Moxin-Tech/moworld_base

Get alerts like this View on GitHub Share on X

Can I trust it?

Be careful with this one.

Stars from real accounts No data
We haven't checked its stars for fakes yet.
Active OK
Last change 4 days ago.
Licence Careful
No licence: legally you can't reuse the code, unless the README says otherwise.

Quick checks from public data. They help, but they are no guarantee.

What it is

A research codebase for MoWorld, a flash world model that generates real-time interactive video from a first frame, a text prompt and camera controls. It covers training on Ascend NPUs with few-step autoregressive generation and reports up to 50 FPS inference in the paper's…

Who it's for

Researchers and engineers working on video world models and camera-controlled video generation on Ascend NPUs

How to use it

Ask your AI to set it up

Paste this into Claude, ChatGPT or your coding assistant.

Help me install and set up Moxin-Tech/moworld_base in my project. Follow its README: https://github.com/Moxin-Tech/moworld_base. Explain each step and check it is safe before running anything.

Read the README

Star curve

279From 0 to 279 stars between 15 Sept 2026 and 20 Oct 2026.

Get alerts for repos like this

We'll email you when something in Models & inference starts rising. Free, once a week, only what matches.

18,263 GitHub repos watched and ranked every hour. Figures as of 20 October 2026.

What arrives: one email on Mondays with the repos that match, never more. See last week's. Privacy

For maintainers

Add this badge to your README. It shows the repo's place on the radar, updates every hour and links back to this page.

[![Moxin-Tech/moworld_base on RepoAlerts](https://repoalerts.com/badge/Moxin-Tech/moworld_base.svg)](https://repoalerts.com/repo/Moxin-Tech/moworld_base?ref=badge)

Share on X

code-video-model/CodeVideoModel
A research codebase for generating videos from editable Three.js scenes. It produces Three.js code from text prompts, renders proxy videos, creates reference images, and runs the MiniMax-H3 model to p
Models & inferencePython · 593 stars · +172 this week · 39 days old
ziplab/ATAS
A Python framework for agentic video generation that keeps a persistent world state across a whole film. A screenplay is compiled into bounded shot requests, each shot is rendered from scene memory an
Creative toolsPython · 302 stars · +301 this week · 9 days old
NVlabs/ASPIRE
A research framework for robotics in which language-model coding agents discover and refine sensorimotor skills through iterative debugging and evolutionary search, instead of gradient-based training.
AI agentsPython · 748 stars · +475 this week · 104 days old
mw00/project-maya
A C++ engine, server and dashboard for running the GLM-5.3-Flash and DeepSeek-V4.1-Flash models locally on one to sixteen NVIDIA or AMD GPUs, on Linux or Windows. It offers OpenAI- and Anthropic-compa
Models & inferenceC++ · 1,225 stars · +482 this week · 14 days old
VAST-AI-Research/EdenLive
Real-time generative renderer that turns a reference video from an interactive program into detailed frames, guided by a target first frame and a text prompt. Provides 5B and 14B model weights, stream
Creative toolsPython · 259 stars · +197 this week · 9 days old
shengshu-ai/Motus2
A research world model for robotic dexterous manipulation that uses one shared-weight model as a policy proposing action chunks, a simulator predicting their visual outcomes, and an evaluator scoring
AI agents660 stars · +436 this week · 39 days old