Views
No views yet
[!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 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.
Compatible with versions 2509 and 2511.
pip install -U diffusers transformers accelerate1import torch
2from diffusers import DiffusionPipeline
3from diffusers.utils import load_image
4
5# Switch to "mps" for Apple devices
6pipe = DiffusionPipeline.from_pretrained(
7 "Qwen/Qwen-Image-Edit-2511",
8 dtype=torch.bfloat16,
9 device_map="cuda"
10)
11
12pipe.load_lora_weights("prithivMLmods/QIE-2511-Object-Remover-v2")
13
14prompt = "Remove the red highlighted object from the scene."
15
16input_image = load_image(
17 "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/cat.png"
18)
19
20image = pipe(image=input_image, prompt=prompt).images[0]| Input Image | Edit Prompt | Output Image |
|---|---|---|
 | Remove the red highlighted object from the scene. |  |
 | Remove the red highlighted object from the scene. |  |
 | Remove the red highlighted object from the scene. |  |
Remove the red highlighted object from the scene.1@misc{prithiv_sakthi_2026,
2 author = { Prithiv Sakthi },
3 title = { QIE-2511-Object-Remover-v2 (Revision 3826041) },
4 year = 2026,
5 url = { https://huggingface.co/prithivMLmods/QIE-2511-Object-Remover-v2 },
6 doi = { 10.57967/hf/7627 },
7 publisher = { Hugging Face }
8}