3D objects

Models 8

• Gen 3
  TripoSplat

  By Tripo AI

  TripoSplat is TripoAI / VAST AI Research’s MIT-licensed image-to-3D model for converting a single 2D image into variable-count 3D Gaussians.

  🎲3D objects🔮Augmented reality🎮3D game assets🎥3D scenes
  NewMultimodal

  Released 1mo ago
• Gen 3
  Pixal3D

  By Tencent

  Pixal3D is Tencent ARC Lab and collaborators’ image-to-3D generation model for creating high-fidelity 3D assets from a single image. It explicitly lifts pixel features into 3D through back-projection, enabling direct pixel-to-3D correspondence, detailed geometry, and PBR textures.

  🌍3D images🎲3D objects🎮3D characters
  NewMultimodal

  Released 2mo ago
• Gen 4
  Seed3D 2.0

  By ByteDance

  Seed3D 2.0 is ByteDance Seed’s upgraded 3D asset generation model for creating higher-precision, more usable 3D content. It is positioned as the latest model in the Seed3D line, aimed at improving quality, practicality, and creator workflow efficiency for 3D generation tasks.

  🖌️3D🌐2D to 3D image conversion🎲3D objects🎨3D textures
  NewImage

  Released 2mo ago
• Gen 1
  AniGen

  By VAST AI Research

  AniGen is VAST-AI’s unified 3D generation framework for creating fully rigged, animate-ready 3D assets from a single image. It jointly generates shape, skeleton, and skinning in one pipeline, aiming to produce meshes that can be imported into standard 3D workflows and driven by off-the-shelf motion data for animation, simulation, and embodied AI use cases.

  🖌️3D🎥3D animations🎲3D objects🎮3D characters
  3d

  Released 3mo ago
• Gen 3
  Asset Harvester

  By NVIDIA

  Asset Harvester is NVIDIA’s open framework for extracting reusable 3D assets from sparse autonomous-driving observations. It turns one or a few in-the-wild object views from driving logs into complete, simulation-ready 3D assets, even under occlusion, noisy calibration, and viewpoint bias.

  🎲3D objects🎥3D scenes🚗Autonomous driving
  Multimodal

  Released 3mo ago
• Gen 1
  Tripo H3.1

  By Tripo AI

  Tripo H3.1 is Tripo’s high-detail 3D generation model for producing production-ready assets from text or reference images. It is designed for hero assets, marketing visuals, rendering, and 3D printing, with much denser geometry, stronger surface detail, and closer-to-final visual fidelity than typical fast AI 3D generators.

  🖌️3D🌍3D images🎲3D objects🎮3D game assets🎨3D textures
  3d

  Released 3mo ago
• Gen 1
  Tripo3D P1.0

  By Tripo AI

  Tripo P1.0, also called Smart Mesh P1.0, is Tripo’s structured mesh-generation model for producing clean, low-poly topology in about 2 seconds. It is built for optimized, lightweight 3D meshes suitable for game engines, web use, and real-time production workflows where topology cleanliness matters more than maximum geometric detail.

  🖌️3D🎮Game assets🎲3D objects🎮3D game assets
  3d

  Released 3mo ago
• Gen 3
  LiTo

  By Apple

  LiTo is Apple’s research image-to-3D model and tokenizer for generating 3D objects with unified geometry and view-dependent appearance.

  🖌️3D🌍3D images🎲3D objects
  Multimodal

  Released 4mo ago