BRIDGE Model Weights

This repository contains the trained BRIDGE model weights for coarse-mask local image editing.

Usage

from safetensors.torch import load_file
state = load_file("model.safetensors")
  • pipe.ste.* — GateBlocks (Discrete Geometric Gate) weights
  • lora_* — LoRA adapters (rank 512)

Base model required: Qwen/Qwen-Image-Edit-2511

See https://github.com/XIONGPEILIN/BRIDGE for inference code and usage instructions.

Citation

@article{xiong2025bridge,
  title={BRIDGE: Background Routing and Isolated Discrete Gating for Coarse-Mask Local Editing},
  author={Peilin Xiong, Honghui Yuan, Junwen Chen, Keiji Yanai},
  journal={arXiv preprint arXiv:2605.07846},
  year={2025}
}
Downloads last month

-

Downloads are not tracked for this model. How to track
Safetensors
Model size
5B params
Tensor type
BF16
·
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Paper for PANDATREE/BRIDGE