3D images

Models 7

• Gen 4
  D4RT

  By Google

  D4RT is DeepMind’s unified 4D scene reconstruction and tracking model that turns ordinary videos into a fast, queryable representation of 3D geometry and motion, solving tracking, depth and pose up to hundreds of times faster than prior work.

  🌍3D images🔊Text to speech🎮Game creation🎬Video editing
  NewImage

  Released 2mo ago
• Gen 4
  VIGA

  By Fugtemypt123

  VIGA is a vision-as-inverse-graphics agent that rebuilds a single image as an editable 3D Blender scene, alternating generator and verifier roles with interleaved multimodal reasoning to capture objects, layout, physics and interactions.

  🌍3D images🔍Image recognition🎥YouTube thumbnails
  NewImage

  Released 2mo ago
• Gen 4
  UltraShape 1.0

  By PKU-YuanGroup

  UltraShape 1.0 is a two-stage diffusion framework for high-fidelity 3D shape generation, using a scalable geometric refinement and watertight processing pipeline to preserve fine geometric details.

  🖼️Image generation🌍3D images
  Image

  Released 3mo ago
• Gen 4
  TRELLIS 2

  By Microsoft

  TRELLIS.2 is a 4B-parameter open-source image-to-3D model from Microsoft that turns a single image into high-resolution, PBR-textured 3D assets using a compact native 3D VAE latent space for efficient, high-fidelity asset generation.

  🌍3D images🖼️Image generation
  Image

  Released 3mo ago
• Gen 4Hunyuan
  HunyuanWorld 1.0

  By Tencent

  Tencent Hunyuan 3D, powered by the Hunyuan 3D Generate Large Model 2.5, is a 3D AI engine that turns text, images and sketches into low-poly 3D assets and scenes, supporting text-to-3D, image-to-3D, animation and texture generation in the browser.

  🌍3D images🖼️Image generation
  Image

  Released 3mo ago
• Gen 4
  Seed3D 1.0

  By ByteDance

  Seed3D 1.0 is a text and image to 3D asset model. It creates meshes with UVs and PBR textures from prompts or references, supports quick edits and relighting, and exports to GLB, FBX, or USD for game, AR, and product workflows.

  🌍3D images🖼️Image generation🔎Image searching with facial recognition
  Image

  Released 5mo ago
• Gen 3Hunyuan
  Hunyuan3D-2

  By Tencent

  Hunyuan3D-2 is Tencent’s second-generation text-to-3D model. It creates detailed 3D assets directly from natural language prompts or reference images, with higher fidelity, cleaner topology, and faster generation than its predecessor—suited for games, AR/VR, and digital content pipelines.

  🌍3D images🖼️Image generation
  Image

  Released 1y ago