xxlong0/Wonder3D

Health v2 · maintenance only

Flags: no_releases

Adoption not part of the score

5425 stars · 439 forks observed · 2026-08-28

What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-29, confidence not recorded

Wonder3D is a cross-domain diffusion model that reconstructs high-fidelity textured 3D meshes from a single image in 2-3 minutes. It generates consistent multi-view normal maps and color images, then fuses them via a geometry-aware normal fusion algorithm.

Use cases

• convert a single photo into a 3D model
• generate textured mesh from one image
• reconstruct 3D geometry from a single-view image
• create multi-view normal maps from an image
• fast image-to-3D asset generation for games
• 3D content creation from photos

When to choose

• you need fast (2-3 minute) single-image to 3D reconstruction
• you want high-quality textured meshes with detailed geometry
• you need a research-grade image-to-3D pipeline with a Hugging Face demo
• you want multi-view consistency without slow per-shape SDS optimization

When to avoid

• you need production-grade 3D generation at scale
• you require editable, artist-ready topology rather than fused meshes
• you cannot run GPU inference locally
• you need a native 3D diffusion model rather than a 2D multi-view approach

Facets

library · maturity active

machine-learning deep-learning image-processing graphics stable-diffusion computer-vision graphics artificial-intelligence deep-learning python cross-platform 3d-generation image-to-3d diffusion-model multi-view mesh-reconstruction normal-maps cvpr-2024 textured-mesh gpu linux

Member repositories

For agents

markdown · JSON · MCP: product_card(name="xxlong0/Wonder3D")