OpenZhenZhen AI 提示词画廊 · Claude Opus 5.5 · video

四款模型视频提示词对比

Comparison of Video Prompts Across Four Models

作者用同一个提示让Claude Opus 5.5、Sonnet 5.5、GPT-6.1 Sol和GPT-6 Sol分别生成一个用HTML5 Canvas程序化绘制奔跑红狐的动画,并在回复中公开了完整提示词。

四款模型视频提示词对比 — AI video creation
四款模型视频提示词对比

提示词 / Prompt

English prompt

Create a single, self-contained HTML file using vanilla JavaScript and HTML5 Canvas 2D to procedurally animate a running wild red fox in crisp 1080p (Full HD). No external assets or libraries. Specifications: Canvas & Resolution:Native resolution: 1920 × 1080 pixels. Style: Smooth 2D vector-style rendering (anti-aliased Bezier paths, linear/radial gradients, dynamic shading). Fox Rigging & Locomotion:Spine Dynamics: Smooth multi-joint spline showing agile spinal flexion and extension, with a slightly arched back at the gathered phase of the gallop. Leg Kinematics: 4 slender, articulated limbs driven by Inverse Kinematics (IK) for a full rotary gallop, with light, springy foot placement. Secondary Motion: A long, bushy tail streaming behind with inertial, wave-like counterbalancing (spring-damped segments), shoulder-blade sliding, subtle ear flicks, and a stabilized, forward-locked head gaze. Styling: Rich russet-orange coat with layered fur-tuft edges and soft gradient shading. Cream-white chest, muzzle, and belly. Black "stocking" lower legs, black-backed ears, and a white-tipped tail. Amber eyes with a narrow pupil, a pointed snout, and fine whisker strokes. High-Res Parallax Environment: Multi-layer 1080p wild woodland-meadow backdrop:Gradient dawn sky and a distant misty horizon with soft atmospheric haze. Mid-ground with procedural pine and birch tree silhouettes and rolling hills, each layer scrolling at a different speed. Foreground terrain of tall grass, ferns, and fallen leaves, with a high-speed particle system generating kicked-up leaves, dirt, and dust plumes behind the paws. Performance:Optimized for stable 60 FPS execution via requestAnimationFrame. No UI elements

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

  • 闪身步

    https://www.runninghub.ai/zh-cn/ai-detail/2109209394184478722/?inviteCode=rh-v1256

  • 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;