A newly shared workflow inside OpenAI's Codex platform chains two skills to convert a text prompt into an interactive, browser-runnable 3D object — reportedly consuming less than 1% of a weekly token allowance. The pipeline pairs Codex's built-in ImageGen skill with an open-source skill called img2threejs, driven by GPT-5.6 Luna at its maximum effort setting, to produce low-poly 3D assets that run directly in the browser via Three.js.
Continue reading
The rest of this article is for AI News Blitz readers. Choose an option below to keep reading.
Already purchased? Sign in✓ Signed in — this article isn’t included in your current plan.
Unlocking the full article...
Contact us
Questions, corrections, or ideas? Send us a message here. We aim to reply by email within 24 hours.
Thank you. Your message has been sent. We aim to reply by email within 24 hours.Please enter your email address and a message.We could not send your message. Please try again in a little while.