Open-source image-to-3dlab fixes garbled text in image-to-3D, runs fully locally
Scobleizer · x · 2026-10-31
Developer Bingeljell released image-to-3dlab (AssetFurnace), an Apache-2.0 open-source pipeline with 1k GitHub stars. Free image-to-3D models typically garble text, logos and fine detail; the new 'Pixel Match' feature copies actual pixels from the source image onto the model, even after retopology down to 5k faces, yielding riggable, animatable low-poly assets.
The pipeline chains Pixal3D, TRELLIS.2, Hunyuan3D (with an MLX port), and SF3D to turn a prompt or picture into a textured, rigged game character with 21 animations, running locally on Apple Silicon or NVIDIA. The author says it approaches Tripo/Meshy-level output while staying free and local, and invites testing, issues and PRs.
More from coding & agent
- The Sims made $5B on watching chores—why agent software needs spatial dashboards — aakashgupta · 2026-10-31
- JetBrains ships free Junie lite coding agent running Qwen 27B on your real repo — dr_cintas · 2026-10-31
- Evaluating enterprise voice agents: caller simulation choices swing accuracy by 5% — rdesh26 · 2026-10-31
- Proton CTO's AI manifesto: stop improving your code with LLMs, improve the LLM's code — dair_ai · 2026-10-31
- Debate: Opus 5.5 reportedly performs better in Cursor than in Claude Code — prasenx · 2026-10-31
- Over 90% of Copilot queries now use Auto to route across models — clamanna · 2026-10-31