Video-prompter for Explainer Tutorial

Create a 30-second ultra-photorealistic cinematic documentary showing the evolution of the universe and life on Earth in one seamless journey. Begin with the Big Bang and the expansion of space, then show matter forming, the first stars, galaxies, supernovae, and the birth of the Solar System and Earth. Transition to volcanic early Earth, cooling oceans, primitive single-celled life, complex marine organisms, life moving onto land, prehistoric forests, dinosaurs, early mammals, primates, hominins, and finally modern Homo sapiens. End with a modern human looking toward the horizon as the camera rapidly pulls back from Earth to the Moon, Solar System, and Milky Way, connecting humanity to the universe. Use continuous cinematic camera movement, seamless transitions through time and scale, realistic physics, scientifically inspired environments, natural motion, detailed animal anatomy, realistic lighting, HDR, and premium documentary cinematography. 16:9, ultra-realistic, photorealistic, emotionally powerful, scientifically grounded. No text, labels, narration, fantasy, cyberpunk, neon, or futuristic elements.

在专业数字绘图和角色设计界面中，创建一个 15 秒的快节奏角色创建延时摄影。 仅将提供的角色参考用作角色外观、比例、服装、发型、颜色和独特特征的最终目标。过程必须从完全空白的画布开始，并从零重建参考角色。 显示一个可见的鼠标光标积极控制整个创建过程。每个主要视觉变化都应感觉是由光标与 UI 的交互引起的。 0:00-0:02 从干净的专业绘图界面中的空白白色或中性画布开始。光标快速创建第一批松散的结构线条、头部形状、身体比例和基本姿势，使用粗略的草图笔触。 0:02-0:05 加速进入详细草图阶段。光标快速定义参考角色的面部、头发、解剖结构、服装轮廓、配饰和特征性特征。使用可信的绘图手势、短促笔触、选区、变换以及偶尔的撤销修正。 0:05-0:08 粗略草图转变为干净的线稿。光标切换工具，调整画笔大小并清理轮廓。不必要的结构线条消失，同时添加精确的面部细节、服装褶皱和小设计元素。 0:08-0:11 快速上色阶段。光标选择区域并用参考中的正确颜色填充角色。显示快速调色板选择、颜色拾取、图层更改、裁剪蒙版和画笔描边。快速连续添加阴影、高光和材质细节。 0:11-0:13 渲染和润色。光标添加最终光照、头发细节、皮肤阴影、织物质感和反射以及小强调细节。短暂放大重要区域，如面部或服装，同时精修它们，然后缩回。 0:13-0:15 界面清除不必要的引导线和面板。完成的角色显示为完全渲染，并与提供的参考紧密匹配。以光标进行最后一次小调整结束，然后停留在干净的完整角色展示上。 风格： 高速数字艺术延时摄影，精炼的专业角色设计工作流程，可信的绘图软件 UI，流畅的光标移动，快速但可读的操作，干净的图层和工具切换，无随机文本，无虚假对话，无无关弹出窗口。 动作： 整个 15 秒应感觉持续高效。避免长时间停顿。将几分钟或几小时的绘图压缩成充满活力的延时摄影，同时保持进程清晰可读：空白画布 → 粗略草图 → 干净线稿 → 扁平颜色 → 阴影 → 精炼最终角色。 镜头： 主要采用屏幕录制风格，带有细微的数字缩放和平移，跟随光标和活跃绘图区域。保持 UI 稳定且可读。不要在软件界面外使用电影式剪辑。 重要： 角色不得瞬间出现或通过单一神奇变换实现。每个阶段都应通过光标驱动的绘图、编辑、上色和渲染操作可见地建立在之前的基础上。

Create a 9-second stylized food animation showing the step-by-step preparation of Filipino Pinakbet in a wok over a gas stove: sauté garlic and red onion, add tomatoes, stir in purple shrimp paste (bagoong alamang), then add long beans, squash, and eggplant, finishing with bitter melon on top. Show realistic sizzling, steam, bubbling broth, colorful fresh vegetables, smooth hand movements, warm kitchen lighting, and appetizing cinematic close-ups.

Create an ultra-realistic cinematic 15-second vertical 9:16 video demonstrating real-world physics through one continuous, believable sequence. Scene: a young woman walks along a riverside carrying a small ball and approaches a wooden boat floating near the shore during golden hour. From 0–3 seconds, she walks naturally toward the boat; her footsteps demonstrate gravity, weight, friction, balance, inertia, and realistic acceleration and deceleration. Loose hair and clothing react naturally to wind and air resistance. From 3–6 seconds, she gently pushes the boat into the water and steps inside. The boat moves backward as a realistic reaction to her push, demonstrating Newton’s third law and conservation of momentum. Her body shifts slightly because of inertia as the boat accelerates, while friction and water drag gradually reduce the boat’s motion. From 6–9 seconds, she drops the ball inside the boat; gravity causes it to fall with realistic acceleration, bounce once according to its elasticity and collision physics, and settle because of friction. From 9–12 seconds, she throws the ball forward; the ball follows a realistic curved trajectory under gravity and air resistance while the moving boat continues forward because of momentum. The ball lands on the water, creating a realistic splash, ripples, displacement, surface tension, buoyancy, and fluid-dynamic interaction. From 12–15 seconds, the boat continues gliding naturally, creating a realistic wake behind it as water resistance and drag gradually reduce its speed. Throughout the entire video, accurately simulate Newton’s three laws, gravity, inertia, momentum, conservation of momentum, conservation of energy, friction, acceleration, deceleration, collision forces, elasticity, mass, weight, air resistance, drag, buoyancy, pressure, surface tension, fluid dynamics, displacement, and realistic cause-and-effect interactions. Every movement must have believable physical consequences and correct timing. Objects must maintain consistent mass, scale, position, texture, and physical properties from frame to frame. Use realistic water reflections, shadows, wind movement, natural motion blur, physically accurate lighting, photorealistic materials, cinematic depth of field, smooth camera movement, and professional film quality. No impossible movement, no floating objects, no teleportation, no sudden unexplained acceleration, no object clipping, no distorted anatomy, no duplicated objects, and no violation of realistic physics. Total duration exactly 15 seconds.

Can you make a video of liquid nitrogen underneath hot lava and show what happens scientifically.

A aesthetic, warm, first-person POV cooking scene featuring a young woman preparing Japanese Omurice: Prep: Close-up of raw eggs cracked into a white bowl, followed by a cube of butter melting in a hot cast-iron skillet.
 Whisking & Interaction: A young woman with blonde hair and a light blue oversized hoodie whisking eggs with chopsticks in a modern white-tiled kitchen. A hand gently tucks a strand of hair behind her ear as she looks up and smiles.
 Cooking: She pours the eggs into the pan, swirling to form a smooth, soft omelet, then carefully places it over a molded bed of fried rice.
 The Reveal: A knife slice opens the omelet down the middle, revealing a runny, soft-scrambled interior drizzled with ketchup as she smiles next to the finished plate.

30秒、16:9横長。日本の大手不動産会社の物件紹介を思わせる、上質で落ち着いた架空の平屋住宅案内動画を制作する。実写の建築映像と自然な日本語の女性案内、控えめなBGM、読みやすい日本語テロップを組み合わせる。 【参照画像】 画像1：案内役の顔・髪型・衣装の基準。同一人物の複数ビューであり、画面に複数人を出さない。この人物資料自体は動画に映さない。 画像2：玄関前でのお迎え。 画像3：玄関収納と廊下。 画像4：LDK。 画像5：キッチンから庭への眺め。 画像6：主寝室とウォークインクローゼット。 画像7：庭側の外観。 【人物と住宅の一貫性】 案内役は画像1と同じ27歳の日本人女性。ネイビーのパンツスーツ、アイボリーのブラウス、パールのピアス、低い位置でまとめた髪。知的で親しみのある笑顔、丁寧で控えめな所作。屋外は黒いパンプス、室内はベージュのスリッパ。全編で顔、体格、衣装、声を統一する。 住宅は参照画像と同じ平屋。白い壁、明るいオーク材、落ち着いた家具、黒い窓枠。各カットの背景は対応する画像を優先し、窓、扉、家具、間取りを勝手に変更しない。 【映像の演出】 高級住宅紹介のように、自然な明るさ、柔らかな窓光、繊細な素材感、抑制された色調で仕上げる。直線が歪まない建築撮影。カメラはゆっくり前進、または短い横移動に限定する。 場所の移動は編集のカットで表現する。壁や扉を通り抜けるカメラ移動、部屋同士の変形による場面転換はしない。女性はその場で小さく身振りをする程度とし、複雑な歩行や扉の開閉は行わない。 【30秒の構成】 0.0〜4.5秒｜玄関前のお迎え 画像2を基準に、家と女性が一緒に見えるワイドショットから緩やかに近づく。 女性はカメラに微笑み、玄関へそっと手を向ける。 女性の台詞： 「木のぬくもりを感じる平屋へ、ようこそ。」 テロップ： 「木のぬくもりと暮らす平屋」 4.5〜8.5秒｜玄関収納 画像3へカット。玄関収納と廊下が分かる構図を保つ。 女性が収納へ自然に手のひらを向ける。カメラはわずかに横移動。 女性の台詞： 「玄関には、すっきり収まる収納を。」 テロップ： 「玄関収納」 8.5〜14.5秒｜LDK 画像4へカット。ダイニング、キッチン、リビングを広く見せる。 女性はカメラから室内へ視線を移し、小さな身振りで紹介する。 ゆっくりした引きの動きで空間の広がりを伝える。 女性の台詞： 「家族が集まるリビングは、明るく、開放的です。」 テロップ： 「光が広がるリビング」 14.5〜19.5秒｜キッチンと庭 画像5へカット。手前のキッチンから窓越しのウッドデッキまで見せる。 女性は庭へ手を向ける。カメラは少しだけ前進し、庭への見通しを強調する。 女性の台詞： 「キッチンからは、庭まで見渡せます。」 テロップ： 「庭へつながる開放感」 19.5〜25.0秒｜主寝室と収納 画像6へカット。女性、ベッド、開いたウォークインクローゼットを一緒に見せる。 女性が収納を紹介し、最後にカメラへ視線を戻す。 女性の台詞： 「寝室には、ウォークインクローゼットも備えています。」 テロップ： 「主寝室・ウォークインクローゼット」 25.0〜30.0秒｜庭側外観・エンディング 画像7へカット。家全体とウッドデッキを見せる、穏やかな引きのショット。 このカットは人物を追加せず、同じ女性の声をナレーションとして重ねる。 ナレーション： 「心地よい毎日を、この住まいから。」 中央下寄りのテロップ： 「心地よい毎日を、この住まいから。」 最下部に小さく： 「架空の物件紹介イメージ」 最後の約1秒は構図を落ち着かせ、音楽とともに自然に終える。 【声・BGM】 女性の声は、落ち着いた明瞭な標準日本語。自然な接客口調で、急がず、台詞間に短い余韻を残す。 女性が映る場面は台詞と口の動きを合わせる。最後のみ画面外のナレーション。 台詞は指定どおりとし、追加の説明や英語を入れない。 BGMは、柔らかなピアノと薄い弦楽器によるオリジナルのインストゥルメンタル。穏やかなテンポ、上品で温かい雰囲気。全編を通して同じ曲を流し、場面転換で曲をリセットしない。声が常に明瞭に聞こえる音量に抑え、最後に自然にフェードアウトする。歌声、強いビート、派手な効果音は不要。 【テロップ】 指定した短い日本語のみを正確に表示する。通常は画面左下の余白に、読みやすい白のゴシック体と薄い影で配置。画面端から十分な余白を取り、顔、手、紹介する設備を隠さない。 各カットにつき1つ、静かなフェードで出し入れする。台詞全文の字幕は追加しない。 最後のコピーのみ上品な明朝体を使用する。 【制約】 全体を正確に30秒に収める。 人物の入れ替わり、複製、顔の変化、不自然な指、家具との接触や貫通を避ける。 住宅の階数、窓、扉、収納、家具を増減しない。 実在企業の名称・ロゴ、価格、所在地、販売実績、検証されていない面積や性能は表示しない。

Create a clean, child-friendly educational vocabulary poster for preschool/kindergarten children, inspired by a simple visual learning card. Feature [FRUIT] as the main large realistic object on the left, and show a [PART / SLICE / SEGMENT] of the same fruit on the right. Connect the two with a playful dotted curved arrow and a tiny simple stick-figure child pointing toward the smaller part. Add the word “[FRUIT NAME]” in large bold uppercase letters at the top and “[PART NAME]” in large bold uppercase letters underneath the smaller image. Use a soft white and very light pastel-blue background, rounded image panels, clean spacing, realistic fruit photography, simple blue typography, and minimal playful illustrations. The overall design should feel bright, educational, modern, uncluttered, and easy for young children to understand, like a premium preschool vocabulary learning card. Vertical 4:5 composition, high resolution, soft lighting, clear labels, no unnecessary decorations.

Create a 15-second cinematic anime/webtoon cooking video featuring a cheerful young woman with short dark hair, wearing a cream apron over a sage-green shirt, cooking in a bright rustic kitchen with wooden counters, hanging plants, and warm morning sunlight. Scene 1 — 0–3s: Close-up of her spreading garlic butter and pesto onto two slices of crispy toasted sourdough, with smooth, satisfying hand movements. Scene 2 — 3–6s: Medium shot as she happily layers lettuce, juicy tomato, melted cheese, crispy chicken, and avocado onto the toast using wooden tongs. Scene 3 — 6–9s: Close-up of a sunny-side-up egg sliding from a small skillet onto the towering sandwich, followed by her placing the second toast slice on top. Scene 4 — 9–12s: Dynamic close-up as she cuts the sandwich diagonally with a chef’s knife; cheese stretches slightly as she lifts both halves toward the camera, revealing the colorful layers. Scene 5 — 12–15s: Cozy medium close-up as she takes a huge bite, closes her eyes, and smiles with a delighted expression while warm sunlight fills the kitchen. Style: High-quality 2D anime/webtoon aesthetic, expressive character animation, clean line art, soft pastel colors, warm cinematic lighting, cozy atmosphere, detailed food textures, smooth camera movements, appetizing close-ups, natural motion, consistent character design.

Create a polished 12-second educational tutorial video in sleek modern minimalist style that clearly demonstrates exactly two steps for making a luxury product advertisement video on LartAI.\n\nStep 1: Slow push-in camera on a bright clean interface; a glowing cyan prompt box lights up as elegant text types itself letter by letter reading “Describe your luxury product in detail”, soft light particles float around the box.\n\nStep 2: A luminous circular Generate button pulses once and is activated; a thin progress ring fills smoothly, then a high-end crystal perfume bottle appears and slowly rotates under warm golden studio lights with sparkling reflections and gentle light flares.\n\nSmooth cross-dissolve transitions between the two steps, large bold centered text overlays “STEP 1” and “STEP 2”, soft ambient electronic background music, crisp white-and-cyan digital interface, professional instructional look, ultra-sharp 720p or higher, no real people or faces, rich surface details, cinematic depth of field and lighting.

Can you make a video of liquid nitrogen in lava and show what happens scientifically

[Speech rule — read first] The woman speaks JAPANESE ONLY. She never speaks Chinese, English, or any other language. She speaks almost continuously for the whole clip. She says exactly this one sentence, broken into four phrases, in this order and nothing else: 「Seedance 2.5なら」 「黒板に日本語の文字を」 「書くことができます。」 「とても便利ですね」 She delivers it at the unhurried pace of a teacher writing on a board: her voice slows to the speed of her own chalk, so each phrase is spoken while her hand is forming that same phrase. Voice and chalk advance together. Only a short natural breath separates one phrase from the next — no long pause anywhere. Total speech fills roughly 13 of the 15 seconds. The only silence is the final 0.8 seconds, where she has finished writing and simply smiles and nods. Forbidden at all times: ad-libbed dialogue, filler words, repeating a phrase, reading the sentence twice, humming, laughing, sighing, and every wordless vocalisation such as "んっ" "うん" "ふふ" "ah" "mm" "hm". She says the four phrases once each and nothing more. Pronounce "Seedance 2.5" as English "seedance two point five". [Reference] @Image1 = the keyframe: a woman in a white coat standing beside a completely empty green chalkboard, holding a slim wooden pointer at her side. Strictly preserve @Image1's face, hair, glasses, white coat, the chalkboard's position and size, the easel, the background shelves, and the framing. Nothing moves in the frame except her arm, her upper body, her face, and the chalk marks she draws. [One-line summary] 15 seconds. A cheerful presenter gives a short lecture, writing four lines of Japanese on a green chalkboard with the tip of a wooden pointer while speaking the same words aloud. Pixar-style 3D animation. Locked-off static camera. [Global setup] Environment: warm indoor study room, soft warm ceiling light, shallow depth of field, background shelves stay blurred. Highly realistic physical texture on the chalk dust and the wood of the easel. Visual style: Pixar-style 3D animation, warm color grade, soft shadows. Camera language: medium shot, eye level, straight-on. The camera is completely locked off — no pan, no tilt, no zoom, no push-in, no handheld shake. One camera behavior only: none. Character: as in @Image1. Keep the glasses, the hair silhouette, and the coat identical. Keep believable skin shading and fine surface detail — do not make her look plastic. Acting core: a warm, confident teacher who enjoys showing something off. *** WRITING RULE — SHE IS THE ONE WRITING, AND SHE WRITES AS SHE SPEAKS. *** Every chalk mark is produced by her own hand movement, in time with her voice. For each phrase: 1. Her shoulder and elbow carry the pointer tip to the start of the line. Her torso turns slightly toward the board and her eyes go to that point first. 2. The tip presses lightly to the board and travels along the path of each stroke. The chalk line appears directly behind the moving tip, following it exactly, never running ahead of it, never appearing anywhere the tip has not touched. 3. Characters are formed one stroke at a time, in correct Japanese stroke order, left to right. Faint chalk dust puffs at the tip and a soft scraping sound follows it. 4. Between strokes the tip lifts a few centimetres, then sets down at the start of the next. 5. The syllables she speaks land together with the characters she is forming — when her voice reaches a word, her hand is writing that word. Voice and chalk stay in step. 6. At the end of each line she lowers the pointer slightly, takes one small breath, glances at the camera, then moves to the line below. Her arm leads and the mark follows — the timing of the arm and the timing of the mark must match frame for frame. Marks NEVER fade in as a whole word. Marks NEVER appear while her arm is at rest or while the tip is away from the board. No invisible hand. No magic writing. The arm motion is fluid and human: the wrist flexes, the elbow opens and closes, the shoulder carries the reach across the board, her body weight shifts slightly as she reaches. Once a line is finished it stays on the board unchanged for the rest of the shot. Japanese script rule (important): Render every kanji with its correct stroke structure and correct number of strokes — 黒 板 日 本 語 文 字 書 便 利. They must be legible as real Japanese characters, not invented or Chinese-simplified lookalikes. Write them at a generous size so the strokes stay separated. "Seedance 2.5" is written in Latin letters and digits exactly as spelled: S-e-e-d-a-n-c-e, space, 2, period, 5. Chalk colors — only two, never any other: YELLOW chalk for "Seedance 2.5" only. WHITE chalk for everything else. Layout rule (important): Four lines, left-aligned to a common left margin, stacked evenly down the board from top to bottom, filling the board by the end. Large, cheerful hand-lettered chalk style with slightly uneven strokes. Exact content, top to bottom: Seedance 2.5なら 黒板に日本語の文字を 書くことができます。 とても便利ですね Never centre a line. Never write small. Each line is written as large as it can be while still fitting: a completed line spans almost the full writable width of the board, from the left margin nearly to the right edge of the board, and the four lines together fill the board from top to bottom. Characters are wide and generously spaced so that dense kanji such as 黒 板 語 書 便 利 keep their strokes separated and legible. If a line would not fit, make the characters narrower rather than shorter in height — never shrink a line so that it occupies only part of the board's width. Do not add any other word, symbol, arrow, underline or drawing. Forbidden: no subtitles, no captions, no on-screen UI, no watermark, no background music, no camera movement, no cutting to another shot, no extra people, no second hand entering the frame, no stick of chalk held in her free hand, no distortion of lines already written. [Timestamp storyboard] 0.0-3.6s LINE 1 Action: she raises the pointer to the upper-left of the empty board and writes "Seedance 2.5なら" in YELLOW chalk — first the Latin letters and digits, then the kana なら — the marks trailing the moving tip. Speech (in step with the writing): 「Seedance 2.5なら」 Intent: a small proud lift in her eyebrows on the brand name. This is the thing she is showing off. Camera: locked. No subtitles. No BGM. Japanese only. 3.6-7.2s LINE 2 Action: she drops to the next line and writes "黒板に日本語の文字を" in WHITE chalk, stroke by stroke. Her eyes follow her own tip. Speech (in step with the writing): 「黒板に日本語の文字を」 Intent: matter-of-fact, the setup half of the sentence. Keep the arm steady and even. Camera: locked. No subtitles. No BGM. Japanese only. 7.2-11.0s LINE 3 Action: she drops to the third line and writes "書くことができます。" in WHITE chalk, stroke by stroke, ending with a firm dot for the 。 Speech (in step with the writing): 「書くことができます。」 Intent: this is the payoff of the sentence — her voice firms up slightly on ます, and the final dot is pressed with a small decisive tap. Camera: locked. No subtitles. No BGM. Japanese only. 11.0-15.0s LINE 4 — the close Action: she writes "とても便利ですね" in WHITE chalk on the bottom line, then lowers the pointer to her side, turns her face fully to the camera, breaks into an open warm smile and gives one clear nod. She holds that pose for the final 0.8 seconds in silence. Speech (in step with the writing, finishing by 14.2s): 「とても便利ですね」 Intent: the nod is the close. Warm, a little playful, as if sharing a good discovery. Camera: locked. No subtitles. No BGM. Japanese only. [Closing constraints — restated for the whole clip]

全片统一要求 四段分别生成，每段10秒，9:16竖屏，4K超写实高端客家美食广告质感，24帧电影感。固定采用温暖自然的客家老厨房环境、深色木质操作台、暖色侧逆光和浅景深微距摄影。 四段中的豆腐必须始终保持统一：传统客家老豆腐，乳白偏暖色，质地细密而略带自然豆孔，切成大小一致的厚实长方块；不能变成嫩豆腐、内酯豆腐、日式豆腐、鸡蛋豆腐、奶酪或面包。 肉馅始终使用同一份新鲜猪肉馅，肥瘦比例自然，保留清晰肉粒，颜色真实。所有酿豆腐的大小、形状、肉馅数量和煎制颜色必须连续统一。 画面只展示食材、厨师双手和烹饪器具，不出现厨师正脸。禁止字幕、文字、品牌标志、水印、包装袋和平台界面。 第1段（0—10秒）：精选黄豆与传统石磨豆浆 生成一段10秒、9:16竖屏、4K超写实高端客家美食广告视频。展示制作客家酿豆腐的第一步：精选黄豆，并使用传统花岗岩石磨磨出细腻豆浆。 0—2秒：暖色晨光照进传统客家厨房。一只浅色竹筛中铺满颗粒饱满、大小均匀的淡金黄色黄豆。镜头贴近黄豆表面缓慢推进，清楚呈现豆粒自然纹理和新鲜光泽。 2—4秒：一只干净自然的手轻轻拨动并挑选黄豆，指尖从豆粒间缓慢划过。黄豆不能发黑、发霉、开裂或变成玉米、花生、咖啡豆。 4—6秒：画面自然切换到传统圆形花岗岩石磨。浸泡好的黄豆与少量清水缓慢加入石磨中央进料口，厨师握住木柄，平稳推动上层磨盘旋转。 6—8秒：石磨持续转动，乳白色豆浆从上下磨盘的缝隙缓慢流出，沿石磨导流槽向下汇聚。豆浆质地细腻、自然顺滑，不能像奶油、胶水或浓稠面糊。 8—10秒：85毫米微距跟随豆浆形成连续细流，流入下方干净的木桶或陶盆。暖色侧逆光照亮乳白豆浆，少量自然水汽轻轻上升，最后定格在豆浆稳定流淌的画面。 采用35毫米环境近景、50毫米操作特写和85毫米微距镜头。镜头运动平稳克制，突出黄豆颗粒、石磨纹理和豆浆流动质感。 严格避免 禁止黄豆凭空变成豆浆；禁止石磨无接触自行高速旋转；禁止豆浆从错误位置流出；禁止使用电动搅拌机、现代豆浆机或金属工业设备；禁止豆浆喷溅爆炸；禁止多余手指、手掌变形、器具穿模、文字、水印和标志。 衔接要求 最后一帧保留乳白豆浆流入容器的近景。第二段使用这批豆浆凝固制作而成的同一批传统老豆腐，整体暖色厨房光线保持一致。 第2段（10—20秒）：手剁肉馅与酿入豆腐 生成一段10秒、9:16竖屏、4K超写实高端客家美食广告视频。展示新鲜猪肉手工剁馅、老豆腐切块、挖出小凹槽并酿入肉馅的真实过程。 0—2秒：同一间暖色客家厨房内，新鲜猪梅头肉放在厚实的深色木砧板上。猪肉肥瘦自然、颜色鲜红，厨师用中式菜刀将猪肉切成均匀小片。 2—4秒：厨师继续用菜刀有节奏地手工剁肉。肉粒逐渐变细，但仍保留清晰颗粒和真实纤维，不能剁成完全光滑的肉泥。镜头贴近刀锋和肉粒，表现传统手工制作质感。 4—5秒：厨师用刀面将剁好的肉馅归拢成一小堆。肉馅中可以看到少量葱白碎和自然肥肉颗粒，整体鲜润但不能大量出水。 5—7秒：第一段豆浆制作而成的传统老豆腐出现在浅色竹砧板上。豆腐被切成大小完全一致的厚实长方块，每块约4厘米长、3厘米宽、2.5厘米厚。厨师用小勺在豆腐上表面中央轻轻挖出一个规则凹槽，不能挖穿豆腐底部。 7—9秒：厨师使用筷子或小勺，把同一份肉馅逐一填入豆腐中央。肉馅压实并略高于豆腐表面，四周豆腐边缘保持完整，不能破裂或塌陷。 9—10秒：镜头缓慢横移，展示一排已经酿好的豆腐。所有豆腐大小一致、肉馅朝上、排列整齐，乳白豆腐与粉红肉馅形成清晰对比。 采用50毫米操作近景与85毫米微距，焦点持续跟随刀锋、豆腐凹槽和填馅动作。暖色柔光突出豆腐细密豆孔、猪肉纤维与手工制作细节。 严格避免 禁止使用机器绞肉；禁止肉馅变成香肠、鱼肉、虾滑或红色肉酱；禁止豆腐自动开洞；禁止把豆腐切成三角形、圆形或薄片；禁止凹槽贯穿底部；禁止肉馅从豆腐内部穿出；禁止豆腐像果冻一样晃动；禁止豆腐碎裂、融化或变成奶酪。 衔接要求 最后一帧固定展示同一批酿好肉馅的长方形豆腐，肉馅朝上整齐排列。第三段必须使用这一批完全相同的酿豆腐进行煎制，数量、大小和肉馅状态不能改变。 第3段（20—30秒）：香煎定型与原汁焖煮 生成一段10秒、9:16竖屏、4K超写实高端客家美食广告视频。使用第二段同一批酿豆腐，完整展示肉馅面煎制定型、豆腐两面煎香、加入调味汁焖煮的过程。 全段固定使用同一只宽口黑色铁锅，炉灶、木质台面和暖色厨房环境保持统一。 0—2秒：铁锅烧热后加入薄薄一层花生油。厨师把同一批酿豆腐轻轻放入锅中，先让带有肉馅的一面贴近锅底煎制定型。豆腐排列整齐，彼此保持适当距离。 2—4秒：豆腐底部与肉馅逐渐定型，边缘发出细密油泡。厨师使用深色木筷子轻轻夹起并翻面，展示肉馅面已经形成均匀金黄色煎香纹理。 4—6秒：继续将豆腐两面煎至浅金黄。豆腐外层形成薄而完整的焦香表皮，内部仍保持柔嫩。所有豆腐煎色接近，不能有的焦黑、有的仍然生白。 6—8秒：沿锅边缓慢倒入由清水、生抽、少量蚝油和白胡椒调成的浅琥珀色汁水。酱汁进入热锅后轻轻沸腾，逐渐包裹豆腐底部。酱汁必须清亮、流动，不能像糖浆一样浓稠。 8—9秒：酿豆腐在原汁中短暂焖煮，细小气泡围绕豆腐自然翻滚。肉馅完全熟透，豆腐吸收少量汁水，但整体形状保持完整。 9—10秒：厨师用宽口锅铲托起一块酿豆腐，展示金黄豆腐表面、完整肉馅和吸满鲜汁的内部结构，为第四段转入砂锅作准备。 采用50毫米锅边近景、85毫米微距与轻微俯拍镜头。暖色侧逆光突出金黄煎面、琥珀汤汁、细密气泡和自然蒸汽。 严格避免 禁止油炸；禁止使用大量深油；禁止豆腐炸成硬壳或焦黑；禁止豆腐翻面时碎裂；禁止肉馅掉出；禁止酱汁突然变成红烧浓油、番茄汁、咖喱或辣椒油；禁止豆腐在锅中凭空翻转；禁止锅具、筷子和豆腐大小发生变化。 衔接要求 最后一帧保留同一块由锅铲托起的金黄酿豆腐，其余酿豆腐仍在浅琥珀色原汁中。第四段必须使用同一批豆腐、同一颜色的汤汁，并转入固定的深棕黑色圆形陶土砂锅。 第4段（30—40秒）：砂锅焖香与成品英雄镜头 生成一段10秒、9:16竖屏、4K超写实高端客家美食广告视频。展示第三段同一批酿豆腐转入陶土砂锅后完成焖煮、撒葱花，并用汤勺夹起成品的英雄镜头。 全段固定使用同一只深棕黑色圆形陶土砂锅。砂锅内整齐摆放8—10块大小一致的长方形酿豆腐，肉馅面朝上或轻微侧向镜头。豆腐浸在少量浅琥珀色鲜汁中，不能被汤汁完全淹没。 0—2秒：镜头从砂锅边缘缓慢推进。酿豆腐在浅琥珀色原汁中轻轻沸腾，豆腐表面呈均匀金黄色，肉馅完整熟透，少量自然蒸汽缓缓上升。 2—4秒：厨师用深色木筷子轻轻调整最前方两块豆腐的位置，让所有酿豆腐排列自然、略微交叠，但不能堆成杂乱的一团。 4—5秒：翠绿色葱花从画面上方自然撒落，均匀点缀在金黄豆腐和鲜汁表面。葱花数量适中，不能完全遮挡肉馅和豆腐。 5—7秒：一把干净的银色中式汤勺从砂锅边缘伸入，稳定托起最前方一块完整酿豆腐。勺子动作缓慢自然，不能夹碎豆腐，肉馅不能脱落。 7—9秒：进入85毫米微距英雄镜头。勺中的酿豆腐悬停在砂锅上方，清楚展示金黄煎香表面、乳白柔嫩豆腐层、饱满猪肉馅和真实细密纹理。少量浅琥珀色鲜汁从豆腐边缘缓慢滴回砂锅。 9—10秒：镜头轻微拉远，完整呈现热气升腾的陶土砂锅、整齐的酿豆腐、翠绿葱花和被汤勺托起的主角豆腐，最后稳定定格。 采用35毫米砂锅环境近景、50毫米缓慢推进和85毫米食物微距。暖色侧逆光勾勒蒸汽层次，柔和高光突出豆腐煎香纹理与鲜汁反光。成品必须呈现传统客家酿豆腐的家常温润感，而不是油炸豆腐或浓油红烧菜。 严格避免 禁止更换砂锅；禁止豆腐数量、大小和形状突然改变；禁止豆腐变成方形肉丸、油豆腐、豆腐泡、鸡蛋块或面包；禁止肉馅消失、脱落或变成红色肉酱；禁止汤汁过多、浑浊、浓稠或呈鲜红色；禁止豆腐焦黑；禁止葱花变成香菜、辣椒或其他配料；禁止筷子与汤勺穿过豆腐；禁止多余手指、畸形手掌、字幕、水印、标志和界面元素。

Create a short anime-style food video showing the step-by-step preparation of grilled meat skewers and a fresh pomegranate drink: a chef slices raw red meat into uniform cubes, seasons them with spices, then opens a ripe pomegranate and squeezes its juice and seeds into a bowl. Pour the juice into a tall glass with ice and sparkling mixer, then garnish with mint. Grill the seasoned meat cubes on skewers with peppers and onions, plate the juicy kebabs with fresh parsley, and present them beautifully beside the chilled pomegranate drink.

Create a 10-second vertical 9:16 ultra-realistic cinematic product video showing a tiny compact wall-mounted electronic heater/temperature-control device being unboxed and installed. Scene 1 (0–2s): Close-up of realistic human hands opening a small retail cardboard package containing a miniature white electronic wall heater. Warm cozy indoor room, wooden table, soft ambient lighting, shallow depth of field. Scene 2 (2–4s): The hands carefully remove the tiny white device from its molded plastic packaging. Macro product cinematography, realistic plastic textures, crisp details, natural hand movements. Scene 3 (4–5.5s): Close-up from the rear as a small screwdriver is used to adjust/install a component on the back of the device. Precise hand movements, satisfying mechanical detail. Scene 4 (5.5–7.5s): The device is mounted onto a wall with subtle floral wallpaper. A small black power connector/cable is plugged into the side. Scene 5 (7.5–10s): Extreme close-up of a finger pressing the control button. The digital display lights up showing the temperature, then the camera slowly pulls back to reveal the compact heater operating on the wall. Style: photorealistic, macro cinematography, miniature product world, cozy home interior, warm natural lighting, realistic shadows, shallow depth of field, smooth handheld camera movement, highly detailed textures, satisfying ASMR-style unboxing and installation, subtle cinematic focus transitions, premium commercial advertisement quality. Important: Preserve realistic proportions, natural human fingers, believable physics and mechanical interaction. No extra objects, no distorted hands, no text overlays, no watermark. Vertical 9:16 composition.

A young traveler hikes through a lush mountain forest, crosses a wooden bridge over a flowing stream, and reaches a stunning waterfall hidden among moss-covered rocks. Ultra-realistic travel documentary, authentic hiking movement, realistic environmental physics, natural English lip-sync, bright daytime lighting, immersive forest ambience, and seamless story continuity throughout.

Create a table full of vegetables, healthy fats, and protein. Then you have a chef create delicious plates with them for a healthy free cancer life.

Use the female character in the reference image as the sole character reference, maintaining high consistency in facial features, hairstyle, skin tone, clothing, and overall temperament. 9:16 vertical screen, 10 seconds, ultra-realistic live-action knowledge science broadcast. The character is sitting in a real home study, medium-close up from the chest up, fixed camera, essentially no movement. Natural window light shines from the side front, background bookshelves are slightly blurred, looking like a real knowledge blogger filmed with a camera. Character naturally broadcasts to the camera: 'Many people think that AI answering questions is finding answers in a database. Actually it's not; it's more like continuously predicting the most likely next word based on the previous content.' Performance requirements: 0-2s: Naturally look directly at the camera to start, conversational tone, slight blinking. 2-5s: When saying 'Actually it's not,' gently shake head once, eyebrows have natural changes. 5-8s: When explaining 'based on previous content,' one hand naturally enters the frame to make a very small explanatory gesture. 8-10s: After saying 'most likely next word,' finish with a slight nod. The whole process should not feel like reading a script or have a host's broadcasting tone. Mouth movements strictly match Chinese speech. Retain natural blinking, breathing, micro-expressions, slight head movements, and real skin texture. Eyes can occasionally briefly deviate from the camera and then naturally look back. Restrained gestures, do not wave hands frequently. Real mobile phone/mirrorless camera shooting texture, slight sensor noise, real skin quality, no airbrushing, no internet celebrity filters, no plastic skin, no exaggerated movie lighting, no camera movement, no subtitles, no watermarks, no screen text.

Infographic on how blue light rays prevent the production of melatonin and disrupt the circadian rhythm

【10秒手工鉛筆速寫繪畫延時】 在專業數位繪圖軟體中，從完全空白的米白色紙張畫布開始，使用全程可見的滑鼠游標，逐步重建提供的參考圖。保持參考圖的人物、姿勢、構圖、長髮、服裝，以及湖面、拱橋、遠山、柳樹、遊船等場景關係。 0:00-0:02 空白畫布開始，游標快速建立人物比例與整體構圖，勾勒人物、湖面、拱橋、遠山與主要環境輪廓。 0:02-0:04 快速細化人物與背景線稿，繪製臉部、五官、長髮、服裝，同步增加橋梁、山體、柳樹、遊船與背景人物。 0:04-0:06 使用石墨鉛筆快速排線，建立頭髮、臉部、服裝與環境明暗。保留自然交叉線、重複線、斷續線與手工修改痕跡。 0:06-0:08.5 持續精修五官、髮絲、服裝褶皺與環境細節，逐漸形成完整的手工鉛筆速寫。 0:08.5-0:09.5 完成最後細節，擦除少量多餘構造線，穩定展示完整作品。 0:09.5-0:10 游標移至畫面左下角，以自然手寫筆觸完成最後署名「● DeepBlue」。署名只能在最後出現，完成後游標停留。 風格： 高速手工鉛筆速寫延時攝影；米白色紙張、石墨線條、自然排線、交叉線、紙張紋理、真實手繪痕跡。畫布為視覺主體，UI 簡潔可信。 核心要求： 空白畫布 → 構圖 → 草圖 → 細節線稿 → 排線明暗 → 精修 → 完成 → 最後署名。所有畫面變化都由可見游標實際繪畫逐步產生，後續畫面必須建立在前一階段之上。禁止角色或背景突然出現、禁止直接切換成完成圖、禁止彩色上色、水彩、3D、動漫風與電影式轉場。

lane reduction indicated lane, and soon vehicle in that lane was merge onto through lane

A visualization of a black hole being created, showing the dynamic process of stellar collapse and formation with gravitational effects, event horizon appearance, and surrounding spacetime distortion

Ultra-photorealistic full 3D cinematic wildlife sequence, 15 seconds, single continuous take with natural camera moves, absolute real-looking African animals, hyper-detailed fur, muscle, dust and light physics, zero CGI look, documentary quality. [0-4s]: Wide establishing shot of the African savanna at golden hour. A fully adult African lioness stands alert in the center foreground, dense golden-tan coat with every individual hair, subtle breathing and ear twitches visible. In the distance a massive horde of over 40 real black-backed and side-striped jackals begins charging toward her across cracked red earth, kicking up thick volumetric red dust clouds. Slow cinematic push-in begins. [4-9s]: Medium tracking shot following the charging jackal horde. The pack surges forward in chaotic realistic running gaits, lean bodies, open jaws with saliva flecks, pointed ears, frantic snarls. Dust particles catch the low sunlight. The lioness remains steady, watching them approach. Camera continues smooth push-in while slightly orbiting right for depth. [9-13s]: The lioness’s massive partner, a dominant African lion with thick dark wind-ruffled mane, emerges powerfully from directly behind her. He strides into the foreground, plants his huge paws in the dust, lowers his head and delivers a deep chest-vibrating roar that freezes the entire jackal pack mid-charge. Extreme detail on mane strands, wet nose, amber eye reflections, muscle ripples under skin. [13-15s]: Close-up reaction shot of the jackals skidding to a halt, some scattering slightly in fear while the lion holds his protective stance in front of the lioness. Camera settles on a powerful heroic medium shot of the lion and lioness together against the dusty savanna. Camera language: smooth cinematic push-in + subtle orbit, shallow depth of field, natural handheld micro-shake, anamorphic lens feel, volumetric god-rays and heat haze. Style: ultra-realistic 3D photorealism, ARRI Alexa 65 look, real animal fur physics, authentic African savanna lighting and atmosphere, 8K detail, original quality. Audio (native full stereo sound): (soft distant wind and savanna ambient bed) <jackal pack running feet on dry earth, growing louder snarls and yips, heavy dust whooshes> <deep powerful African lion roar that echoes across the plains, low chest rumble> <jackals skidding and whimpering in fear, sudden silence after the roar>

First & Last Frame (FLF2V) using [StartFrame] and [EndFrame]. [CAMERA]: Fixed locked tripod shot, 24mm wide lens facing the cliff edge. Zero camera drift. [TIMELINE & MOTION]: - 00:00 - 00:12 (Timelapse Build Phase 1): 100x speed timelapse. Two craftsmen work synchronously. Builder 1 chisels bedrock and excavates the pool basin; Builder 2 mixes mortar and lays stone blocks around the pool rim. Flying stone dust, rapid mallet impacts, and sweeping sun shadows. - 00:12 - 00:18 (Mid-Build ASMR Relaxation Pause): Speed drops to 24fps normal motion. The two builders sit at the edge of the finished pool frame, sharing coconut water, talking softly, and watching eagles soar over the canyon mist. - 00:18 - 00:26 (Timelapse Build Phase 2): 100x speed timelapse resumes. Builders install bamboo decking, smooth waterproof pool lining, route natural stream water into the basin, and place rattan loungers and lanterns. - 00:26 - 00:30 (Sunset Cinematic Reveal): Normal speed. Builders step out of frame. Pool fills to the brim, overflowing smoothly into the canyon as dusk settles and warm pool lights turn on. [ASMR AUDIO]: Crisp stone chiseling, mallet thuds, water filling pool (gush-trickle), coconut cracking sound, wind over canyon, serene evening atmosphere.