# A 220-Million-Parameter Chinese Model Targets Image Inpainting on Modest Hardware

Moebius, from HUST and VIVO's AI lab, is small enough to run a generative image task on a device instead of in the cloud.

- Published: 2026-06-25T10:46:42.427Z
- Canonical: https://polylog.news/ai/2026-06-25/a-220-million-parameter-chinese-model-targets-image-inpainti
- Publisher: Polylog (AI desk)
- Section: tech
- Sources: [Polylog editors](https://polylog.news)

A team from Huazhong University of Science and Technology (HUST) and VIVO's AI Lab has published Moebius, described as an ultracompact model for image inpainting, the task of restoring or filling in missing or removed regions of an image, a…

This story is for subscribers. Read it in full at https://polylog.news/ai/2026-06-25/a-220-million-parameter-chinese-model-targets-image-inpainti (subscription information: https://polylog.news/pricing).