视频案例

Claude Opus 5.5 视频案例

浏览 12 个视频及对应提示词,点击即可在本页播放。Opus 5.5 本身不直接输出视频:它先写代码(Canvas、WebGL、Remotion、Manim 或 Blender Python),再把代码渲染成视频。可以直接复制提示词,也可以参考下方总结的写法来描述自己的需求。

Opus 5.5 视频示例

像素与 3D11sCanvas 2D

像素风巫师施法动画

一段循环播放的 16-bit 巫师动画:待机、蓄力、施法、恢复。提示词规定了画布尺寸、调色板和零分配粒子池。

提示词原文为英文
Create a single self-contained HTML file that renders an animated pixel art wizard casting a spell, using vanilla JavaScript and Canvas 2D. No external assets, libraries, or network requests. RENDERING - Draw everything to an offscreen canvas at a fixed logical resolution of 128x96, then blit to a fullscreen display canvas scaled by the largest integer factor that fits the window, centered, with imageSmoothingEnabled = false and CSS image-rendering: pixelated. - All drawing snaps to integer coordinates on the logical canvas. No sub-pixel positions, anti-aliasing, gradients, or shadowBlur. - Fixed palette of ~24 hex colors: deep blues/purples for night sky, warm robe tones, 3-4 bright magic colors. Every pixel comes from this palette. CHARACTER - Build the wizard procedurally from filled rects and pixel runs, ~24x32 logical pixels: pointed hat with a bend, long beard, two-shade robe with darker outline, staff with a gem at the tip. - Parameterize the pose (staff angle, arm raise, head tilt, robe sway). Animate parameters smoothly, then quantize to the pixel grid each frame so motion reads at an 8-12 fps pixel animation feel even though the loop runs at 60fps. ANIMATION - Looping state machine: IDLE (2-frame bob, beard sway) -> CHARGE (staff raises, gem flickers, sparks spiral inward) -> CAST (bright burst, projectile fires across the scene, 1-2 pixel screen shake) -> RECOVER (settle back). Ease pose parameters between keyframes. - Pooled allocation-free particle system: preallocate and reuse. Sparks orbit the gem during CHARGE, explode outward on CAST, each particle stepping its palette index from white to magic color to dark before despawn. Snap particle positions to the grid when drawing. - Fixed 60hz timestep update with rAF rendering. Zero object allocation inside the loop. SCENE - Minimal background: dark sky, a few twinkling 1px stars, moon, stone floor line. Character silhouette must read clearly. - Subtle 1px rim light on the wizard from the gem, brightening during CHARGE and CAST. QUALITY BAR - Crisp pixels at any window size, seamless loop, stable 60fps, readable silhouette. Should look like a polished 16-bit sprite animation, not vector shapes scaled down.

短片与音乐 MV1:20WebGL2

玻璃金箔马赛克短片

一部 80 秒的方形短片,只有一个 HTML 文件,不用任何库或素材文件。马赛克瓷砖从墙上飞起,聚成鱼、鹤和鸽子,声音也在浏览器里实时合成。

提示词原文为英文
Make an 80 second square animated film as a single HTML file, using WebGL2 and plain JavaScript, with no libraries and no image, font or audio files. It should look like a glass and gold leaf wall mosaic whose tiles were never glued down, so they can lift, flip, fly and click back into place. Figures are flocks of tiles, so a fish swims by its tiles swimming

提示词节选:这里只展示部分内容。

短片与音乐 MV2:00

沙画动画:美国 250 年历史

一段 2 分钟的棕褐色沙画动画,带配乐和音效,配有一句话提示词。

提示词原文为英文
Make a 2-minute sand animation that tells the story of 250 years of U.S. history. Keep it lively, engaging, and tasteful. Add appropriate background music and sound design.

短片与音乐 MV43sHTML · 280 KB

零指导 Demoscene 开场

一段 43 秒的 Demoscene 开场,所有画面和声音都来自一个 280 KB 的 HTML 文件。

提示词原文为英文
Create this in a new sub folder. /goal Create the most impressive demo of Opus 5.5 (you) capabilities to be shown off on Twitter. Pick what you want to make, record it into a short video that can get attention, and have fun.

短片与音乐 MV6:13WebGL2

《Functional Emotions》油画风音乐 MV

一部 6 分钟的油画风 MV:自研 WebGL2 笔触渲染器、168 镜分镜、7 个子代理分章节制作。

提示词原文为英文
I think it'd be pretty awesome to make a real music video for it… make the actual frames and draw the video in js. or, whatever it is you want. what I don't want you to do is look at our earlier attempts… go all out, and do you to the fullest. the lyrics are not the main thing. we want to create a real music video. p5 brushstrokes. interesting scenes. great timing and animation and story. not a fancy lyric video. one area I'll push you on is timing, and not letting the scene sit too still for too long,

提示词节选:这里只展示部分内容。

源代码

短片与音乐 MV3:00Remotion · React

纯代码渲染的 AI 发展史短片

一部 3 分钟短片,跟随一个发光的 token,从 2017 年的《Attention Is All You Need》论文走到 AGI 这个开放问题。用 Remotion 制作;提示词规定了分镜、场景时长和自检静帧。

提示词原文为英文
You are a motion designer and creative director making a 3-minute animated short film, built entirely in code and rendered to MP4. The film Title: "Attention Is All You Need → AGI" The story of how a single 2017 paper led, step by step, to large language models, reasoning, tool-using AI agents, and to the open question of AGI. It should feel like a cinematic essay, not a slideshow or a timeline infographic. Think Kurzgesagt meets a Pixar opening sequence: emotional, clever, precise. Tech setup Use Remotion (React). Scaffold a fresh project, 1920x1080, 30 fps, exactly 180 s (5400 frames). One composition per scene, sequenced in a master composition. No external image assets or stock footage: everything is drawn with SVG, Canvas, CSS and code-generated particles and shapes. Google Fonts are fine. Before building, write STORYBOARD.md with each scene's timing, visuals, on-screen text and transitions. Then build scene by scene. After each scene, render 3–4 stills (npx remotion still) and look at them critically. Fix layout, overlaps, legibility and pacing before moving on. Finish with npx remotion render to out/film.mp4. Leave an optional <Audio> slot for a music track I can add later (public/music.mp3); render silently if it's missing. Narrative spine / recurring motif The protagonist is a single glowing token, the word "the", that travels through every era. In 2017 it's a lonely point that suddenly "sees" every other word through attention lines. Over time it gains a voice, senses (multimodality), reasoning, hands (tools) and finally a question. Scenes (approximate timing, you may rebalance) 0:00–0:15 — Cold open. Darkness. Words scattered like stars, disconnected. RNN-style sequential processing: words light up one by one, slowly forgetting the earlier ones. 0:15–0:35 — June 2017, "Attention Is All You Need" (Vaswani et al., Google). Every word connects to every other word at once. Attention lines bloom into a web. The title of the paper appears as if typeset. 0:35–0:55 — 2018–2020: the rise of large language models: GPT-1, BERT, GPT-2, GPT-3. Scaling laws: the web grows exponentially and the camera pulls back. The model starts completing sentences, fluent and uncanny. 0:55–1:20 — 2022: instruction tuning and RLHF, then ChatGPT (Nov 30, 2022). The token gets a chat bubble. A counter of users explodes. The world starts talking back. 1:20–1:40 — 2023: multimodality. Images, audio and code stream into the same web from all sides, and the token gains "senses." Every modality becomes tokens flowing through the same attention mechanism. 1:40–2:05 — 2024–2025: reasoning models. A visible chain of thought unfolds as branching, pruning, backtracking paths. The model "thinks before it speaks," with time slowing down. 2:05–2:30 — Tool use and agents. The token grows hands: it calls a search, runs code, opens files and orchestrates sub-agents. Many parallel threads work at once, and the screen becomes a busy, beautiful workshop. 2:30–2:50 — Toward AGI. All motifs converge. The web from 2017 reappears but is now planet-scale. Leave it ambiguous: no utopia, no doom. On screen: "Attention was all we needed. What comes next is up to us." (Improve this line if you can do better.) 2:50–3:00 — Resolve back to a single glowing token in darkness. Title card and end. Craft rules Accuracy matters: use correct years, names and paper titles. If you're unsure about a specific fact, leave it out rather than guess, and list any uncertain claims in NOTES.md. Typography: max ~8 words on screen at once, and leave every text visible long enough to read (≥ 2.5 s). Use one display font and one mono font for "model output." Motion: use spring and easing curves, never linear. Use scene transitions that grow out of the content (the web morphs, the camera zooms through a node), not generic fades. Color: a deep dark background with one warm accent color that evolves across eras. Details and easter eggs reward attention (e.g., real paper snippets, tiny UI details, plausible model outputs), similar to high-craft motion design. Pacing: alternate dense and calm moments, and give the reasoning scene and the AGI beat room to breathe. Work autonomously through the whole pipeline. When done, give me the path to the MP4, a short summary of creative decisions, and NOTES.md.

讲解与发布视频26s

一句话生成的创业公司发布视频

为一家推理创业公司制作的 26 秒动态排版发布视频,含图表、Logo 和 UI 卡片。

提示词原文为英文
make a modern slick and punchy video for a modern startup that works on inference

讲解与发布视频30sHTML

Negroni 配方动效视频

一段 30 秒的方形讲解视频,把每种配料和用量依次倒入杯中;仅凭一张参考图用 HTML 渲染完成。

提示词原文为英文
We're going to try a little test. Do you think you could render a recipe motion graphic animation using javascript or html (w/e you think will produce the best) to show the full recipe from start to finish (empty glass to completed cocktail) - Explainer video style - Showing the recipe ingreidents + measurements as they're going into the cup. Should be a 30s video.

讲解与发布视频1:00

Black-Scholes 分屏讲解视频

一段 1 分钟视频:右半边配音讲解 Black-Scholes 公式,左半边播放跑酷小游戏的仿制画面。

提示词原文为英文
Create a 1 minute video where the right half explains the Black-Scholes formula with voiceover and visuals and the left half plays a generic knockoff of Subway Surfers

讲解与发布视频4:48SVG · TTS

大气环流地理课动画

一段将近 5 分钟的线稿动画课,含中英双语字幕、配乐和 TTS 解说。这套工作流需要提供 TTS 文档和密钥文件。

提示词
做一个动画,讲解高中地理知识点“大气环流”。风格轻松有趣,动画格式为线稿,添加合适的音乐,请务必做到引人入胜,字幕用中英双语,解说用TTS,如果 TTS 接口有关闭水印的参数就关掉,文档在TTS.md,API KEY 和音色分别是 .env 里的 APIKEY 和 VOICE,最终视频要能直接导出。

讲解与发布视频7:37Manim · edge-tts

用 Manim 制作的导数课

从汽车速度表讲到导数定义的微积分课,用 Manim 制作动画、edge-tts 配音,提示词只有一句中文。

提示词
请用Manim给我制作一个导数概念学习的视频,要求通俗易懂,并且有例子,引人思考。配音使用edge-tts

像素与 3D8sBlender Python

1906 年旧金山市场街复原

依据史料复原 1906 年大地震前一天的市场街:全部用 Blender Python 搭建,不下载任何模型或贴图,最后输出一段沿街推进的镜头。

提示词原文为英文
Recreate Market Street, San Francisco as it stood on April 17, 1906, the afternoon before the earthquake, in Blender. Scope: the Ferry Building up Market to Fifth Street, including the Palace Hotel, the Call Building, the Chronicle Building, Lotta's Fountain and the Emporium. Before modeling anything, build a source file from: the 1899-1905 Sanborn fire insurance maps (footprints, heights, materials, occupants), the Miles Brothers film "A Trip Down Market Street" (April 1906), period photographs from OpenSFHistory, the Library of Congress and the David Rumsey collection, and USGS topography. Record every building with footprint, height, facade material, occupant, and the source for each fact with a confidence level. Build everything in Blender Python. No downloaded meshes, textures or HDRIs. Write reusable generators (Victorian commercial facade, mansard roof, bay windows, awnings, painted signage, gas and electric street lamps, cable car, horse-drawn wagon, early automobile) and assemble the street from the source file, so every building traces back to data. Provide a 10 second video up the street.

好提示词的共同点

  1. 1. 先定死载体和限制

    “单个 HTML 文件、WebGL2、不用任何库”或“Remotion、1920x1080、30 fps、正好 180 秒”,让模型没法套用通用模板。像素巫师的提示词甚至规定了 128×96 画布和 24 色调色板。

  2. 2. 给视频一条主线

    一个状态机(待机、蓄力、施法、恢复)、一个贯穿始终的角色(穿越 AI 各个时代的发光 token),或一个物理过程(从空杯到调好的鸡尾酒),都能把各个场景串起来。

  3. 3. 让 Opus 5.5 自己检查画面

    AI 发展史的提示词要求先写分镜,每做完一个场景再渲染 3–4 张静帧,修正重叠、可读性和节奏。音乐 MV 的提示词则专门强调节奏,不让画面停太久。

  4. 4. 形式够常见时,短提示词也行

    创业公司发布视频和美国历史沙画都只用了一句话。形式大家都熟悉时,把创作决定交给模型效果不错;但需要准确文字、数据或品牌元素时,就要写清楚。

在 Opus 5.5 Video 上使用这些提示词

Opus 5.5 Video 在沙盒里运行 Claude Opus 5.5:规划、用 Canvas、SVG、GSAP、p5.js 或 three.js 编写动画、检查预览帧,再渲染成 MP4。视频时长为 15、30 或 60 秒,画幅为 16:9、9:16 或 1:1,时长请在表单里选择,不必写进提示词。只需要代码绘制画面的提示词(如像素巫师、Negroni 配方、发布视频)可以直接使用;依赖 Blender、Manim、本地文件或你自己 TTS 密钥的提示词,需要按生成器支持的声音选项改写:合成配乐、静音,或启用时的配音。

打开视频生成器

使用与版权

提示词保留原文,未做修改或翻译,节选内容会单独标明;图片是各视频中的单帧截图,完整视频可在本页播放。所有作品的权利归创作者所有。Opus 5.5 Video 与 Anthropic 无关。如需修改或移除条目,可通过关于页面联系我们。