VAST-AI-Research/TripoSplat

Health v2 · maintenance only

Flags: no_releases young

Adoption not part of the score

1232 stars · 140 forks observed · 2026-08-28

What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-30, confidence not recorded

TripoSplat is an inference-only Python library from TripoAI that converts a single 2D image into high-quality 3D Gaussian splats with a variable number of Gaussians (up to 262,144). It ships with minimal, readable code (~2,000 LOC across two files), near-zero dependencies, and official ComfyUI workflow support.

Use cases

• convert a single image into a 3D gaussian splat model
• generate 3D assets for game development from photos
• create 3D content for AR/VR applications from images
• build simulation environments with image-derived 3D objects
• integrate image-to-3D generation into a ComfyUI pipeline
• control gaussian count to trade quality against rendering cost

When to choose

• you need fast single-image to 3D gaussian splat generation without heavy dependencies
• you want a simple, hackable codebase to integrate into your own pipeline
• you need variable gaussian counts to balance quality and performance
• you work in ComfyUI and want an official image-to-gaussian-splat workflow

When to avoid

• you need to train or fine-tune the model yourself (use the separate TripoSplat-Training repo)
• you need textured meshes rather than gaussian splat representations
• you require multi-view or video input rather than a single image
• you have no GPU available for inference

Facets

library · maturity active

machine-learning image-processing graphics sdk computer-vision graphics artificial-intelligence python cross-platform image-to-3d gaussian-splatting 3d-reconstruction inference comfyui single-image-to-3d game-development gpu

Member repositories

For agents

markdown · JSON · MCP: product_card(name="VAST-AI-Research/TripoSplat")