Note: The input image should be well defined. If you upload a half-cropped or semi-cropped image, only that region will be extracted as the mockup.

QIE-2511-Extract-Outfit

QIE-2511-Extract-Outfit is an adapter LoRA developed for Qwen’s Qwen-Image-Edit-2511 image-to-image model, designed to precisely extract clothing from images and convert it into a clean, flat mockup. The model intelligently separates garments from the subject while preserving original fabric details, textures, colors, stitching, and patterns. It removes the body, pose, and background influence, producing a studio-style flat outfit layout suitable for fashion design, catalogs, and product visualization, with minimal artifacts and high visual fidelity.

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-Extract-Outfit")

prompt = "Extract the clothing and create a flat mockup."

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]

Trained on ModelScope.cn

Trigger Prompt

Use the following prompt to activate the outfit extraction behavior:

Extract the clothing and create a flat mockup.

Download Model

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

@misc{prithiv_sakthi_2026,
    author       = { Prithiv Sakthi },
    title        = { QIE-2511-Extract-Outfit (Revision dc0f473) },
    year         = 2026,
    url          = { https://huggingface.co/prithivMLmods/QIE-2511-Extract-Outfit },
    doi          = { 10.57967/hf/7646 },
    publisher    = { Hugging Face }
}