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.
More from coding & agent
- Building a buyer agent that negotiates 8 seller agents: what broke and what fixed it — mv_soura · 2026-10-31
- PostTrainBench traces hit 104k monthly downloads — author warns it's likely reward hacking — maksym_andr · 2026-10-31
- Building games with AI? Set up a 'tech art' test scene to tune your look fast — chongdashu · 2026-10-31
- Sanity open-sources pi-mcp-events: streaming MCP Events client for the Pi agent harness — knutmelvaer · 2026-10-31
- Skydive opens to all: watch your AI coworkers work in a 3D office — Scobleizer · 2026-10-31
- LangChain SF meetup: decision models and a third path for agent evals — LangChain · 2026-10-31