Published by Video Runtime · Source check 2026-09-14 · Evidence method · Suggest a correction
EDITORIALLY VERIFIED PRODUCT INFORMATION
About DreamX-World
A general-purpose action-controlled video world model with open-ended event response and long-rollout training. Progressively trains camera control and event response, adds reinforcement learning for action following, and applies forcing and distillation for inference.
Key features
Publishes code, a 5B checkpoint, technical report, long-horizon examples and an official hosted experience.
Getting started
Install the repository dependencies, download Wan2.2-5B-TI2V and the DreamX checkpoint, then follow the supplied inference configuration; use the separate official website for hosted access.
Real-time interaction
Progressively trains camera control and event response, adds reinforcement learning for action following, and applies forcing and distillation for inference.
Pricing
Apache-2.0 code; self-hosted compute costs extra Repository code is published under Apache-2.0. Confirm separate model, dataset and dependency terms before reuse. No hosted price is inferred. Budget for the documented GPU, storage and setup requirements.
Limitations
The repository's published 5B camera-model table lists 509 seconds for a five-second 720p sample on one H20, so the downloadable path must not be described as independently real-time.
EDITORIAL VIEW
Editor's Verdict
DreamX-World is included as a source-available implementation relevant to real-time generative video or interactive world systems.
Run the supplied example on representative hardware and review every linked licence before production use.
How It Works
- Progressively trains camera control and event response, adds reinforcement learning for action following, and applies forcing and distillation for inference.
What We Like
- Publishes code, a 5B checkpoint, technical report, long-horizon examples and an official hosted experience.
Current Limitations
- The repository's published 5B camera-model table lists 509 seconds for a five-second 720p sample on one H20, so the downloadable path must not be described as independently real-time.
Pricing & Access
- Repository code is published under Apache-2.0. Confirm separate model, dataset and dependency terms before reuse.
- No hosted price is inferred. Budget for the documented GPU, storage and setup requirements.
Verification Summary
- Official repository and licence reviewed on 2026-09-14. Video Runtime has not installed or benchmarked this project.
- Performance and compatibility statements below are attributed to the maintainers and are not site measurements.
Technical notes & official performance
Official Performance Data
- The authors describe interactive generation, while the inspected self-hosted table reports 509 seconds for five seconds of 720p video on one H20. No site benchmark was run.
Technical Notes
- The July 2026 hosted launch and the downloadable checkpoint have different access and performance characteristics.
Sources
- Official GitHub repository ↗github · accessed 2026-09-14
- Code licence ↗github · accessed 2026-09-14
- Official project page ↗official-docs · accessed 2026-09-14
Access, stage & mechanism
These are separate source-checked facts, not a live uptime monitor. Unverified fields are left open; transport and persistent sessions do not establish how frames are generated.
- Release stage
- Not verified
- Access mode
- Not verified
- Source availability
- Not verified
- Transport
- Not verified
- Interaction
- Not verified
- Session mode
- Not verified
- Generation mechanism
- Not verified
- Continuity method
- Not verified
- Licence status
- Not verified
- Tasks
- Not classified
CONTINUE EXPLORING
Related projects & models
Selected by research links and category, not by popularity.
Run an action-conditioned interactive world model with open-ended rollout on a single desktop GPU.
A related project selected in this entry’s research.Public repository; self-hosted installation and compatible GPU required
Build long-horizon playable video worlds with camera control, prompt switching and explicit spatial memory.
A related project selected in this entry’s research.Public repository; self-hosted setup and compatible GPU required
Generate egocentric video worlds controlled by tracked hand poses and camera motion from VR equipment.
A related project selected in this entry’s research.Public repository; self-hosted installation and compatible GPU requiredAn open-source workspace for interactive video generation and editing, with a browser interface and a self-hosted FastVideo backend.
Another clip ahead option in this section.See the official website for current access requirements.Read how official-source and hands-on records stay separate in our Methodology.