vivoCameraResearch/Magic-World
official code for "magicworld: towards long-horizon stability for interactive video world exploration"
This project helps creators, designers, or visual artists transform a single still image into an interactive, explorable video world. You provide one scene image and then navigate through it using keyboard controls (W, A, S, D), generating a dynamic video that maintains visual consistency. The tool is ideal for quickly prototyping virtual environments or exploring creative scene variations.
Use this if you want to generate a stable, interactive video exploration from a single static image, allowing you to 'walk through' and dynamically interact with the scene.
Not ideal if you need to create entirely new 3D models or highly complex, physics-driven simulations rather than extending an existing 2D image into a navigable video.
Stars
30
Forks
1
Language
Python
License
Apache-2.0
Category
Last pushed
Mar 21, 2026
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/vivoCameraResearch/Magic-World"
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