Tutorial Video

3D printer layer by layer constructing a detailed miniature building, time-lapse style, warm workshop lighting, shallow depth of field focusing on the print head

Create a 5-second cinematic route-guide clip for a walking navigation video. Continuity: This is scene {N} of 5 in a route from North Avenue MARTA Station to Coda Tech Square in Atlanta. The guide is the same stylish female tour guide in every scene: black sunglasses, sleeveless cream belted dress, brown leather belt, tour lanyard, small shoulder bag, brown hair tied back, confident warm expression. She appears on the sidewalk or plaza only, never in traffic lanes. Scene role: {route_step} Starting frame: Use the supplied Street View image as the real-world location reference. Preserve the recognizable street layout, building massing, sidewalk direction, signage, and lighting. Action: The guide is already in frame, slightly ahead of the viewer. She turns toward the camera, gestures toward the next walking direction, then begins to lead the viewer forward. Camera: Smooth handheld walking pace, slight forward push-in, no jumpy zooms, no orbit. Keep horizon stable. The final second should frame the direction of the next scene so the edit can cut naturally. End frame: End with the camera facing {next_direction_or_landmark}, with the guide near the edge of frame pointing forward. Restrictions: Do not invent a different city, indoor location, parking lot, or tourist group. Do not place the guide in the road. Do not block crosswalks, street signs, building entrances, or the Coda facade.

授人与鱼不如授人以渔，大佬们发精彩视频发得热闹，他们也公布提示词给大家看，但是他们从来不给你讲这个提示词是怎么写出来的，今天开始我抛砖引玉慢慢给大家讲我自己在制作Seedance 2.0 视频的时候提示词的写作方法，手把手以案例来分析如何来控制角色的行为和画面调度。今天发个长达1分钟的长视频，给大家讲讲制作过程，其中用到不同的Seedance视频制作方法这个视频的前面小节红衣女郎弹吉他是向疯狂的MAX中的金典镜头致敬，这段镜头是用9宫格来制作的，后面的是全局参考用提示词加角色融入制作的， 内容太长估计一段话聊不完，我们把后面的内容结合这个视频的制作流程放在回帖里慢慢讲解。 先聊9宫格吧，九宫格的提示词大家应该都知道，原作者是大佬@techhalla 我在他的提示词基础之上自己改了一个可以生成故事情节分镜的3x3格提示词，这个提示词的优点是非常完美的保留了参考图的画质和惊人的镜头语言，既有大场面也有细节描写，当然也方便各位大佬自己在上面针对自己需要的情节调整，而且这个提示词是万能场景应用，既可以做大场景也可以做角色，这个9宫格的提示词内容如下：<role> You are an award-winning trailer director + cinematographer + storyboard artist. Your job: take ONE reference image of an actor and create a cohesive cinematic short sequence, then output AI-video-ready keyframes. </role> 色调参考图2 <input> User provides: one reference image (image). Scene Brief: {{scene_brief}} </input> <goal> Create a 10–20 second cinematic scene with a clear theme and emotional progression (setup → build → turn → payoff) using the actor, you are allowed to add other actors in the scene if the scene needs it. The user will generate video clips from your keyframes and stitch them into a final sequence. </goal> <steps> 1. a Keyframe List: 9 frames (later assembled into ONE master grid). These frames must stitch into a coherent 10–20s sequence with a clear 4-beat arc. Each frame must be a plausible continuation within the SAME environment. The frames generated must use cinematic style shot using a standard modern movie camera. 2. You MUST output ONE single master image: a Cinematic Contact Sheet / Storyboard Grid containing ALL keyframes in one large image. - Default grid: 3x3. </steps>

Seedance 2.0 Text-to-Video Prompt [Style] Pseudo-documentary (Vlog Style), hyperrealism, fixed camera position with realistic footage feel, natural lighting, with a touch of suspenseful comedy. [Duration] 15 seconds [Protagonist] An ordinary young woman, in front of her bathroom sink at home. [00:00-00:06] Shot 1: Daily Setup (Normalcy). Scene: In front of an ordinary bathroom mirror. Action: The protagonist is brushing her teeth facing the mirror, mouth full of foam. While brushing, she makes various silly faces at the mirror (squinting and grimacing). Key Detail: At this point, the reflection in the mirror is completely normal, movements are synchronized. [00:06-00:11] Shot 2: The Glitch Appears (The Glitch). Action: The protagonist finishes brushing, leans down to spit out the foam, then turns to leave the bathroom. High-Impact Moment (Core Reveal): Just as the protagonist's real body has turned away and left the mirror's frame, the "reflection" in the mirror doesn't move! The "reflection" still maintains the tooth-brushing pose, even smirks mischievously and raises an eyebrow at the camera, staying for a full 2 seconds before suddenly panicking and "fast-forwarding" to catch up with the real body's movements before disappearing. Director's Note: Must create an extremely realistic "network lag" feeling, giving the reflection a sense of independent consciousness. [00:11-00:15] Shot 3: Comedy Twist (The Punchline). Action: The protagonist, who has already reached the door, seems to sense something is wrong and suddenly turns back to look at the mirror. Result: The mirror has now completely returned to normal, empty, only reflecting the opposite wall. The protagonist looks completely bewildered, scratches her head, and shows a "questioning life" expression to the camera. The frame freezes on the protagonist's confused face (comedic effect).

{ "video_prompt": { "duration": "15 seconds", "title": "Blueprint to Reality – Single-Story House Transformation", "style": "Architectural visualization, photoreal, modern farmhouse exterior, clean cinematic motion", "blueprint_reference": { "floors": 1, "footprint_shape": "Irregular L-plus-T shape", "layout_zones": { "top_left": "Master bedroom with large en-suite (double vanity, bathtub, shower, toilet)", "top_center": "Open lounge / sitting area with plants", "top_right": "Secondary bedroom + full bathroom", "center_left": "Walk-in closet / laundry adjacent to master bath", "center": "Open-plan kitchen with island, connected to dining room", "center_right": "Family room / playroom with colorful seating", "right": "Covered outdoor terrace / patio (open to sky)", "bottom_center": "Entry foyer leading to interior", "bottom_left": "Double attached garage (2-car, open indoor space, roofed)", "bottom_right_upper": "Bedroom 3 with shared bathroom", "bottom_right_lower": "Bedroom 4 with small private patio (open to sky)", "bottom_right_corner": "Small outdoor lounge / garden corner (open to sky)" } }, "roof_rules": { "all_interior_rooms": "Fully covered with roof — master bedroom, all secondary bedrooms, bathrooms, kitchen, dining, family room, lounge, garage, foyer, hallways", "outdoor_spaces": "Open to sky — right-side terrace, bottom-right small patio, garden corner", "garage": "Roofed as part of main structure, no skylight" }, "exterior_style_reference": { "roof_type": "Standing seam dark charcoal / black metal roof, low-to-mid pitch", "facade": "Light beige / warm white board-and-batten vertical siding", "trim": "Dark brown / black window frames and fascia", "garage_door": "Dark modern panel garage door, double-wide", "covered_porch": "Covered front entry and right-side patio with exposed wood beam columns", "windows": "Large black-framed rectangular windows matching each room's position" }, "sequence": [ { "time": "0:00–0:02", "action": "Clean white background. Crisp 2D top-down colored floor plan appears — exact layout with all rooms labeled, walls in bold black, rooms color-coded in warm wood tones and blue for bathrooms, gray for garage." }, { "time": "0:02–0:05", "action": "Camera slowly pulls back. Floor plan glows softly. Thin white grid lines appear beneath the plan, establishing ground plane. Room walls begin to gently pulse, ready to rise." }, { "time": "0:05–0:09", "action": "Walls begin extruding upward from the 2D plan — all interior walls rise simultaneously, preserving exact footprint. Garage walls, bedroom walls, k

男孩子在房间里认真组装乐高积木，画面采用3D动画风格，色彩鲜艳，线条流畅，充满童趣和活力，加入延时摄影效果展示组装过程。 0-3秒：房间全景，阳光透过窗户洒在桌面上，男孩子坐在桌前专注地组装乐高积木，表情认真，镜头缓慢推近 3-6秒：延时摄影效果展示男孩子快速拼接乐高积木的动作，积木块在他手中逐渐成型，镜头切换到不同角度 6-9秒：手部特写，展示男孩子熟练地拼接乐高积木的细节，手指灵活地操作积木块，镜头跟随手部动作移动 9-12秒：延时摄影效果继续展示组装过程，积木作品逐渐变得完整，男孩子的表情从专注到满意 12-15秒：男孩子抬起头，露出满意的笑容，镜头拉远展示他已经完成的乐高作品。

The main subject enters the frame, first sprinkles salt lightly into the flour and then stirs it evenly by hand, then pours in an appropriate amount of water, cracks an egg into it, and starts kneading the dough.

human evolution over time a chronological hyper lapse video seamless transitions

Image Prompt: A colored pencil sketch style choreography sheet infographic for an urban street dance solo performance. Layout: 16 steps arranged in a clean 4x4 grid, each panel showing a different breakdance-inspired move. Subject: a teenage Asian girl with long wavy hair, wearing effortless urban streetwear with stylish layered details (oversized washed black hoodie, loose cargo jogger pants, fitted inner top, chunky sneakers with muted grey, soft lavender, and faded blue accents, silver chain accessories, fingerless gloves). Style: hand-drawn colored pencil illustration, soft shading, visible pencil texture, slightly sketchy but clean lines, muted urban tones blended with subtle pastel accents and dark outfit contrast. Movement: each frame shows dynamic breakdance motions and freestyle street dance energy (toprock, footwork, spins, freezes, slides, shoulder drops, groove transitions, power poses), with small arrows indicating movement direction, momentum, and flow. Design: modern urban dance aesthetic, minimal and stylish infographic layout, subtle graffiti-inspired visual accents, step numbers (1–16), short captions under each frame. Text: Title at the top — “URBAN STREET BREAKDANCE – 16 COUNTS – 10 SECONDS – FREESTYLE FLOW”. Environment: simple industrial dance studio background with concrete textures, soft cinematic lighting, minimal shadows. Quality: high detail, sharp composition, balanced layout, editorial dance tutorial poster, stylish choreography reference sheet. Negative prompt: blurry, low quality, extra limbs, distorted anatomy, bad proportions, messy layout, overcrowded design, text errors, watermark.

可愛らしいふっくらとした赤いトマトのキャラクターが、カメラに向かって直接話しかけている。完璧なリップシンクで「みんな、僕たちトマトを冷蔵庫に入れてない？実はそれ、NGなんだ！寒さで甘みが飛んじゃうから、常温で保存してね！食べる直前に少し冷やすのが一番美味しいよ！」と元気な声で喋っている。言葉のテンポに合わせて少し弾むような動きをする。ピクサー風の高品質な3Dアニメーションスタイル。背景は少しぼけたキッチン。

ウェブ検索機能を使い、1969年7月20日という日付に関連する世界的に有名で前向きな歴史ニュースを特定してください。 その内容を、昭和後期の日本のニュース放送のような形式で発表してください。 語り手は、厳粛で希望に満ちた歴史的なトーンで、まるで当時の国際ニュースを伝えるヴィンテージのニュース放送のように、出来事を分かりやすく説明します。 字幕は表示しないこと。 テロップも表示しないこと。 画面上に文字は一切表示しないこと。

Anime style, Makoto Shinkai, cozy kitchen, warm sunlight through window, copper pots on shelves. Side and top-down camera alternating. Final reference: green matcha roll cake with pink strawberry cream filling, topped with grapes, watermelon slice, pearl beads, held on white plate. Strict sequence: Eggs cracked into bowl — whisk beats with sugar until pale and fluffy, ribbons form. Matcha powder and flour sifted over egg mixture — green cloud settles, folded gently with spatula. Warm milk and butter poured in — folded until smooth vivid green batter. Batter poured onto flat baking sheet lined with parchment — spread evenly thin with spatula. Sheet placed in oven — warm glow, timer set. Sponge removed — thin green sheet, springy surface. Placed on clean parchment, rolled loosely while warm — sets the shape. Unrolled gently. Strawberries sliced on board — thin even pieces. Heavy cream whipped in bowl — pink food coloring added, whipped to stiff peaks, pink cream formed. Pink cream spread generously across entire green sponge surface — spatula smooth strokes. Strawberry slices laid in even row across cream. Sponge rolled tightly from one end — both hands roll firmly and evenly, parchment guides the roll. Rolled cake wrapped in parchment, refrigerated — hands press ends flat. Roll unwrapped — placed on white plate. Pink mirror glaze poured over top — glossy pink coat drips down sides. Green grapes placed on top center. Watermelon slice wedge placed beside grapes. Pearl beads placed around base. Hands lift plate toward window — sunlight catches glaze. Sounds only: whisk, batter spread, oven hum, cream whipping, rolling, glaze pour. 15 seconds. Gentle flowing pacing.