No After Effects needed: a 5-layer prompt has Claude script, Gemini voice and Remotion render motion graphics
aziz4ai · x · 2026-10-18
Saudi AI creator aziz4ai (43K followers) shows a motion-graphics workflow with no After Effects or Premiere — everything written via prompt. The idea: treat AI motion video as a full team you direct.
- The team: Claude writes the script and turns each scene into animation code; Gemini TTS reads the voiceover in your dialect; Nano Banana generates elements and images; Remotion renders the final MP4. Claude orchestrates the rest.
- A strong motion prompt has 5 layers: goal (what message, what should the viewer see), style (colors, a reference video saves 100 lines of description), scenes (what happens each second), motion (speed, easing, transitions — easing separates amateur from agency-grade), output specs (e.g. 1080×1920, 60s, 30fps).
- Three pro secrets: sound is half the motion — sound effects per action, hits on music beats; motion follows the timed script; make the AI review its own work by screenshotting frames and fixing errors before render.
The full adaptable prompt is in the follow-up post; works best where Claude can run code (e.g. Claude Code).
Related event: Claude + Remotion Workflow Replaces AE/PR for Animation(2 posts)→
More from coding & agent
- One founder's week on personal AI agents: taxes filed, Hamilton tickets, and an honest purchase scoreboard — altryne · 2026-10-18
- Shopify's Tobi Lütke: 'We are all verification engineers now' as agents become the third customer — schwentker · 2026-10-18
- Shopify CEO Tobi Lütke: "We are now all verification engineers" — schwentker · 2026-10-18
- Anthropic researcher on agent memory: "dreaming" aggregates memories from past sessions — schwentker · 2026-10-18
- Voice demo built with Jev draws "holy crap, that's the missing thing to get rid of keyboards" reaction — schwentker · 2026-10-18
- Agents reach llms.txt in only 32% of cases; 86% of those via site links — schwentker · 2026-10-18