InclusionAI just open sourced a design model that can create a finished graphic, and a…
This is a AI post classified by Jev as AI image (a model release), kept by the AI Radar because it carries real work, not commentary.
InclusionAI just open sourced a design model that can create a finished graphic, and a companion model that can break one back into editable layers. MING-IMAGE-0.1-DESIGN • 6B • Generates UIs, dashboards, infographics and posters • Handles structured prompts up to 8K tokens • Creates transparent-background RGBA assets MING-IMAGE-0.1-DESIGN-LAYER • 6B • Splits flat graphics into 2–9 editable RGBA layers • Separates elements so they can be moved, replaced or recolored They also released two open source Agent Skills: one for building a UI from a prompt or screenshot through browser validation,
Posted by Joey (4.8k followers) 1 h ago · 3 likes · 235 views · view the original post on X. Kept by the AI Radar as AI image. Tools mentioned: ming-image-0.1-design-layer, ming-image.
More AI work like this
- More from where that came ! — @ItsmeAjayKV
- Grok Imagine on Web now has Loop template — @techdevnotes
- Again cannot stress how good we are getting for - — @ItsmeAjayKV
- Introducing OpenDesign Pass. — @OpenDesignHQ
- If you're building with Qwen-Image-2.1 then this is for you! — @ItsmeAjayKV
- 感觉在sol上效果一般，它甚至忘了自己可以生图。 — @klarkxy01
- I slept a few hours last night. — @emmanuel_2m
- Image generation models have struggled to create native vector graphics. They mostly try… — @Carles_Reina
Every post is read and classified by Jev (TypeSafe): what it is, which market it belongs to, and whether the link is a real tool. 44.3k posts from 5k X accounts over the last 14 days, 1.8k tools, 19 markets. Collected every 5 minutes, fully re-ranked every hour — last update 2026-09-23 13:36 UTC. Full method.