diff --git a/README.md b/README.md
index 1347c2b..23a84ca 100644
--- a/README.md
+++ b/README.md
@@ -1,16 +1,23 @@
-# Design2GarmentCode: Programmatic Garment Patterns from Text and Images
+# Design2GarmentCode: Turning Design Concepts to Tangible Garments Through Program Synthesis
-[arXiv](https://arxiv.org/abs/2412.08603) | [Project Page](https://style3d.github.io/design2garmentcode/)
+[](https://arxiv.org/abs/2412.08603)
+[](https://style3d.github.io/design2garmentcode/)
+[](https://www.youtube.com/xxx)
-Feng Zhou, Ruiyang Liu, Chen Liu, Gaofeng He, Yong‑Lu Li, Xiaogang Jin, Huamin Wang. *CVPR 2025 .*
+Feng Zhou,
+Ruiyang Liu,
+Chen Liu,
+Gaofeng He,
+Yong-Lu Li,
+Xiaogang Jin,
+Huamin Wang
+
+
+ 
+
+Official implementation for Design2GarmentCode, a motility-agnostic sewing pattern generation framework that leverages fine-tuned Large Multimodal Models to generate parametric pattern-making programs from multi-modal design concepts.
-
- we propose a novel
-sewing pattern generation approach Design2GarmentCode
-based on Large Multimodal Models (LMMs), to generate parametric pattern-making programs from multi-modal
-design concepts
----
## Installation
### 1. Clone the repository
@@ -53,15 +60,20 @@ Follow the steps **in the given order**:
`lmm_utils/Qwen/qwen2vl_lora_mlp/`
---
-## Quick GUI Demo
+## Testing with GUI
+
+Setting up the GUI with `python gui.py` where you will see the following interface (modified from GarmentCode)
+
+
+ 
+
+
+Switching to the `Parse Design` tab, and input your design input, either text description, photograph or sketch, to the chatbox. The generated sewing pattern will appear on the right side after parsing.
+
+Once a pattern is generated, you can modify the result by typing `modify: ` in the chatbox.
-```bash
-python gui.py
-```
-- Input: free‑form prompt or an image/sketch
-- Output: GarmentCode JSON, preview image, and (optionally) physics simulation
---
-## Model Inference
+## Batch Inference
### 1. Text Guided Generation
Use `test_text_batch.py` to process a list of text descriptions from a JSON file.
@@ -95,25 +107,21 @@ python lmm_utils/test_picture_batch.py \
- `--sim`: Enable or disable physical simulation output.
---
-### 3. Modify Patterns in the GUI
-Once a pattern is generated in GUI, you can refine them directly inside the GUI:
-1. Focus the **input box** at the bottom.
-2. Type `modify: ` .
-3. Press **Enter** – the system will regenerate the pattern to reflect your changes.
-
-
-## Get 3D Garment Patterns
+## Simulate 3D Garment
### 1. Generate from a pattern.json
-After generating the pattern data, you can simulate the corresponding 3D output directly from the pattern's JSON file.
+After generating the pattern data, you can simulate the corresponding 3D output directly from the pattern's JSON file with
```bash
python test_garment_sim.py --pattern_spec $INPUT_JSON
```
-### 2. Generate from gui
-You can also run the simulation directly on the GUI to obtain 3D data.
-```bash
-python gui.py
-```
+Or run the simulation directly in the `3D View` GUI tab.
+
+
+ 
+
+
+We also support integration
+
### Citation
```bash
If you find this work useful, please cite:
@@ -122,7 +130,7 @@ If you find this work useful, please cite:
@article{zhou2024design2garmentcode,
title={Design2GarmentCode: Turning Design Concepts to Tangible Garments Through Program Synthesis},
author={Zhou, Feng and Liu, Ruiyang and Liu, Chen and He, Gaofeng and Li, Yong-Lu and Jin, Xiaogang and Wang, Huamin},
- journal={arXiv preprint arXiv:2412.08603},
- year={2024}
+ booktitle={Proceedings of the Computer Vision and Pattern Recognition Conference},
+ year={2025}
}
```
\ No newline at end of file
diff --git a/assets/img/gui_example.png b/assets/img/gui_example.png
new file mode 100644
index 0000000..20231ee
Binary files /dev/null and b/assets/img/gui_example.png differ
diff --git a/assets/img/neural_symbolic-pipeline.png b/assets/img/neural_symbolic-pipeline.png
new file mode 100644
index 0000000..4ee648d
Binary files /dev/null and b/assets/img/neural_symbolic-pipeline.png differ
diff --git a/requirements.txt b/requirements.txt
new file mode 100644
index 0000000..20771fa
--- /dev/null
+++ b/requirements.txt
@@ -0,0 +1,29 @@
+- --extra-index-url https://download.pytorch.org/whl/cu121
+- numpy==1.26.4
+- scipy==1.13.1
+- pyyaml==6.0.2
+- svgwrite==1.4.3
+- psutil==6.0.0
+- matplotlib
+- svgpathtools
+- cairosvg==2.7.1
+- nicegui==2.15.0
+- trimesh
+- cgal
+- torch==2.4.0+cu121
+- torchvision==0.19.0+cu121
+- torchaudio==2.4.0+cu121
+- transformers==4.46.2
+- tokenizers==0.20.3
+- accelerate==1.1.1
+- datasets==2.18.0
+- huggingface-hub==0.29.2
+- safetensors==0.5.3
+- tiktoken==0.9.0
+- peft==0.13.2
+- qwen-vl-utils==0.0.8
+- modelscope==1.18.0
+- pyrender==0.1.45
+- libigl==2.5.1
+- cgal==6.0.1.post202410241521
+- openai==1.54.4