adapter LoRA developed for Qwen’s Qwen-Image-Edit-2511 image-to-image model • 20 items • Updated • 8
QIE-2511-Zoom-Master
QIE-2511-Zoom-Master is an adapter LoRA developed for Qwen’s Qwen-Image-Edit-2511 image-to-image model, designed to perform precise, high-quality zoom-in transformations on selected regions of an image. The model focuses on the highlighted area and enhances local detail, clarity, and composition while maintaining visual consistency with the original scene. It preserves textures, lighting, colors, and perspective during zoom operations, producing sharp, natural-looking close-ups without distortion or artifacts.
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-Zoom-Master")
prompt = "Zoom into the red highlighted area."
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 (Zoom In)
Trained on ModelScope.cn
Trigger Prompt
Use the following prompt to activate the zoom behavior:
Zoom into the red highlighted area.
Download Model
You can download the model files from the Files & versions tab: Download
@misc{prithiv_sakthi_2026,
author = { Prithiv Sakthi },
title = { QIE-2511-Zoom-Master (Revision aa3fda3) },
year = 2026,
url = { https://huggingface.co/prithivMLmods/QIE-2511-Zoom-Master },
doi = { 10.57967/hf/7630 },
publisher = { Hugging Face }
}
- Downloads last month
- 501
Model tree for prithivMLmods/QIE-2511-Zoom-Master
Base model
Qwen/Qwen-Image-Edit-2511