#3d-generation Repositories
Discover 54 active open source GitHub repositories tagged with #3d-generation, accumulating 118,348 total stars (averaging 2,191 stars per project). Leading this topic is Tencent-Hunyuan/Hunyuan3D-2 with 15,208 stars.
54 repositories total
High-Resolution 3D Assets Generation with Large Scale Hunyuan3D Diffusion Models.
Official repo for paper "Structured 3D Latents for Scalable and Versatile 3D Generation" (CVPR'25 Spotlight).
From Images to High-Fidelity 3D Assets with Production-Ready PBR Material
[ICLR 2024] Official implementation of DreamCraft3D: Hierarchical 3D Generation with Bootstrapped Diffusion Prior
Generating Immersive, Explorable, and Interactive 3D Worlds from Words or Pixels with Hunyuan3D World Model
[NeurIPS 2025] PartCrafter: Structured 3D Mesh Generation via Compositional Latent Diffusion Transformers
[NeurIPS 2023] MotionGPT: Human Motion as a Foreign Language, a unified motion-language generation model using LLMs
[ICCV 2023] Make-It-3D: High-Fidelity 3D Creation from A Single Image with Diffusion Prior
[NeurIPS 2023] Official code of "One-2-3-45: Any Single Image to 3D Mesh in 45 Seconds without Per-Shape Optimization"
TripoSG: High-Fidelity 3D Shape Synthesis using Large-Scale Rectified Flow Models
[ICLR'24] Official PyTorch Implementation of Magic123: One Image to High-Quality 3D Object Generation Using Both 2D and 3D Diffusion Priors
Voyager is an interactive RGBD video generation model conditioned on camera input, and supports real-time 3D reconstruction.
๐ฆPortable package for running Hunyuan3D 2.0/2.1 on Windows. | Hunyuan 3D 2.0/2.1 integrated package
A comprehensive open-source 3A game-generation skill and asset framework.
[NeurIPS 2025] Direct3DโS2: Gigascale 3D Generation Made Easy with Spatial Sparse Attention
[ICCV 2025] Official impl. of "MV-Adapter: Multi-view Consistent Image Generation Made Easy"
AssetFurnace: the most complete open-source image-to-3D pipeline (Oct 2026). Prompt or picture โ textured, rigged, animated game character, locally on Apple Silicon or NVIDIA. Pixal3D, TRELLIS.2, Hunyuan3D, SF3D, auto-rigging, and 21 moves. For indie game developers and 3D artists. Free, Apache-2.0.
Official implementation of "MoMask: Generative Masked Modeling of 3D Human Motions (CVPR2024)"
[CVPR 2025 Highlight] 3DTopia-XL: High-Quality 3D PBR Asset Generation via Primitive Diffusion
[ICCV 2025] From anything to mesh like human artists. Official impl. of "MeshAnything V2: Artist-Created Mesh Generation With Adjacent Mesh Tokenization"
MotionDiffuse: Text-Driven Human Motion Generation with Diffusion Model
[CVPR 2025] MIDI: Multi-Instance Diffusion for Single Image to 3D Scene Generation
Step1X-3D: Towards High-Fidelity and Controllable Generation of Textured 3D Assets
Baking Gaussian Splatting into Diffusion Denoiser for Fast and Scalable Single-stage Image-to-3D Generation and Reconstruction (ICCV 2025)
Generate large-scale explorable 3D scenes with high-quality panorama videos from a single image or text prompt.
CraftsMan: High-fidelity Mesh Generation with 3D Native Diffusion and Interactive Geometry Refiner
[SIGGRAPH 2025] Diffusion as Shader: 3D-aware Video Diffusion for Versatile Video Generation Control
Design workspace for programmable 3D. Nova builds assets and worlds as editable, versioned programs: parametric, articulated, and simulation-ready, compiled for CAD tools, 3D applications, and robotics simulators.
Official Hi3D v1.0: high-resolution 3D geometry refinement built on Sparc3D. Inference code, model weights, and documentation.
[CVPR'25 Highlight] You See it, You Got it: Learning 3D Creation on Pose-Free Videos at Scale
The official implementation of "CityDreamer: Compositional Generative Model of Unbounded 3D Cities". (CVPR 2024)
A Collection of Papers and Codes for CVPR2026/CVPR2025/ICCV2025/CVPR2024/ECCV2026/ECCV2024 AIGC
(ICLR2026) ReconViaGen: Towards Accurate Multi-view 3D Object Reconstruction via Generation
Hunyuan3D-Omni: A Unified Framework for Controllable Generation of 3D Assets
[SIGGRAPH 2026] AniGen: Unified S^3 Fields for Animatable 3D Asset Generation
[ICCV 2025 & TPAMI] VistaDream: Sampling Multiview-Consistent Images for Single-View Scene Reconstruction
[CVPR 2024 Highlight] XCube: Large-Scale 3D Generative Modeling using Sparse Voxel Hierarchies
Frequently Asked Questions
What is the most popular #3d-generation repository on GitHub?
The top ranked open source #3d-generation project on GitHub is Tencent-Hunyuan/Hunyuan3D-2 with 15,208 stars. High-Resolution 3D Assets Generation with Large Scale Hunyuan3D Diffusion Models.
Which programming languages are most used in #3d-generation repositories?
Among the top ranked #3d-generation projects on GitHub, the most common programming languages are Python, Jupyter Notebook, Batchfile, HTML.
How is the #3d-generation repository ranking calculated?
We track 54 active open source repositories tagged with #3d-generation (500+ stars), totaling 118,348 stars with an average of 2,191 stars per repository. Rankings update daily from the GitHub API.