metadata
license: apache-2.0
language:
- en
base_model:
- Qwen/Qwen-Image-Edit-2509
pipeline_tag: image-to-image
library_name: diffusers
tags:
- Object-Remover
- lora
- art
- Bbox
QIE-2509-Object-Remover-Bbox
QIE-2509-Object-Remover-Bbox is an adapter LoRA developed for Qwen-Image-Edit-2509, designed to precisely remove unwanted objects from images using bounding box guidance. The model intelligently reconstructs the selected region with context-aware filling, while preserving surrounding textures, lighting, shadows, and perspective. It delivers clean object removal without visible artifacts, edge distortion, or style mismatch, ensuring natural and seamless edits while retaining the original image quality.
Quick Start with Diffusers
pip install -U diffusers transformers accelerate
import torch
from diffusers import DiffusionPipeline
from diffusers.utils import load_image
# Switch to "mps" for Apple devices
pipe = DiffusionPipeline.from_pretrained(
"Qwen/Qwen-Image-Edit-2509",
dtype=torch.bfloat16,
device_map="cuda"
)
pipe.load_lora_weights("prithivMLmods/QIE-2509-Object-Remover-Bbox")
prompt = "Remove the red highlighted object from the scene."
input_image = load_image(
"https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/cat.png"
)
image = pipe(image=input_image, prompt=prompt).images[0]
Trigger Prompt
Remove the red highlighted object from the scene.
Download Model
You can download the model files from the Files & versions tab: Download