Upload README.md with huggingface_hub
Browse files
README.md
CHANGED
|
@@ -1,3 +1,32 @@
|
|
| 1 |
---
|
| 2 |
license: apache-2.0
|
| 3 |
---
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
---
|
| 2 |
license: apache-2.0
|
| 3 |
---
|
| 4 |
+
|
| 5 |
+
# BRIDGE Model Weights
|
| 6 |
+
|
| 7 |
+
This repository contains the trained BRIDGE model weights for coarse-mask local image editing.
|
| 8 |
+
|
| 9 |
+
## Usage
|
| 10 |
+
|
| 11 |
+
```python
|
| 12 |
+
from safetensors.torch import load_file
|
| 13 |
+
state = load_file("model.safetensors")
|
| 14 |
+
```
|
| 15 |
+
|
| 16 |
+
- `pipe.ste.*` — GateBlocks (Discrete Geometric Gate) weights
|
| 17 |
+
- `lora_*` — LoRA adapters (rank 512)
|
| 18 |
+
|
| 19 |
+
**Base model required:** `Qwen/Qwen-Image-Edit-2511`
|
| 20 |
+
|
| 21 |
+
See https://github.com/XIONGPEILIN/BRIDGE for inference code and usage instructions.
|
| 22 |
+
|
| 23 |
+
## Citation
|
| 24 |
+
|
| 25 |
+
```bibtex
|
| 26 |
+
@article{xiong2025bridge,
|
| 27 |
+
title={BRIDGE: Background Routing and Isolated Discrete Gating for Coarse-Mask Local Editing},
|
| 28 |
+
author={Peilin Xiong, Honghui Yuan, Junwen Chen, Keiji Yanai},
|
| 29 |
+
journal={arXiv preprint arXiv:2605.07846},
|
| 30 |
+
year={2025}
|
| 31 |
+
}
|
| 32 |
+
```
|