ActiveVisionLab/gaussctrl
[ECCV 2024] GaussCtrl: Multi-View Consistent Text-Driven 3D Gaussian Splatting Editing
This project helps 3D artists, designers, and visual effects professionals modify existing 3D scenes using simple text descriptions. You provide a set of images of a real-world object or scene and a text prompt describing the desired change (e.g., "make it rusty" or "add flowers"). The output is a new 3D model with the specified edits, maintaining a consistent look from all angles.
131 stars.
Use this if you need to quickly and intuitively edit specific objects or entire environments within a 3D scene using natural language, rather than complex 3D modeling software.
Not ideal if you need precise, pixel-level control over intricate 3D model geometry or if you're working with complex animations.
Stars
131
Forks
13
Language
Python
License
BSD-3-Clause
Category
Last pushed
Mar 18, 2026
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/ActiveVisionLab/gaussctrl"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Related models
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.
caiyuanhao1998/Open-DiffusionGS
Baking Gaussian Splatting into Diffusion Denoiser for Fast and Scalable Single-stage Image-to-3D...
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...