Project ◆ Hidden gem
TripoSR
VAST-AI-Research/TripoSR · Python · MIT
Fast feed-forward image-to-3D
TripoSR prioritizes speed: drop an image, get a mesh quickly for blocking out game assets.
57.6 / 100 · Score
★ 7.1k Stars
+64 30-day growth
20 min Time to first run
Not required API key
Score
Trend 61
Activity 9
Quality 65
Community 41
Relevance 100
Setup at a glance
DeployCli
GPU6 GB
API keyNot required
UI languages
Doc languagesen
Install
pip install triposr Deep dive
TripoSR is a fast single-image-to-3D reconstruction model from VAST AI Research (with Stability AI collaboration): one photo in, a textured 3D model out in under a second on a capable GPU.
It builds on the LRM (Large Reconstruction Model) line of research — feed-forward 3D reconstruction without per-object optimization — which is what makes it fast enough for interactive use.
The repo is a compact, pip-installable inference stack with clear requirements (Python 3.8+, CUDA, PyTorch), so it drops into existing 3D tooling; the approach is documented in an arXiv paper.
Use cases
Rapid prop drafts
Concept-to-mesh
Pipeline smoke tests
Good for / Not ideal for
Good for
Designers iterating quickly
Not ideal for
Final hero assets needing perfect topology