Qwen-Image-Edit-2511-Object-Adder

Qwen-Image-Edit-2511-Object-Adder is an adapter (LoRA) developed for Qwen’s Qwen-Image-Edit-2511 image-to-image model, specifically designed for precise object addition to images. The model adds specified objects while preserving the background, lighting, and surrounding elements, maintaining realism and original visual details. It can be used in combination with the lighting model configured with 4 steps to produce high-quality, high-resolution results. A key strength of this model is its strong consistency during image editing, ensuring that surrounding textures, lighting, shadows, and scene structure remain intact after object addition. This makes it well suited for tasks that require seamless edits without compromising image authenticity. Below are some example outputs that demonstrate the model’s ability to deliver accurate, realistic, and visually integrated object addition results.

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/Qwen-Image-Edit-2511-Object-Adder")

prompt = "Add the specified objects to the image while preserving the background lighting and surrounding elements maintaining realism and original details."
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 (Add Objects)

Trained on ModelScope.cn

Trigger Prompt

You should use the following prompt to trigger object addition:

Add the specified objects to the image while preserving the background lighting and surrounding elements maintaining realism and original details

Download Model

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