Adding an image reference to skill-based 3D generation: 153k to 252k tokens, better details

chaseleantj · x · 2026-09-13

Continuing his 3D generation experiment with the same prompt: with a skill but no image reference, the run took 77 minutes and 153k output tokens; with skill plus an image reference, 81 minutes and 252k tokens.

The reference-image version has much better details, though lighting suffered slightly. The reference can be a real photo, a AAA game screenshot, or AI-generated — he made his with gpt-image-2.5-sunburst.

Related event: AI Can't One-Shot Polished 3D: Manual Iteration and Reference Images Are Key(2 posts)→

Original post →

More from coding & agent

coding & agent channel →