[!note] Note: Removing 4–5 or more objects or a specified highlighted area may require more inference steps. Please specify it as [marked area] and proceed.

QIE-2511-Object-Remover-v2

QIE-2511-Object-Remover-v2 is an adapter LoRA developed for Qwen’s Qwen-Image-Edit-2511 image-to-image model, designed to precisely remove unwanted objects from images while preserving the surrounding scene. The model intelligently fills in removed regions with context-aware reconstruction, maintaining consistent textures, lighting, shadows, and perspective. It excels at clean object removal without visible artifacts, edge distortion, or style mismatch, resulting in natural and seamless edits that retain the original image quality.

Quick Start with Diffusers

Compatible with versions 2509 and 2511.

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-2511",
    dtype=torch.bfloat16,
    device_map="cuda"
)

pipe.load_lora_weights("prithivMLmods/QIE-2511-Object-Remover-v2")

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]

Sample Inferences (Remove Objects)

Trained on ModelScope.cn

Trigger Prompt

Use the following prompt to activate the object removal behavior:

Remove the red highlighted object from the scene.

Download Model

You can download the model files from the Files & versions tab: Download

@misc{prithiv_sakthi_2026,
	author       = { Prithiv Sakthi },
	title        = { QIE-2511-Object-Remover-v2 (Revision 3826041) },
	year         = 2026,
	url          = { https://huggingface.co/prithivMLmods/QIE-2511-Object-Remover-v2 },
	doi          = { 10.57967/hf/7627 },
	publisher    = { Hugging Face }
}