caiyuanhao1998/Open-DiffusionGS
Baking Gaussian Splatting into Diffusion Denoiser for Fast and Scalable Single-stage Image-to-3D Generation and Reconstruction (ICCV 2025)
This project helps artists, designers, and 3D modelers quickly generate realistic 3D objects and scenes from a single image or text description. You input a 2D image or a textual prompt, and it outputs a high-quality, editable 3D model. This is ideal for anyone needing rapid 3D content creation without extensive modeling experience, from game developers to architects.
823 stars.
Use this if you need to rapidly create detailed 3D models or reconstruct scenes from a single image or text, aiming for speed and scalability.
Not ideal if you require highly precise, manual control over every facet of a 3D model for professional-grade CAD or intricate animation.
Stars
823
Forks
38
Language
Python
License
MIT
Category
Last pushed
Jan 28, 2026
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/caiyuanhao1998/Open-DiffusionGS"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
jayin92/Skyfall-GS
Skyfall-GS: Synthesizing Immersive 3D Urban Scenes from Satellite Imagery
Tencent-Hunyuan/Hunyuan3D-2
High-Resolution 3D Assets Generation with Large Scale Hunyuan3D Diffusion Models.
ActiveVisionLab/gaussctrl
[ECCV 2024] GaussCtrl: Multi-View Consistent Text-Driven 3D Gaussian Splatting Editing
deepseek-ai/DreamCraft3D
[ICLR 2024] Official implementation of DreamCraft3D: Hierarchical 3D Generation with...
aminshabani/house_diffusion
The implementation of "HouseDiffusion: Vector Floorplan Generation via a Diffusion Model with...