---
title: DiffSketchEdit
emoji: ✏️
colorFrom: red
colorTo: yellow
sdk: custom
app_file: handler.py
pinned: false
license: mit
tags:
- svg-editing
- vector-graphics
- diffusion
- sketch-editing
- text-guided
pipeline_tag: text-to-image
---

# DiffSketchEdit: Text-based Vector Sketch Editing

DiffSketchEdit enables text-guided editing of vector sketches using diffusion models. It supports various editing operations including word replacement, prompt refinement, and attention reweighting.

## Usage

```python
import requests

API_URL = "https://api-inference.huggingface.co/models/jree423/diffsketchedit"
headers = {"Authorization": "Bearer YOUR_HF_TOKEN"}

# Word replacement example
payload = {
    "inputs": {
        "prompts": [
            "A painting of a squirrel eating a burger",
            "A painting of a rabbit eating a burger"
        ],
        "edit_type": "replace"
    }
}

response = requests.post(API_URL, headers=headers, json=payload)
```

## Edit Types

- **replace**: Word swap editing
- **refine**: Prompt refinement 
- **reweight**: Attention reweighting
- **generate**: Simple generation

## License

MIT License