Making Stop-Motion Videos with Codex, Astra and GPT Image 2.5

Melvin Vivas · X video post · 2026-09-16 · 0:31 · 686 views · Open on X

Topics: AI Dev Tools & Productivity, AI Agents, Tool Use & MCP · Level: beginner

Summary

A short demo with no narration. Melvin Vivas shows a stop-motion video made with OpenAI Codex. In the quoted post, he says he asked Astra to generate individual scenes with GPT Image 2.5 and then stitch them into a stop-motion video. He says he made no manual edits. The post shows that coding agents can run multi-step creative media pipelines, not just write code.

Key points

• Codex can handle more than code: it can coordinate image generation and video assembly from a single request.
• Workflow: use Astra inside Codex, ask it to generate scenes with GPT Image 2.5, then have it stitch the frames into a stop-motion video.
• The creator says he made no manual edits; the agent did the whole pipeline.
• Stop-motion fits this well because it is a sequence of still images, so an image model can make the frames and the agent can assemble them.
• The video is 31 seconds long, has no speech, and is a showcase rather than a step-by-step tutorial.

Resources mentioned

• OpenAI Codex · tool · openai.com · paid
  OpenAI's coding agent. In the diagram it writes code, fixes review findings and drives the build loop. The creator also used it to make this video.
  Also in: An agent bot that installs and drives Codex on its own (Melvin Vivas on X · notes), Asking a Coder bot to install Codex (Melvin Vivas on X · notes), Sign in with ChatGPT: Setting Usage Limits for Each App (Melvin Vivas on X · notes), Codex Cloud Environments Must Be Saved & Published Before Use (Melvin Vivas on X · notes) and 240 more
• GPT-6 Astra · tool · openai.com · paid
  The model announced in the quoted launch post, pitched as the developer's most capable model for work, coding, science and cybersecurity, and able to operate a computer.
  Also in: Customizing Your Coding Setup with Pi Coding Agent Extensions (Melvin Vivas on X · notes), Pi Agent Council: Ask Multiple LLMs in Parallel and Compare Their Advice (Melvin Vivas on X · notes), Use GPT-6.1 Sol by Default, Save Astra for Emergencies (Melvin Vivas on X · notes), Dots in ChatGPT: always-on AI agents that you hand responsibilities to (Melvin Vivas on X · notes) and 49 more
• GPT Image 2.5 · tool · openai.com · free
  An OpenAI image generation model, used here to make the stop-motion frames of the spaghetti scene.
  Also in: Making Stop-Motion Videos with Codex, Astra and GPT Image 2.5 (Melvin Vivas on X · notes), Will Smith Spaghetti Benchmark: Stop Motion with GPT Image 2.5 and Astra (Melvin Vivas on X · notes)

Try this

• Try asking Codex (via Astra) to generate a series of scenes with GPT Image 2.5 and stitch them into a stop-motion video.
• Build a stop-motion video entirely with a coding agent: generate the frames with an image model and have the agent stitch them into a video with no manual edits.