Qwen-Image-Studio-Realism

Prompt

Studio Realism, a close-up shot of a young womans face features a neutral expression. The womans eyes are a deep brown, her hair is a dark brown, and her eyebrows are a lighter shade of brown. She is wearing a black and yellow t-shirt, with a cream collar around her neck. Her ear is adorned with a gold earring, adding a touch of shine to her face. The backdrop is a stark white, and the womans hair is pulled back in a ponytail.

Prompt

Studio Realism, Captured in a close-up, eye-level shot of a young man with curly brown hair. He is wearing a pair of rimmed glasses with a gold frame. His eyes are a piercing blue, and his lips are a pinkish-pink color. His hair is a rich brown, and he is wearing an orange and blue shirt with a brown tie around the neck. The backdrop is a plain white wall.

Prompt

Studio Realism, a close-up shot of a young womans face is adorned with a vibrant orange baseball cap, adorned with orange and yellow paint. Her eyes are adorned with blue-green tinted eyes, adding a pop of color to her face. Her lips are painted a vibrant shade of pink, while her braids are pulled back in a braid. She is wearing a white tank top, and her hair is cascading down her shoulders. The backdrop is a vibrant yellow, creating a striking contrast to her skin.

Prompt

Studio Realism, a woman with long blonde hair, wearing a white baseball cap adorned with a black buckle and the word ABE written in red letters. Her eyes are a piercing green, and her lips are a vibrant pink. She is wearing a blue shirt with a yellow collar around her neck. Her hair is cascading down her shoulders, adding a touch of texture to her face. The backdrop is a vibrant blue, creating a striking contrast to the womans face.

Model description for Qwen-Image-Studio-Realism

Image Processing Parameters

Parameter	Value	Parameter	Value
LR Scheduler	constant	Noise Offset	0.03
Optimizer	AdamW	Multires Noise Discount	0.1
Network Dim	64	Multires Noise Iterations	10
Network Alpha	32	Repeat & Steps	20 & 2790
Epoch	20	Save Every N Epochs	1

Labeling: florence2-en(natural language & English)

Total Images Used for Training : 27 [HQ Images]

Data Sources

Source	Link
Playground	playground.com
ArtStation	artstation.com
4K Wallpapers	4kwallpapers.com

Best Dimensions & Inference

Dimensions	Aspect Ratio	Recommendation
1472 x 1140	4:3 (approx.)	Best
1024 x 1024	1:1	Default

Inference Range

Recommended Inference Steps: 35-50

Setting Up

import torch
from diffusers import DiffusionPipeline

base_model = "Qwen/Qwen-Image"
pipe = DiffusionPipeline.from_pretrained(base_model, torch_dtype=torch.bfloat16)

lora_repo = "prithivMLmods/Qwen-Image-Studio-Realism"
trigger_word = "Studio Realism"  
pipe.load_lora_weights(lora_repo)

device = torch.device("cuda")
pipe.to(device)