GradientSpaces/respace
Code for "ReSpace: Text-Driven 3D Indoor Scene Synthesis and Editing with Preference Alignment"
This project helps interior designers and architects rapidly prototype and modify 3D indoor scene layouts using simple text commands. You provide a general description or an existing scene layout, and it generates a detailed 3D arrangement of furniture and objects. The output is a refined 3D scene model, complete with specific asset placements, ready for visualization. This is designed for professionals creating and editing interior spaces.
Use this if you need to quickly generate or edit detailed 3D indoor scene layouts by simply typing what you want, like "add a modern wooden wardrobe" or "swap the sofa for a loveseat."
Not ideal if you require precise manual control over every minute geometric detail of an individual object's placement or if you are working with outdoor or non-architectural 3D environments.
Stars
63
Forks
4
Language
Python
License
—
Category
Last pushed
Dec 09, 2025
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/GradientSpaces/respace"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
zai-org/CogVideo
text and image to video generation: CogVideoX (2024) and CogVideo (ICLR 2023)
zhaorw02/DeepMesh
[ICCV 2025] Official code of DeepMesh: Auto-Regressive Artist-mesh Creation with Reinforcement Learning
YangLing0818/RPG-DiffusionMaster
[ICML 2024] Mastering Text-to-Image Diffusion: Recaptioning, Planning, and Generating with...
thu-nics/FrameFusion
[ICCV'25] The official code of paper "Combining Similarity and Importance for Video Token...
Yushi-Hu/tifa
TIFA: Accurate and Interpretable Text-to-Image Faithfulness Evaluation with Question Answering