54 curated cases: making videos with Claude Opus 5.5 by writing code, prompts included
vista8 · x · 2026-09-27
A GitHub repo curates public cases of "code-rendered video" with Claude Opus 5.5: 18 complete copy-ready prompts, 54 cases, and 9 technical approaches, each with links to the original posts.
How it works: Opus 5.5 doesn't output video files — it writes code that draws each frame (HTML Canvas, p5.js, Three.js, Remotion, Manim, Blender scripts), captures frames via headless browser, and stitches MP4s with FFmpeg; music via Web Audio/Python, narration via TTS. It excels at motion graphics, sketch/ink animation, explainers and lyric videos, but not photorealistic footage — for that it typically orchestrates video models like Seedance or Runway.
Quickstart: Claude Code on Opus 5.5 (effort high/xhigh), Node.js, Chrome and FFmpeg locally, then paste a prompt into an empty folder. A one-liner produced a startup launch video in 1 minute for $2, per the author; Chinese-language sketch-animation prompts are included.
Related event: Community Compiles 54 Claude Opus 5.5 Video Generation Prompts(2 posts)→
More from coding & agent
- Personal agents from big labs vs one shared company agent: which design wins? — AshishKulkarni1411 · 2026-11-16
- WebArena-Pro launches: 300-task multimodal web-agent benchmark across 20 apps — xhluca · 2026-11-16
- Self-improving agent papers this week: agents learn the benchmark, not the task — TheTuringPost · 2026-11-16
- 1,000 agents, one week, 630k lines: HF builds a weights-free Python chatbot — _lewtun · 2026-11-16
- One-person content agency targets $30K/mo with 11 AI agents — full playbook — VibeMarketer_ · 2026-11-16
- Hugging Face releases definitive fine-tuning guide for 3D generation model TRELLIS.2 — ariG23498 · 2026-11-16