Image-to-3D Tools
Image-to-3D technology converts photographs or other two-dimensional images into three-dimensional representations, such as meshes, textured objects, or scene layouts. It can help creators build digital assets when a model is unavailable, reduce manual modeling work, and infer shape and appearance from visual input. Results vary with image quality, viewpoint, and the complexity of the subject, so generated geometry may need editing before use.
2 repositories · updated January 14, 2026
PartCrafter: Structured 3D Mesh Generation via Compositional Latent Diffusion Transformers
PartCrafter is an innovative structured 3D generative model that enables the creation of complex 3D meshes and scenes from a single RGB image. Accepted at NeurIPS 2025, this project leverages compositional latent diffusion transformers to jointly generate multiple parts and objects in one shot. It offers powerful capabilities for both 3D object and scene generation, making it a valuable tool for researchers and developers in the field.
HunyuanWorld-1.0: Generating Immersive 3D Worlds from Text or Pixels
HunyuanWorld-1.0 is an innovative GitHub repository from Tencent-Hunyuan, designed for generating immersive, explorable, and interactive 3D worlds. It leverages advanced models to create detailed 3D environments directly from text descriptions or input images. This project aims to overcome limitations in existing 3D world generation by offering 360° immersive experiences and mesh export capabilities.