ymxlzgy/commonscenes
[NeurIPS 2023] The repo of CommonScenes, a scene generation method powered by the diffusion model.
This project helps 3D artists, interior designers, or researchers quickly generate realistic 3D indoor scenes from a textual description of objects and their relationships. You input a 'scene graph' describing elements like 'a sofa is in front of a coffee table' and it outputs a complete 3D scene, including the layout and the 3D shapes of all objects. This is ideal for quickly prototyping virtual environments or populating simulations.
No commits in the last 6 months.
Use this if you need to programmatically create diverse and plausible 3D indoor scene layouts and object geometries from high-level descriptions.
Not ideal if you need to generate outdoor scenes, require extremely high-fidelity, photorealistic textures, or need fine-grained manual control over every detail of the scene's composition without a programmatic approach.
Stars
96
Forks
4
Language
Python
License
—
Category
Last pushed
Jun 04, 2024
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/ymxlzgy/commonscenes"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
PRIS-CV/DemoFusion
Let us democratise high-resolution generation! (CVPR 2024)
mit-han-lab/distrifuser
[CVPR 2024 Highlight] DistriFusion: Distributed Parallel Inference for High-Resolution Diffusion Models
Tencent-Hunyuan/HunyuanPortrait
[CVPR-2025] The official code of HunyuanPortrait: Implicit Condition Control for Enhanced...
giuvecchio/matfuse
MatFuse: Controllable Material Generation with Diffusion Models (CVPR2024)
Shilin-LU/TF-ICON
[ICCV 2023] "TF-ICON: Diffusion-Based Training-Free Cross-Domain Image Composition" (Official...