Downloads · 30 days
134
10% of all-time downloads
sdfafdfsdf/Qwen-Image-Edit-2511-Ultra-Realistic-Portrait
Qwen-Image-Edit-2511-Ultra-Realistic-Portrait is a image-to-image model from sdfafdfsdf. Use it when you need one image transformed into another. It is set up for diffusers. The card lists the license as apache-2.0.
Downloads · 30 days
134
10% of all-time downloads
All-time downloads
1.3K
Public
Repo size
944 MB
Likes
4
Public
Click a slice to open those files.
.safetensors944 MB · 100%
From the Hugging Face model README

Qwen-Image-Edit-2511-Ultra-Realistic-Portrait is an adapter LoRA developed for Qwen’s Qwen-Image-Edit-2511 image-to-image model, designed to generate ultra-realistic glamour-style portraits with strict identity preservation. The model focuses on high-end fashion realism by combining cinematic directional lighting, refined makeup aesthetics, and detailed epidermal textures. It enhances micropores, microhairs, subtle oil sheen, soft wrinkles, and subsurface scattering while preserving the subject’s natural facial structure and original details. Visual consistency is maintained across lighting, shadows, skin tones, and composition, delivering a luxury fashion-magazine look without artificial smoothing or excessive retouching. This makes the model well suited for premium portrait generation where realism, identity fidelity, and cinematic polish are essential. Above are example outputs demonstrating the model’s ability to produce high-quality, visually cohesive ultra-realistic portrait results.
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-Ultra-Realistic-Portrait")
prompt = "ultra-realistic portrait"
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]
Transform the image into an ultra-realistic glamour portrait while strictly preserving the subject’s identity. Apply a close-up composition with a slight head tilt and a hand near the face, enhance cinematic directional lighting with dramatic fashion-style highlights, and refine makeup details including glowing skin, glossy lips, luminous highlighter, and defined eyes. Increase skin realism with detailed epidermal textures such as micropores, microhairs, subtle oil sheen, natural highlights, soft wrinkles, and subsurface scattering. Maintain a luxury fashion-magazine look in a 9:16 aspect ratio, preserving realism, facial structure, and original details without over-smoothing or retouching.
Use the following prompt to activate the ultra-realistic portrait effect:
ultra-realistic portrait
You can download the model files from the Files & versions tab: Download