Add Layer model Quick Start

README.md

@@ -14,20 +14,29 @@ tags:
 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.
 
-## Gallery
+## Quick Start
 
-<p align="center">
-  <img src="./assets/showcase.webp" width="100%" alt="Ming-Image-0.1-Design-Layer decomposition example">
-</p>
+Use the companion [Ming-Image repository](https://github.com/inclusionAI/Ming-Image)
+for installation and inference:
 
-The example shows the input design, six decomposed layers, and the recomposed
-result.
+```bash
+git clone https://github.com/inclusionAI/Ming-Image
+cd Ming-Image
+pip install -r requirements.txt
 
-## Usage
+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
+```
 
-Installation instructions, inference code, and a runnable
+This runs the released six-layer card-making example. See the full
 [layer-decomposition demo](https://github.com/inclusionAI/Ming-Image#layer-decomposition-demo)
-are available in the Ming-Image repository.
+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](https://github.com/inclusionAI/Ming-Image#layer-decomposition-prompt-rewriting).
@@ -46,6 +55,15 @@ Provide `--input-image` plus either a detailed layer specification through
 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
+
+<p align="center">
+  <img src="./assets/showcase.webp" width="100%" alt="Ming-Image-0.1-Design-Layer decomposition example">
+</p>
+
+The example shows the input design, six decomposed layers, and the recomposed
+result.
+
 ## License
 
 This model is released under the [MIT License](./LICENSE).