OpenZhenZhen AI 提示词画廊 · Claude Opus 5.5 · video
Orange dot motion design system
A 15-second 2D motion design film built entirely in HTML/CSS/JS with Opus 5.5, turning an orange dot into a sequence of toggle, typography, graph, shape morph and kinetic type scenes, using a detailed structured prompt the creator published in full.

提示词 / Prompt
English prompt
<inputs> Ask me for: a short label for the opening toggle, one hero word, a percentage for the graph, the text for the final card, one accent color, and a track with a clear beat. </inputs> <direction> A 2D motion design film in 16:9. Use a warm off-white canvas, near-black backgrounds, bold typography and one vivid orange accent. The orange dot connects every scene: it starts in the UI, becomes the dot over a letter, traces a spring graph, grows into a shape and returns on the end card. A cursor makes the opening click feel real. Keep the motion sharp and controlled, with small spring overshoots and no dead time. Banned: stock footage, gradients, glows, particle bursts, random transitions and motion that isn't connected to an element already on screen. </direction> <structure> Around 15 seconds, with a visual change on every major beat. Open: a cursor clicks the orange toggle beside "Reduce Motion". The letters bend and move into place until only "Motion" remains, with the orange dot above the "i". Spring: the dot jumps away from the word and lands on a graph. Its path draws a spring response, overshoots the target and settles beside a "+22%" callout. Shape: the dot shoots across a line, grows into an orange circle and fills the frame. A black rounded square rotates inside it, then stretches into a pill. The scene contracts to a single orange dot on black. Type: words like "SPRINGS", "EASING", "KINETIC TYPE", "3D" and "SOUND" orbit the dot. The circle of type opens out into a field of tiny dots. Reveal: the halftone field expands and flips to black, revealing the final card: "Opus 5.5", "Motion designer." and "0 keyframes". Return: the orange dot moves back through the halftone, graph and toggle. Match the final frame to the first so the video loops cleanly. </structure> <build> 1. One HTML file, 1920x1080 at 60fps. Compute every visual from time inside seek(t): no CSS transitions, timers or state carried between frames. 2. Use closed-form springs for the toggle, bouncing dot and graph. Draw the graph from the same spring function that moves the dot. 3. Animate letters individually for the "Reduce Motion" to "Motion" transformation. Keep the orange dot attached to the "i" until it begins its jump. 4. Make the orange circle, rotating square and pill different states of the same shape. Preserve its position and motion through each transformation. 5. Place the orbiting words along a circular path, then move their letters outward to hand the frame over to the halftone grid. 6. Draw the halftone as a grid of dots whose sizes respond to the orange dot. Let it grow past the frame edges before revealing the end card. 7. Sync the click, dot landing, graph peak, shape changes and final title to measured beats. Render one frame per beat to check the pacing before the full export. </build> <gotchas> The graph and dot must follow the same motion or the spring will feel fake. Keep the orange accent consistent across every scene. Give outgoing and incoming text separate timing so letters don't overlap. When a shape fills the screen, scale it past all four corners. Match the cursor, dot and typography in the first and last frames to avoid a loop stutter. </gotchas> <start> Ask me for the inputs, then show me the beat map and four stills (toggle, graph, kinetic type, end card) before building the full video. </start>
主题与风格
探索更多图片和视频提示词 · 生成图片 · 生成视频 · 在 AI 画布中创作
相关作品
- 谁叫你这么运镜的
https://www.runninghub.ai/zh-cn/ai-detail/2109209394184478722/?inviteCode=rh-v1256 一键复刻
- 哈士奇111
subject_definitions: <Subject 1> 是本片唯一的宠物主角 — FACE from <Picture 1>(哈士奇雪橇犬,冰蓝色眼睛,黑色鼻头,黑白双色、头顶黑色面罩纹、灰黑鞍部、白脸白胸白四肢,蓬松双层毛、体态骨架匀称结实,气质活泼)。只参考 <Picture 1> 的外观(五官、毛色、花纹、体型),不使用 <Picture 1> 的背景、场景与构图;视频全程保持与 <Picture 1> 外观完全一致。 summary: [reference generation] 0-5s 静谧微距张力;5-9s 爪部微距切全景;9-15s 摇臂升空+逆光剪影谢幕。主角全程
- 哈士奇
subject_definitions: <Subject 1> 是本片唯一的宠物主角 — FACE from <Picture 1>(哈士奇雪橇犬,冰蓝色眼睛,黑色鼻头,黑白双色、头顶黑色面罩纹、灰黑鞍部、白脸白胸白四肢,蓬松双层毛、体态骨架匀称结实,气质活泼)。只参考 <Picture 1> 的外观(五官、毛色、花纹、体型),不使用 <Picture 1> 的背景、场景与构图;视频全程保持与 <Picture 1> 外观完全一致。 summary: [reference generation] 0-4s 鼻头超微距视觉钩子;4-9s 变速极速拉出+3D环绕;9-15s 0.4x呼吸感定格
- 西格玛男人修仙
用了吃猪侠那个跑30秒的工作流 所以可以跑20秒视频
- 女孩真人感测试
**【参考图像锚定】** 图像 1 是 [年轻女性],保留参考图中的面部特征、精致妆容、浅金色长直发与空气刘海、简约白色上衣、脖颈细金链与小巧金坠吊坠,及整体外貌。人物仅锚人物本身,场景按下文文字重建,不得沿用图内任何构图或背景细节。 **【分镜】** **人物初始站位与空间关系**:夜晚路灯下,她站在街边一盏路灯正下方偏前的位置,手持手机以真实前置摄像头自拍视角拍摄,画面从胸以上的中近景开始,镜头随她的手持动作运动。头顶路灯洒下柔和的暖白光池,从上方偏正前照亮她的脸 —— 额头、鼻梁、颧骨受光,鼻下与眼窝投下朝下的柔影;浅金发顶和颊边碎发被灯光勾出一圈暖色轮廓光,发丝末梢泛一点暖亮的金;
- H3单采,7秒打斗测试
integrated_multimodal_description: (本段为极度硬核的高速CG兵器交锋。禁用2D动漫渲染。画面中只有加雷斯和洛恩两人。加雷斯在连续攻击中开口嘲讽,洛恩全程嘴唇紧闭死扛。) [Shot1] 0-2.5s, Unreal Engine 5 render, hyper-realistic, fast-paced sword fight, dynamic camera tracking. A muscular man in heavy red-black iron armor (Gareth) swings a massive greatsword downward