thu-ml / thu-ml/TurboDiffusion

DreamX-World: A General-Purpose Interactive World Model

Open
#135 0 comments 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

Dominant language
Python
Stars
3.7k
Forks
277
Avg merge
2h 57m
Merged PRs (30d)
2

Description

Hi TurboDiffusion team,

Your acceleration results are highly relevant to interactive world models.

We recently open-sourced AMAP-ML/DreamX-World, an interactive text/image-to-video world model where speed is tied not only to visual fidelity, but also to camera-following accuracy, scene memory, and stable autoregressive rollout.

In our setting, acceleration quality becomes especially important when users navigate through a generated world, revisit earlier viewpoints, or trigger promptable events over time.

If there is a suitable place for related community examples, we would be glad to contribute DreamX-World cases around fast controllable video generation and long-horizon consistency.

Thanks for the great work on efficient diffusion.

Contributor guide

No contributing guide indexed for this repository

First steps

  1. Read the whole issue, then the project's contributing guide.
  2. Comment on the issue to say you are picking it up — it saves two people doing the same work.
  3. Fork the repository and make your change on a branch.
  4. Open a pull request that references the issue number.

Research direction

The issue proposes adding DreamX-World examples but names no files, tests, or entry points in TurboDiffusion. First clarify whether community examples are wanted and where they should live; the work is done only once a concrete example scope and integration location are agreed.

Written by the indexing model from the issue text.

Assessment

Tech stack
python
Domain
ai, machine-learning
Issue type
Feature
Difficulty
5/5
Estimated time
Over a week
Activity status
Quiet
Clarity
Needs clarification
Newbie friendliness
20/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.