RafailFridman/SceneScape
Official Pytorch Implementation for "SceneScape: Text-Driven Consistent Scene Generation"
This tool helps 3D artists, game designers, or architects quickly create immersive, persistent video walkthroughs of imagined indoor environments. You provide a text description (e.g., 'a spaceship corridor' or 'an ice castle') and camera movement instructions. The output is a video showing a continuous, geometrically consistent journey through that scene, perfect for pre-visualization or concept art.
162 stars. No commits in the last 6 months.
Use this if you need to rapidly generate long, continuous video walkthroughs of various indoor scenes described by text, such as for architectural visualization, game level design, or virtual reality environments.
Not ideal if you need to generate outdoor scenes, videos with dynamic elements like moving characters or objects, or if you require very quick generation times for high-frame-rate videos.
Stars
162
Forks
9
Language
Python
License
—
Category
Last pushed
Jun 14, 2023
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/RafailFridman/SceneScape"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
hao-ai-lab/FastVideo
A unified inference and post-training framework for accelerated video generation.
ModelTC/LightX2V
Light Image Video Generation Inference Framework
thu-ml/TurboDiffusion
TurboDiffusion: 100–200× Acceleration for Video Diffusion Models
PKU-YuanGroup/Helios
Helios: Real Real-Time Long Video Generation Model
PKU-YuanGroup/MagicTime
[TPAMI 2025🔥] MagicTime: Time-lapse Video Generation Models as Metamorphic Simulators