Intel / post

Ant Ling Open-Sources 6B UI Design Models and Two Agent Skills

Source: x.com
Date: Published Sep 22, 2026

Context

Ant Ling, which announces models from InclusionAI, open-sourced the Ming-Image-0.1-Design family on September 22. It contains two 6-billion-parameter models, Ming-Image-0.1-Design and Ming-Image-0.1-Design-Layer, and two open-source skills: the Ling UI Design and the Image-to-Editable-PPT Skill, which by its name turns an image into an editable slide presentation.

Ant Ling's headline claim is that Ming-Image-0.1-Design ranks first among models, meaning models whose weights anyone can download and run, on Artificial Analysis's UI/UX Design leaderboard. That is a ranking within open-weight models in one design category, not across all image generators. Artificial Analysis's own post about the model confirms the open-weight lead and places it 17th among all models in that category. It describes Ming-Image-0.1-Design as a text-to-image model built for user interfaces, infographics, posters and other text-heavy designs, with RGBA output that supports transparent backgrounds.

The companion model's role is less clear from the announcement. InclusionAI's Hugging Face release of Ming-Image-0.1-Design-Layer tags it for layer decomposition with RGBA output, which suggests it separates a finished design into transparent layers that can be edited individually, but the text of Ant Ling's post does not describe how it works or how well.

Terms in this piece · Glossary

AI agent — An AI system that doesn't just answer once but works toward a goal in a loop — taking actions, reading the results, and deciding what to do next.
agent skill — A reusable instruction file that teaches an agent how to do one job well — the procedure, the tools, and what counts as done.
open weights — A model whose trained parameters are published for anyone to download and run — unlike API-only models you can access but never possess.

Read the source x.com