER: • Minimal futuristic typography • White, silver & neon blue aesthetic • AI-inspired icons • Information cards • Why This Style Works STORYBOARD: 1. Robot silhouette emerging from darkness 2. AI eyes powering on 3. Precision hand movement 4. Human and robot handshake 5. Robot assisting daily life 6. Smart home interaction 7. Futuristic city sequence 8. Hero robot portrait STYLE: Tesla Optimus × Apple commercial aesthetic, ultra-clean sci-fi design, volumetric lighting, cinematic realism, premium technology branding, glossy white surfaces, Apple keynote presentation, Behance showcase, Hollywood VFX quality, ultra realistic, 8K.
A cozy attic room filled with vintage treasures, old maps, potted plants,
Seedance 2.0
檢視提示
A cozy attic room filled with vintage treasures, old maps, potted plants, fairy lights, and a skylight revealing a breathtaking galaxy-filled night sky, warm and magical atmosphere, Studio Ghibli inspired, highly detailed anime illustration.
A compact submarine racing through the skeletons of enormous ancient
Seedance 2.0
檢視提示
A compact submarine racing through the skeletons of enormous ancient creatures deep beneath the ocean. Giant ribs form narrow tunnels, bioluminescent fish scatter, collapsing bones crash into the path. Camera starts inches above the water. Wide reveal showing endless skeletons disappearing into darkness. Side tracking through rib cages. Frontal shot as a skull fills the frame. Final hero angle surrounded by glowing creatures. Bubbles, particles, blue fog, claustrophobic speed.
The shot opens tight on a beautiful woman face, wind tearing at her coat as
Seedance 2.0
檢視提示
The shot opens tight on a beautiful woman face, wind tearing at her coat as she stands on a jagged cliff. The camera eases over her shoulder and tilts down, following her line of sight. We descend past the crumbling lip into the void, the frame widening to reveal cliffs dropping away. The ocean roars into view, violent surf detonating against rock. The move continues into a high overhead, locking into an aerial top-down that frames the lone figure at the precipice as waves explode below.
photoreal cinematic, 8K, ultra-detailed, high-budget epic fantasy film look.
Seedance 2.0
檢視提示
STYLE: photoreal cinematic, 8K, ultra-detailed, high-budget epic fantasy film look. Natural skin / stone / bark / iron / leaf / cloth textures with pore-and-grain micro-detail, macro texture on grass, soil and dew, real organic film grain, strong motion blur on fast moves, filmic dawn grade. Diegetic SFX only, no music. REFERENCE LEGEND: <<<image_1>>> = dawn grass field below a white-and-gold spired elven citadel on a misty grey mountain, low sun flaring screen-right (img 1) <<<image_2>>> = blonde elven warrior, silver-and-gold leaf-filigree armor, pale-blue cape, elven longsword — appearance reference for the HERO elf only (img 2) <<<image_3>>> = massive dark grey-green orc, battered black-iron plate, tusks, amber eyes (img 3) <<<image_4>>> = forest/plant warrior, carved wooden face, glowing amber eyes, orange flower-petal mane, green leaf mantle, vine-wrapped spear + glowing amber-cored shield (img 4) <<<image_5>>> = STONE warrior — humanoid built from grey moss-flecked boulders, craggy carved face, pale glowing eyes, rope belt, chipped raw-stone sword (img 5) SCENE CONTEXT: an epic large-scale battle of an elven army against an orc horde on the dawn grass field below the white-gold citadel. Told in four cuts: a roaring orc, a continuous FPV-drone dive from the giant battle down to a tiny ground-level battle hidden in the grass, the elven hero swordswoman cutting through orcs, then a grand super-wide of the whole clash. ACTIVE REFERENCES: <<<image_1>>>: green grass field rising to the white-and-gold spired elven citadel on a misty grey mountain, low dawn sun flaring screen-right, drifting haze. 100% matches. <<<image_2>>>: appearance reference for the HERO elf swordswoman ONLY (the one seen close-up in CUT 3) — blonde, silver-and-gold leaf-filigree armor, pale-blue cape, fighting only with an elven SWORD (no bow, no arrows). The rest of the elven army is VARIED — both men and women, different faces, hair colors, builds, armor styles and capes, each elf UNIQUE, NOT copies of <<<image_2>>>. 100% matches for the hero only. <<<image_3>>>: massive grey-green orcs in dark battered black-iron plate, tusks, amber eyes, heavy weapons — each orc UNIQUE. 100% matches. <<<image_4>>>: forest/plant warriors, carved wooden faces with glowing amber eyes, orange flower-petal manes, green leaf mantles, bark skin, vine-wrapped spears and glowing amber-cored shields — each one slightly UNIQUE. 100% matches. <<<image_5>>>: STONE warriors woven from grey moss-flecked boulders, craggy carved faces, pale glowing eyes, rope belts, chipped raw-stone swords — each one slightly UNIQUE. 100% matches. SCALE LOCK: in CUT 2 at ground level the plant and stone warriors are TINY — each about the size of a human palm, miniature soldiers fighting among and half-hidden by towering blades of grass. The elves and orcs are full-size GIANTS by comparison, as tall as four humans stacked head to toe relative to the grass; down low only their massive legs, feet and stomping boots tower above and crash near the tiny armies. FORMAT MODE: SEQUENCE OF CUTS — CUT 1 … CUT 2 … CUT 3 … CUT 4, described in order. Cuts only at the specified points; the camera does not cut on its own. CUT 2 is itself one continuous free-flying FPV-drone take. OPTICS: CUT 1 — 18° tight portrait on the orc, shallow focus. CUT 2 — opens ~84° wide for scale and speed, tightening to ~47° weaving through the fighters, then macro ~18° at ground level among the grass (deep focus high, shallow macro focus low). No drift mid-segment. CUT 3 — 47° neutral medium following the hero elf, shallow-ish focus separating her from the orcs. CUT 4 — 107° architectural ultra-wide, deep focus. CAMERA: CUT 1 — locked tight handheld, eye-level, micro-tremor, holding on the orc's face. CUT 2 — aggressive, weightless, dynamic FPV-drone. Open on a wide SIDE view: a VARIED elven army (men and women) charging from screen-LEFT, orcs charging from screen-RIGHT, the two lines rushing together across <<<image_1>>>, citadel and dawn sun behind. The drone flies fast and low THROUGH the middle of the clash, weaving and banking between colliding elves and orcs, dodging swinging swords, then whips downward and punches between the TALL grass blades to the soil, where out-of-focus grass blades sweep across the foreground and a tiny ground-level battle is half-hidden in the grass. CUT 3 — fluid tracking move orbiting with the elven hero swordswoman, eye-level, following her blade. CUT 4 — slow high crane pull-back revealing the full battlefield, citadel and mountain screen-right-back. ACTION: CUT 1 — extreme tight on <<<image_3>>>: the orc throws its head forward and ROARS in fury, jaw wide over the tusks, amber eyes blazing, neck veins bulging, spit and breath-fog bursting toward camera. CUT 2 — up top the giant armies collide: VARIED elven swordsmen and swordswomen trade blows with orcs across the line, swords ringing. As the drone dives into the grass, a TINY ground-level battle is revealed, half-concealed by towering grass blades — a small army of plant/forest warriors (<<<image_4>>> type) charging from screen-LEFT clashing with a small army of STONE warriors (<<<image_5>>> type) from screen-RIGHT: plant warriors lunging and thrusting vine spears, stone warriors parrying and counter-swinging heavy stone swords, leaves and amber embers scattering, stone chips flaking, while enormous orc and elf feet pound the earth nearby, near-missing them. Tall out-of-focus grass keeps sweeping across the foreground. CUT 3 — <<<image_2>>> the elven hero swordswoman moves through the orc ranks at speed, blade flashing: she parries an orc's heavy chop, spins past it and cuts it down, then drops a second charging orc with a clean diagonal slash, cape streaming. Sword only. CUT 4 — super-wide grand view: the two giant armies fully engaged across the dawn field, hundreds of varied elves and orcs clashing in a massive-scale battle, dust and haze rolling, the white-gold citadel and rising sun screen-right-back. PHYSICS: realistic momentum and weight. Giant footfalls send tremors, bursting dust and dew droplets at macro scale; tall grass blades whip, bend and brush the lens in the drone's wake; stone warriors move with heavy grinding mass, plant warriors fast and agile with weighty organic creak; the hero elf moves light and fluid, cape and braids carrying inertia. Mass has weight, correct contact shadows, no teleporting poses. LIGHTING: cinematic dawn from <<<image_1>>> — warm low backlight and sun flare screen-right, soft mist rolling down the mountain at ~40% density. CUT 1: hard low key on the orc's right side, half the face in shadow. CUT 2: sun glints through the tall wet grass at ground level, giant legs casting moving shadows over the tiny armies, plant warriors' amber glow and stone warriors' pale eye-glow reading against shadowed soil; bright blurred battle bokeh above. CUT 3: warm rim light catching the hero elf's filigree armor and blade. CUT 4: volumetric god-rays through the haze across the whole field. White balance 5000K. COLOR: cold steel-grey orc iron and stone against warm dawn-gold light; the plant warriors' orange petals and amber cores glowing warm; the varied elven armor catching the low sun in silvers, golds and pale blues; green grass deep and wet, soil dark and shadowed. AUDIO (SFX only): CUT 1 — guttural roaring war cry, wet breath. CUT 2 — thundering charge, clashing steel and sword rings, thundering giant footsteps overhead, and down in the grass the massed clashes of tiny weapons, stone grinding, creaking wood, scattering leaves, bursting dew, wind through tall grass. CUT 3 — fast steel clashes, orc grunts, cape snap. CUT 4 — vast roaring battle wash. No music. POSITIVE LOCKS: - Four cuts in order: roaring orc → FPV-drone dive into the grass → hero elf cutting down orcs → grand massive-scale super-wide. Cuts only at the specified points; the camera does not cut on its own. - The elven army is VARIED — men and women, different faces, hair, builds and armor; only the HERO swordswoman in CUT 3 matches <<<image_2>>>. Elves fight only with SWORDS — no bows, no arrows, no archers anywhere. - At ground level it is TWO TINY ARMIES, not a duel: plant/forest warriors (<<<image_4>>> type) on the LEFT versus STONE warriors (<<<image_5>>> type) on the RIGHT, fighting among and half-hidden by towering grass, with tall grass blades across the foreground, while giant orc and elf legs fight and stomp above. - Each orc, each elf, each tiny warrior is unique. Citadel, sun direction, dawn light identical across all cuts. - CUT 4 is a massive-scale battle with hundreds of fighters. Dynamic motion throughout, stable readable picture, no ghosting, no flickering.
Shot on ALEXA 65mm anamorphic lens. Photorealistic cinematic quality. Aspect
Seedance 2.0
檢視提示
Shot on ALEXA 65mm anamorphic lens. Photorealistic cinematic quality. Aspect ratio 2.39:1 widescreen. Teal shadows, warm amber highlights. Film grain. Rain-soaked New York street at night. Neon signs, streetlights reflecting on wet asphalt. Steam rising from manholes. Lens flares, motion blur. Dolby Vision HDR. 0.0s–2.5s: Extreme low-angle tracking shot — a lone female fighter strides down a narrow NYC street, rain pouring heavily. Leather jacket soaked, hair slicked back and dripping. Heels echo faintly on wet pavement. Camera tracks backward with subtle shake. Yellow taxi lights streak across puddles. Figures step out from alleyways and fire escapes, slowly surrounding her. She tilts her head, cracks her knuckles — calm, fearless expression. 2.6s–5.0s: Whip-pan — first attacker lunges. TIME REMAP: slow-motion as she pivots smoothly, dodging and delivering a sharp elbow strike. Water sprays on impact. Her jacket snaps with the motion. Another attacker crashes into a stack of trash bags and metal bins. Sparks flicker from a flickering streetlight overhead. 5.1s–7.5s: Drone shot — overhead view as she moves fluidly through multiple opponents. SLOW MOTION: precise kicks and spins land cleanly, bodies sliding across rain-slick asphalt. Steam swirls under golden streetlights. One attacker swings a bat — she catches it mid-swing, twists, and disarms them effortlessly. 7.6s–10.0s: 360° orbital shot — she leaps into a spinning kick, taking down two attackers at once. Camera circles her as another rushes from behind. Without turning, she blocks and counters instantly. Breath visible in the cold night air. Each strike hits in sync with a rising cinematic score. 10.1s–13.0s: First-person POV — the final opponent charges. SMASH CUT: rapid, close-range exchange in slow motion. Her final punch lands clean. Silence falls. Rain continues to pour. Slow push-in — she stands alone in the empty street, adjusts her jacket sleeve, exhales steadily. Low-angle shot. Eyes locked forward. Unshaken.
Seedance Creator Video 125
Seedance 2.0
檢視提示
{ "Objective": "Generate a clean TikTok dance storyboard in a 16:9 layout with 9 panels, combining minimal skincare-inspired aesthetics with engaging dance movements.", "Persona_Details": { "Main_Character": { "Description": "An adult Japanese woman with striking beauty and a sensual, confident presence", "Wardrobe": "Simple shorts with a minimal, stylish top", "Expression": "Confident, soft, expressive, camera-aware" }, "Target_Audience": "TikTok users interested in dance trends, beauty, and minimalist aesthetics" }, "Visual_Style": { "Lighting": "Soft natural lighting with even exposure and gentle highlights", "Aesthetic": "Clean, minimal, modern smartphone-style visuals", "Color_Palette": "Neutral tones, soft whites, and natural skin tones", "Background": "Plain dance studio background with no distractions" }, "Camera_Style": { "Aspect_Ratio": "16:9", "Framing": "Smartphone-inspired composition with a mix of wide, medium, and close-up shots", "Movement": "Subtle handheld or stabilized movement for an organic TikTok feel" }, "Storyboard_Panels": [ { "Panel": 1, "Shot_Type": "Wide", "Description": "Character centered in studio, neutral pose", "Action": "Pre-dance stance, slight sway" }, { "Panel": 2, "Shot_Type": "Medium", "Description": "Upper body focus", "Action": "Arm wave movement begins" }, { "Panel": 3, "Shot_Type": "Close-up", "Description": "Face and shoulders", "Action": "Soft expression, subtle head movement" }, { "Panel": 4, "Shot_Type": "Medium-wide", "Description": "Torso and hips visible", "Action": "Hip sway synchronized with beat" }, { "Panel": 5, "Shot_Type": "Tracking", "Description": "Slight camera movement", "Action": "Step and turn combination" }, { "Panel": 6, "Shot_Type": "Close-up", "Description": "Hair and face emphasis", "Action": "Hair flip with confident expression" }, { "Panel": 7, "Shot_Type": "Wide", "Description": "Full body in frame", "Action": "Full dance combo sequence" }, { "Panel": 8, "Shot_Type": "Medium", "Description": "Upper body focus", "Action": "Signature TikTok pose and gesture" }, { "Panel": 9, "Shot_Type": "Close-up", "Description": "Final frame", "Action": "Direct eye contact with subtle smile" } ], "Task_Instructions": [ "Ensure smooth transitions between each panel to simulate a TikTok flow", "Maintain a minimal and uncluttered composition", "Keep lighting soft and flattering throughout", "Focus on expressive dance movements and camera engagement", "Preserve a smartphone-style visual authenticity" ], "Response_Format": { "Type": "Storyboard JSON", "Panels": 9, "Aspect_Ratio": "16:9", "Style": "Minimal TikTok dance storyboard" } }
Text to video #5
FLUX 3
六個實用提示詞想法供你嘗試
產品上市構想
提示構想：一雙無品牌運動鞋置於極簡攝影棚中，一滴小水珠落在鞋底，攝影機展現側面輪廓。讓產品保持可辨識；在整段鏡頭中檢視撞擊與形狀。
自然建立場景鏡頭
提示構想：黎明時分，一條海岸小徑彎向大海，攝影機緩慢向前移動，畫面邊緣附近的草輕輕擺動。在要求更多環境活動之前，先判斷場景的深度與節奏。
特寫動作
提示構想：湯匙在碗中攪動湯品，蒸氣輕輕升起。使用固定的特寫、暖光與簡單背景。檢視接觸、液體行為以及碗的任何非預期變化。
參考場景
提示構想：使用支援的休息室圖片，描述攝影機朝窗戶細微推進，讓家具與房間幾何保持穩定。將參考與多個影格比較，而不是只檢查開頭。
具聲音意識的簡報
提示構想：描述一列火車抵達安靜月台。若有提供音訊，分別要求輕柔的車輪噪音與車站環境音。聆聽實際結果；不要假設每個模型或模式都會產生聲音。
直式社群短片
提示構想：一位花店店員將一枝花插入花瓶，以直式拍攝，花藝置中且上方留有足夠空間供後續文案使用。在編輯器中加入標題前，檢查完整動作與預定裁切。
如何使用 Veo 3 影片生成器
寫出你能評判的簡述
從 Veo 影片場景規劃開始。說出主體、場景與目的，然後描述視覺動作與攝影機取景，僅在所選模式支援時加入音訊指示。
選擇輸入與取景
選擇可用的影片模型，並閱讀該任務提供的控制項。僅在支援該輸入時才使用參考。依照成果將出現的位置選擇取景，並為之後要加入的裁切或文字預留空間。
檢視報價並提交
在選擇模型與輸出設定後，檢查目前的點數報價。儲存你的簡述與所選控制項，以便日後比較其他嘗試。當輸入符合你的規劃時提交任務，然後等待其狀態，而非反覆提交同一個請求。
檢視、潤飾並下載
在 History 或 Assets 中開啟完成的結果，並檢視短片的取景、動作以及實際返回的任何音訊。觀看整段短片，並比較其開頭、中段與結尾。
可用的影片模型與點數報價
使用生成器中顯示的實際模型標籤與控制項。這裡的重點是 Veo 影片場景規劃；輸入支援、輸出選項與點數成本仍取決於你的選擇。在輸入允許的情況下，使用相同的簡報比較模型。
- 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
讓每一點數創造更多
以內含點數開始，比較方案，並在需要時隨時加購點數。
正在載入價格…
無需帳戶即可創建
開始創作 →- 無需註冊。生成內容會使用點數。
- 無需註冊即可獲得符合資格的一次性點數包。訂閱和僅限訂閱的包需要登入。
- 訪客點數和歷史記錄連結到此瀏覽器。保持 cookie 啟用。
- 10 登入即享免費點數
- 無需購買即可瀏覽已發布的範例。
安全結帳服務可使用。 如需洽詢或協助，請透過以下方式聯絡我們： support@canvasseed.com.
Veo 3 影片生成器問題
我可以不建立帳號就生成嗎？
可以。無需註冊。生成會使用點數；提交前請檢視報價與你的餘額。訪客點數與歷史記錄會與此瀏覽器綁定，因此請保持 Cookie 啟用。當結帳可用時，你可以購買符合資格的一次性點數包。訂閱則需要登入。
我可以用 Veo 3 影片生成器建立什麼？
使用 CanvasSeed 探索 Veo 場景規劃。選擇支援你預定任務的模型，並在生成前查看其目前的輸入選項。從 Veo 影片場景規劃開始。
我該如何撰寫影片提示詞？
從明確的主體、場景與視覺方向開始。提示詞構想：一雙無品牌運動鞋置於極簡攝影棚中，一滴小水滴落在鞋底，鏡頭帶出側面輪廓。保持產品清晰可辨；在整個鏡頭中檢視撞擊效果與形狀。從該模型實際顯示的選項中選擇取景與時長。將此視為起始簡報：針對你自己的專案調整細節，然後在檢視結果後變更一項指示。
我可以從參考圖像開始嗎？
選擇支援圖像輸入的工作流程。描述你想要的动作與鏡頭運動，然後檢查輸出中原始主體是否有變化。
點數如何計算？
生成器會顯示所選模型與設定的報價。提交前請檢視該報價；變更選擇可能會改變費用。
已發布的範例是由哪個模型建立的？
每個範例的實際模型標籤會指出所使用的模型。範例使用的模型可能與你為新任務所選的模型不同。
如果某個模型無法使用，我該怎麼辦？
使用目前為該任務列出的模型，或就可用性聯絡支援。頁面標題或已發布的範例並不保證現在可以選取某個模型。