Ming-Image-0.1-Design-Layer

🧩 ModelScope · 🤗 Hugging Face · 📄 Blog · 🖥️ Demo
🎨 Design Skill · 📊 PPT Skill

Ming-Image-0.1-Design-Layer decomposes a flattened design image into a requested number of RGBA layers using an image and a layer plan.

Quick Start

Use the companion Ming-Image repository for installation and inference:

git clone https://github.com/inclusionAI/Ming-Image
cd Ming-Image
pip install -r requirements.txt

python infer.py \
  --model inclusionAI/Ming-Image-0.1-Design-Layer \
  --task layer-decompose \
  --input-image assets/layer_samples/card_making_input.png \
  --prompt assets/layer_samples/card_making_prompt.txt \
  --attn-implementation flash_attention_2 \
  --resolution 1024 \
  --output-dir outputs/layers

This runs the released six-layer card-making example. See the full layer-decomposition demo for the output structure and layer-count behavior.

Prompt enhancement (PE) can use Ling-3.0-flash-VL or qwen3.8-27B; see layer-decomposition prompt rewriting.

Deployment

We recommend the following inference frameworks to serve the model:

• vLLM-Omni: see the recipes and installation guide.

Recommended settings

• Working-resolution bucket: 1024 (recommended), or 512 for faster layer decomposition. The output preserves the input image's aspect ratio.
• Sampling steps: 12.
• CFG scale: 2.0.
• Precision: BF16.
• Hardware: one CUDA GPU with 80 GiB VRAM (validated configuration).

Provide --input-image plus either a detailed layer specification through --prompt, or omit --prompt and set --num-layers N to create the default request. When --prompt is supplied, the layer count declared in that prompt controls the output count. The standalone outputs are saved as RGBA PNG files.

Gallery

The example shows the input design, six decomposed layers, and the recomposed result.

The gallery shows additional flattened designs, their transparent layers, and the corresponding recomposed results.

Performance

The table reports quantitative layer-decomposition results on the Crello test set; lower RGB L1 and higher Alpha soft IoU are better.

License

This model is released under the MIT License.