Spaces:
Running
Running
Update README with proper metadata
Browse files
README.md
CHANGED
|
@@ -1,12 +1,53 @@
|
|
| 1 |
---
|
| 2 |
-
title: Garment
|
| 3 |
-
emoji:
|
| 4 |
-
colorFrom:
|
| 5 |
-
colorTo:
|
| 6 |
sdk: gradio
|
| 7 |
sdk_version: 6.13.0
|
| 8 |
app_file: app.py
|
| 9 |
pinned: false
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 10 |
---
|
| 11 |
|
| 12 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
---
|
| 2 |
+
title: Garment Image → 2D Sewing Pattern
|
| 3 |
+
emoji: 🧵
|
| 4 |
+
colorFrom: pink
|
| 5 |
+
colorTo: purple
|
| 6 |
sdk: gradio
|
| 7 |
sdk_version: 6.13.0
|
| 8 |
app_file: app.py
|
| 9 |
pinned: false
|
| 10 |
+
tags:
|
| 11 |
+
- fashion
|
| 12 |
+
- sewing-pattern
|
| 13 |
+
- garment
|
| 14 |
+
- pattern-making
|
| 15 |
+
- vlm
|
| 16 |
+
- computer-vision
|
| 17 |
---
|
| 18 |
|
| 19 |
+
# 🧵 Garment Image → 2D Sewing Pattern
|
| 20 |
+
|
| 21 |
+
Upload a garment image or describe one — get flat 2D sewing pattern pieces with seam allowances, grain lines, and notches.
|
| 22 |
+
|
| 23 |
+
## How It Works
|
| 24 |
+
|
| 25 |
+
1. **Image Analysis**: A Vision-Language Model (Qwen2.5-VL) analyzes the garment to identify type, style, and proportions
|
| 26 |
+
2. **Parameter Extraction**: Structured measurements and features are extracted as JSON
|
| 27 |
+
3. **Pattern Generation**: A parametric pattern engine generates anatomically-correct 2D sewing pattern pieces
|
| 28 |
+
|
| 29 |
+
## Features
|
| 30 |
+
|
| 31 |
+
- 📸 **From Image**: Upload any garment photo for AI-powered analysis
|
| 32 |
+
- ✍️ **From Text**: Describe a garment and get pattern pieces
|
| 33 |
+
- 📐 **Manual**: Fine-tune every measurement with sliders
|
| 34 |
+
- Supports: shirts, dresses, skirts, pants, jackets, hoodies, vests
|
| 35 |
+
- Pattern pieces include: cut lines, seam lines, fold lines, grain lines, notches
|
| 36 |
+
|
| 37 |
+
## Research Background
|
| 38 |
+
|
| 39 |
+
Inspired by the latest research in garment-to-pattern conversion:
|
| 40 |
+
|
| 41 |
+
| Paper | Year | Approach |
|
| 42 |
+
|-------|------|----------|
|
| 43 |
+
| [ChatGarment](https://arxiv.org/abs/2412.17811) | 2024 | VLM → GarmentCode JSON → sewing patterns |
|
| 44 |
+
| [NGL-Prompter](https://arxiv.org/abs/2602.20700) | 2025 | Training-free VLM + Natural Garment Language |
|
| 45 |
+
| [SewFormer](https://arxiv.org/abs/2311.04218) | 2023 | Two-level Transformer for pattern reconstruction |
|
| 46 |
+
| [GarmentDiffusion](https://arxiv.org/abs/2504.21476) | 2025 | DiT-based multimodal pattern generation |
|
| 47 |
+
| [GarmageNet](https://arxiv.org/abs/2504.01483) | 2025 | Geometry image diffusion for sewing patterns |
|
| 48 |
+
|
| 49 |
+
## Related Resources
|
| 50 |
+
|
| 51 |
+
- [ChatGarment Dataset](https://huggingface.co/datasets/sy000/ChatGarmentDataset) — 362GB training data
|
| 52 |
+
- [GarmageSet](https://huggingface.co/datasets/Style3D/GarmageSet) — 14,801 professional garments
|
| 53 |
+
- [GarmentCode DSL](https://github.com/maria-korosteleva/GarmentCode) — Parametric pattern compiler
|