Skip to content
TrustList
MI
AI Model

Ming-Image-0.1-Design

New· 4

Open-weight 6B text-to-image model from Ant Group's inclusionAI for UI screens, dashboards, infographics and posters, under the MIT licence

About Ming-Image-0.1-Design

Designed visuals, not general pictures, are the target of Ming-Image-0.1-Design, a text-to-image model made by Ant Group's research lab, inclusionAI, which also produces the Ling models.

What it generates

With 6 billion parameters, the model is aimed at finished interface screens, dashboards, infographics and posters, text included, generated from structured prompts. It can also produce RGBA output with a transparent background, enabled through a set prompt prefix written in English or Chinese. That makes the results easier to drop onto an existing layout.

Running it

The weights are published on Hugging Face under the MIT license and were reported as released on 22 September 2026. The model card recommends 2048 by 2048 output with 12 sampling steps. Just one setup has been validated so far: a single 80 GB GPU running BF16 through vLLM-Omni. Running it in-house is therefore a data-center GPU decision, not a laptop one. The developer offers no hosted API and no price.

Companion releases

Alongside it came Ming-Image-0.1-Design-Layer, which splits images into layers, and two open-source agent skills. One covers interface design and the other converts generated slides into editable PowerPoint files.

Licensing and claims

The MIT license stands out for a buyer, since commercial use is allowed with none of the revenue thresholds attached to several other open image models. inclusionAI claims the top spot as an open-weight model on the UI/UX design leaderboard run by Artificial Analysis, but shows that only as an image on its model card, so it is the developer's own claim.

TrustList summary

Ming-Image-0.1-Design is an open-weight text-to-image model from inclusionAI, the research lab of Ant Group, built for visual design rather than general imagery. It has 6 billion parameters, and it was reported as released on 22 September 2026.

Its MIT licence permits commercial use, with none of the revenue caps that some other open image models attach.

Main features

  • Interface screens: complete user-interface screens and dashboards, with the text inside them, from structured prompts.
  • Infographics and posters: visual design output with legible text.
  • Transparent backgrounds: a fixed prompt prefix, in English or Chinese, turns on RGBA output with a transparent background.
  • Agent skills: two open-source agent skills ship with it. One handles interface design, the other converts generated slides into PowerPoint files that can be edited.
  • Layer splitting: a companion model, Ming-Image-0.1-Design-Layer, splits a finished design into layers.

Key facts

  • Licence: MIT.
  • Developer: inclusionAI, the research lab of Ant Group.
  • Recommended output: 2048 × 2048 pixels with 12 sampling steps.
  • Validated setup: one 80 GB GPU in BF16, run with vLLM-Omni.
  • Hosted access: no hosted API from the developer.
  • Developer's claim: the developer says it ranks first among open-weight models on the UI/UX design leaderboard of Artificial Analysis.

Summary written by TrustList from the business's own published information, Nov 2026.

Benchmarks & AI stats

BenchmarkOfficialCommunity avg
No benchmark scores yet. Be the first to add one.

“Official” values are editor-approved and feed the ranking. “Community avg” is the mean of member submissions (shown for transparency; it never affects the ranking until an editor approves a value).

Sign in to add a benchmark score for this model.

Ming-Image-0.1-Design launches

Trust Score

4/ 100
Trust Score: New

An earned signal from verification, reviews, awards, transparency and engagement - the vendor can't buy it.

Verification
0/100 · 20%
Reviews
0/100 · 30%
Awards
0/100 · 15%
Transparency
18/100 · 20%
Engagement
0/100 · 15%
Joining soon
Recommendations
Coming soon
Complaints
Coming soon

Updated 9/24/2026

Request a demo or quote from Ming-Image-0.1-Design

Protected by reCAPTCHA - Google Privacy Policy and Terms apply.

By sending, you agree we may share your request and contact details with the provider once you confirm your email.

Reviews

Write the first review of Ming-Image-0.1-Design

Used it? Your experience helps other buyers decide.

Write a review

Questions & answers

No questions yet. Be the first to ask about Ming-Image-0.1-Design.

Ming-Image-0.1-Design alternatives

Similar listings buyers compare against this one.

Open-weight translation model from Bilibili's Index team, covering 150 languages and following glossary and style instructions

Black Forest Labs' image generation and editing model with bounding-box layouts, multiple reference images and 4K output

Aleph Alpha's open-weight English-German mixture-of-experts model for self-hosting, released under Apache 2.0 in October 2026

Liquid AI's open-weight decision model, giving yes or no, choice or score answers from text and images

Perplexity's open-weight decision model that picks among given options for routing and checks in AI systems

Open-source 2B decision model from AWS's Strands Agents project that picks options and returns scores with a reliability figure

JetBrains' open 12B mixture-of-experts coding model with 2.5B parameters active per token under Apache 2.0

Anthropic's smallest and fastest Claude 5.5 model, available on its own API and three cloud platforms