Ming-Image-0.1-Design-Layer
An open-weight 6B model from Ant Group’s inclusionAI that splits a finished, flattened design back into separate transparent layers that can be edited, under the MIT licence.
About this launch
Ming-Image-0.1-Design-Layer is a 6-billion-parameter open-weight model from inclusionAI, Ant Group’s research lab, released under the MIT licence alongside Ming-Image-0.1-Design and reported as released on 22 September 2026 (DataNorth, 23 September). It works in the opposite direction to a generator: given one flattened design image and a text plan of the layers wanted — a background and individual foreground elements — it returns each as a separate transparent RGBA image at the input’s dimensions. The use is practical: editing generated or legacy artwork in layer-based design tools without rebuilding it by hand. The validated configuration is a single GPU with 80 GB of memory in BF16, at 1024-pixel resolution with a faster 512-pixel option. inclusionAI publishes results on the Crello design test set, measuring colour and transparency accuracy, and says the model leads every setting it evaluated; those are the developer’s own measurements and are not stored as scores. No independent benchmark was available at release, and there is no hosted API or price from the developer.
Discussion
Questions & answers about Ming-Image-0.1-Design-Layer.
No questions yet. Be the first to ask about Ming-Image-0.1-Design-Layer.
More on TrustList
Everything here links back to the same verified catalogue. Pick your next stop.
- All launchesToday's board, this week's and the all-time archive.
- Ming-Image-0.1-Design-Layer on TrustListReviews, pricing, features and alternatives.
- CompaniesAgencies, consultancies and IT service providers, ranked by verified reviews.
- ProductsSoftware and SaaS with pricing, features, integrations and alternatives.
- ArticlesGuides, comparisons and research from the editorial desk and the community.
- AwardsAnnual recognition decided by verified reviews and an independent jury.
- AI ModelsBenchmark scores and community ratings for every major model.
- RequestsBuyers describe what they need; vendors respond directly.
- PeopleReviewers, authors and makers with public profiles.
- ComparePut up to four listings side by side before you shortlist.