Prompt

st portrait, a close-up shot of a young Asian womans face is featured prominently in the center of the frame. She is wearing a pair of gold rimmed glasses, a brown sweater with a white turtleneck underneath, adorned with the word "NIKIE" in bold white letters. Her hair is a vibrant shade of brown, framing her face. Her earring is adorned with a gold hoop, adding a pop of color to her ears. The background is a stark white, creating a stark contrast to her brown sweater.

Prompt

st portrait, a close-up shot of a white hooded sweatshirt, adorned with silver earrings and a silver ring on the right ear. The sweatshirts hoodie is adorned with a silver zipper, adding a touch of warmth to the scene. The backdrop is a stark white, creating a stark contrast to the mas face. The mans eyebrows and mustache are a darker shade of blue, adding depth to the composition. His eyes are a piercing blue, and his eyebrows are a lighter shade of brown. He is wearing a white fedora type hat, with the words "SELECTAL" and "2018" prominently displayed on the front of the hat.

Prompt

st portrait, a close-up shot captures a young boys face, adorned with a white hat adorned with an emblem. The boys eyes are a piercing blue, and he is wearing a black and gray t-shirt with a gray collar. His hair is a vibrant shade of brown, adding a pop of color to the scene. The backdrop is a muted brown, creating a stark contrast to the boys white hat.

Prompt

st portrait, A young man with curly black hair wearing a dark green sweater featuring the word "EVEREST" in bold white letters across the chest. He has a studious expression, enhanced by black-rimmed glasses, and his right ear has a small silver stud earring. The background is a soft gradient of pastel blue and white, giving the portrait a clean, serene atmosphere.

Model description for Flux-St-Shot

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	18 & 2530
Epoch	15	Save Every N Epochs	1

Labeling: florence2-en(natural language & English)

Total Images Used for Training : 22

Best Dimensions & Inference

Dimensions	Aspect Ratio	Recommendation
1280 x 832	3:2	Best
1024 x 1024	1:1	Default

Inference Range

• Recommended Inference Steps: 30–35

Setting Up

import torch
from pipelines import DiffusionPipeline

base_model = "black-forest-labs/Flux-St-Shot"
pipe = DiffusionPipeline.from_pretrained(base_model, torch_dtype=torch.bfloat16)

lora_repo = "strangerzonehf/Flux-St-Shot"
trigger_word = "st portrait"  
pipe.load_lora_weights(lora_repo)

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

Trigger words

You should use st portrait to trigger the image generation.

Download model

Weights for this model are available in Safetensors format.

Download them in the Files & versions tab.