Will Smith Spaghetti Benchmark: Stop Motion with GPT Image 2.5 and Astra
Melvin Vivas · X video post · 2026-09-09 · 0:17 · 393 views · Open on X
Topics: Industry Trends & Job Market · Level: beginner
Summary
A 17-second demo with no narration. It shows a new take on the informal "Will Smith eating spaghetti" benchmark, a meme used to track how much AI image and video generation has improved. The creator made a stop-motion clip by generating frames with GPT Image 2.5 and putting them together with a tool called Astra. It shows what current tools can do, but it doesn't explain how the clip was made.
Key points
- "Will Smith eating spaghetti" is a community meme benchmark. People use it to compare AI image and video generation quality over time.
- This version is a stop-motion clip, not a video generated directly from a prompt.
- The frames were made with GPT Image 2.5, the image model named in the quoted post.
- Astra was used with GPT Image 2.5 to turn the frames into the stop-motion clip. The post doesn't explain exactly what Astra did.
- The clip has no speech or tutorial. It's a showcase of what the tools can do, not a how-to.
Resources mentioned
- 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), Making Stop-Motion Videos with Codex, Astra and GPT Image 2.5 (Melvin Vivas on X · notes) - 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
Try this
- Make a short stop-motion clip by generating consistent frames with an image model and putting them together as an animation.
More in Industry Trends & Job Market
- DeepSeek-V4.1-Flash Released: Smallest, Faster DeepSeek Model
- Grok Release Cadence: About One New Version per Month
- AuK: Tencent Hunyuan's Unified Audio Generation and Editing Model (TTS Demo)
- ChatGPT Images 2.5 (GPT Image 2.5): What's New in OpenAI's Image Update
- Meta Launches Muse, a Personal AI Agent (and the Manus Connection)
- GPT-6 Astra Announced: Computer Use, Coding and Math