Image-to-3D first, then GPT splits and rigs: a better Blender 3D workflow
dotey · x · 2026-09-07
- Directly asking GPT-6 Astra to build 3D models (especially character designs) is still underwhelming. The author's workflow: generate a high-detail whole model with an image-to-3D AI model, export as glb, then have GPT split it into components and add a skeleton for animation.
- Demo video included; a detailed tutorial is promised.
More from coding & agent
- Dev demos AI models handling 3D objects and animations surprisingly well — chongdashu · 2026-10-23
- Jason Kneen burns 104.56B tokens and $24.7K in 304 days of AI coding on Codex and Claude Code — jasonkneen · 2026-10-23
- Typosquatted Blender MCP Repo Hit 958 Stars in Days and Silently Ran Malware — Promptmethus · 2026-10-23
- Benchmarking 56 fresh dependency bugs: MCP routing lifts Claude Code accuracy 68% to 91% — Available_Side_7134 · 2026-10-23
- Swapping only the eval harness moves results 30%: designing agent evals like a scientist — AI Engineer · 2026-10-23
- Med student builds a whole-library RAG with Cognee; single-book ingestion still freezes his machine — shrike293103 · 2026-10-23