Published by Video Runtime · Source check 2026-09-14 · Evidence method · Suggest a correction
EDITORIALLY VERIFIED PRODUCT INFORMATION
About ABot-World
Run an action-conditioned interactive world model with open-ended rollout on a single desktop GPU. Uses a causal student model and LongForcing training so keyboard actions can drive an autoregressive visual world without a fixed rollout length.
Key features
Provides code, checkpoints, Docker images, a Gradio client and an official online studio for trying the interaction model.
Getting started
Use the published Docker image or manual Ubuntu setup, download the ABot-World and base-model checkpoints, then launch the included Gradio client on a selected CUDA device.
Real-time interaction
Uses a causal student model and LongForcing training so keyboard actions can drive an autoregressive visual world without a fixed rollout length.
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 documented reference environment is an RTX 5090 with CUDA 12.8; other GPUs and platforms require separate compatibility checks.
EDITORIAL VIEW
Editor's Verdict
ABot-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
- Uses a causal student model and LongForcing training so keyboard actions can drive an autoregressive visual world without a fixed rollout length.
What We Like
- Provides code, checkpoints, Docker images, a Gradio client and an official online studio for trying the interaction model.
Current Limitations
- The documented reference environment is an RTX 5090 with CUDA 12.8; other GPUs and platforms require separate compatibility checks.
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
- Authors report 720p at 16 FPS, 1.2-second latency and about 19 GB GPU memory on one RTX 5090. These are not Video Runtime measurements.
Technical Notes
- The official setup lists Ubuntu 22.04, Python 3.12 and CUDA 12.8, with a separate FAQ for hardware compatibility.
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.
Train playable action-conditioned video world models with an open progressive causal recipe.
Another frame streaming option in this section.Public repository; self-hosted setup and compatible GPU required
A streaming interactive world-model release focused on 720p generation and long-horizon memory.
Another frame streaming option in this section.Public repository; self-hosted installation and compatible GPU required
A general-purpose action-controlled video world model with open-ended event response and long-rollout training.
A related project selected in this entry’s research.Public repository; self-hosted installation and compatible GPU required
Generate continuing interactive worlds with bounded external state, mid-rollout prompts and camera control.
Another frame streaming option in this section.Public repository; self-hosted setup and compatible GPU requiredRead how official-source and hands-on records stay separate in our Methodology.