Ming-Image 0.1 Design Layer
A solid pick for self-hosting and full data control.
Overview
Ming-Image 0.1 Design Layer, released on 23 September 2026 by inclusionAI (Ant Group), does the reverse of a generator: it takes a flattened design image, such as a poster, card or slide, and splits it into separate RGBA layers, typically a background and foreground elements. You give it the image plus a layer plan, or just a layer count. The output keeps the source image's aspect ratio. The intended use is retouching: recovering the layers of an AI-generated visual, or making a flat deliverable editable again. It pairs naturally with Ming-Image 0.1 Design, which generates the visual, and with the agent skills in the same repository. It is heavy: the vendor-validated setup is a single 80 GB VRAM GPU in BF16, with 12 sampling steps and a 1024-pixel working resolution (512 for speed). Weight size is not published. Without a server of that class, the realistic route is an API; it is offered for free on OpenRouter, with the same caveat about where your data goes. Open weights under MIT.
Skill profile
Not disclosed
Strengths
- Open-source and self-hostable
Limitations
- API pricing not disclosed
Who is it for
- you want to control cost or self-host
- your data must stay in the EU
Ideal use cases
- Recovering layers from an AI-generated visual to retouch it
- Making a flat poster or slide editable again
Access & availability
Key specifications
What it costs per month
Estimate from sourced API prices and a hardware tier for self-hosting. Assumptions are editable.
Assumptions: 36-month amortisation, 0.25 €/kWh, 22 days/month, 1 $ = 0.92 €. Excludes labour, software licences, redundancy.
nAIvigate Trust Index
What the vendor offers and documents for professional use in Europe. An undocumented criterion counts as zero and stays visible: the score rises when the vendor publishes, not when we assume.
19/19 criteria documented · 100 % · 12 of them set by rule
See the criteria▾
Trust Index badge
Show this score in your docs, README or security page. It updates automatically.
[](https://naivigate.com/en/model/ming-image-0-1-design-layer)Data & compliance
What we know, line by line, with source and date. These lines feed the Data and Enterprise families of the Trust Index above. GDPR compliance depends on your processing, not on the model alone.
| EU data residency | Yes |
| Data processing agreement (DPA) | N/A· self-hosted: data never leaves |
| Transfer outside the EU | No |
| Training on your data | No |
| Configurable retention | N/A· self-hosted: data never leaves |
| Zero Data Retention | N/A· self-hosted: data never leaves |
| Self-hostable | Yes |
| Declared hosting | self |
Quality of this card’s data
This score measures the quality of the data on this card: price, context, Elo, licence, documented, sourced and fresh. It measures neither the model nor its compliance: for that, see the Trust Index above.
2/8 documented · 1/8 primary sources
Run it locally
Deploy
Copy-ready commands generated from this card. Adjust context length and GPU count to your hardware.
OpenAI-compatible server for production on NVIDIA GPUs.
pip install vllm
vllm serve inclusionAI/Ming-Image-0.1-Design-Layer \
--max-model-len 32768 \
--tensor-parallel-size 1 \
--dtype autoAdvanced data · for expertsArchitecture, modalities, detailed cost, full benchmarks▾
| Arena Elo | — |
| MMLU | — |
| GPQA | — |
| HumanEval | — |
| SWE-Bench | — |
| MATH | — |