Best 3D
Models that generate three-dimensional assets from images or text, producing detailed meshes and textures suitable for games, product visualisation, and spatial computing workflows.
Best rated
by Tripo AI
Tripo 3D v3.1 is a high-fidelity 3D generation model that creates production-ready 3D assets from text prompts or images. It delivers enhanced detail, stronger geometry precision, and improved texture quality compared to earlier versions, with support for PBR materials and export in GLB, FBX, OBJ, and STL formats.
Featured Models
Top-performing models in this category, recommended by our community and performance benchmarks.
Hunyuan 3D 3.1 Pro is a production-grade 3D generation model from Tencent that creates high-fidelity assets from text prompts or images. It uses enhanced 8-view reconstruction for improved spatial accuracy and reduced geometric artifacts, producing clean topology, watertight meshes, and PBR materials suitable for game development, 3D printing, and professional animation workflows.
Hunyuan 3D 3.1 Rapid is a speed-optimized 3D generation model from Tencent designed for fast prototyping and iteration. It generates 3D assets from text prompts or single images in seconds, producing clean meshes with PBR materials. Ideal for concept evaluation, rapid asset library building, and early-stage design workflows where speed is prioritized over maximum geometric detail.
by Meshy
Meshy-6 is a 3D generation model for text-to-3D and image-to-3D workflows. It is built for cleaner geometry, sharper hard-surface detail, low-poly generation, configurable quad or triangle topology, polycount and symmetry control, A/T pose support, and textured outputs with optional PBR materials. It fits game asset creation, 3D printing, and production-oriented 3D pipelines.
by Microsoft
TRELLIS.2 is a 4-billion-parameter 3D generative model that transforms 2D images into fully textured 3D assets with complex topology, sharp features, and physically based rendering materials. It uses a novel field-free sparse voxel representation and scalable structured latent space to enable efficient, high-resolution 3D generation from single image input.
by Meta
SAM 3D Objects is a foundation 3D model from Meta that reconstructs full 3D shape geometry, realistic texture, and scene layout of objects from a single RGB image. It produces high-fidelity 3D meshes robustly even in cluttered, occluded real-world scenes, and significantly outperforms prior single-image 3D methods. SAM 3D Objects is part of the broader SAM 3D family, enabling 2D-to-3D reconstruction workflows for visualization, AR/VR, robotics, and digital content creation.
by Hyper3D
Rodin Gen-2 is a 10 billion parameter 3D generation model from Hyper3D built on the BANG architecture. It creates production-ready assets from text prompts or up to 5 input images, with 4x geometry improvement over Gen-1. It supports quad-dominant and raw mesh modes, PBR and shaded materials, configurable polygon counts, T/A pose control, bounding box constraints, and output in GLB, FBX, OBJ, USDZ, and STL formats.