88Z AI, 31 August — Loopit has open-sourced Zing-0.5, a real-time interactive video world model based on Wan2.2-TI2V-5B with 5 billion parameters. It supports combined keyboard and text control, generates video at over 24 FPS on a single RTX 5090, and ranks first in the WBench benchmark for real-time world models.
At a glance
- Supports combined keyboard and text control, integrating instructions without resetting the scene
- Generates over 24 FPS in real time on a single RTX 5090, ranking first in WBench
The update
Loopit has officially open-sourced Zing-0.5, a real-time interactive video world model built on the Wan2.2-TI2V-5B architecture with 5 billion parameters. Its core feature is a combined control mechanism supporting both keyboard inputs and natural language semantic rewriting. Users can modify the virtual world in real time via text commands while moving their viewpoint. New instructions are dynamically integrated into the current scene without resetting it. In terms of performance, Zing-0.5 is highly optimized, achieving real-time video generation at over 24 FPS on a single RTX 5090 GPU, with an inference cost of approximately 0.06 yuan per minute. Due to its superior real-time interaction capabilities, the model ranked first in the WBench benchmark for real-time world models.
Sources & editorial note
This article is an AI-assisted synthesis by 88Z AI based on the public sources below. Product claims and availability are attributed to their publishers. It does not represent independent testing or first-hand reporting.
- Zing-0.5Source published
Source dates above refer to the original announcements; the date under the headline is this article’s publication on 88Z AI.