BnW-Expressions-Flux

Prompt

BnW Expressions, Captured in a black and white monochromatic shot, a young woman with medium length dark brown hair, wearing a white t-shirt. Her hair is pulled back in a ponytail, adding a touch of texture to her face. Her eyes are wide open, and her lips are slightly parted, as if she is looking to the right. Her eyebrows are a darker shade of brown, and she has a slight smile on her lips. The backdrop is a stark white, and the womans hair is cascading down her shoulders.

Prompt

BnW Expressions, A black and white close-up shot of a woman with long dark hair and a headband on her head. She is smiling, her eyes are closed and her lips are slightly parted. Her hair is pulled back and cascades over her shoulders. She is wearing a black blouse with a black collar. The background is blurred, but it appears to be a hillside.

Prompt

BnW Expressions, Captured in a black and white monochromatic shot, a close-up of a mans face features a serious expression. The mans eyes are squinted with dark brown eyes, and his hair is slicked back and cascades over his shoulders. His eyebrows are arched, adding a touch of texture to his face. He is wearing a black t-shirt, with a collar around his neck. The background is a stark white, creating a stark contrast to the mans upper body.

Prompt

BnW Expressions, A black and white close-up shot of a womans face. The womans left hand is resting on her chin, while her right hand rests on her left hand. Her right eye is slightly open, and her lips are pursed. Her hair is long and cascades over her shoulders, framing her face. Her eyebrows are straight, adding a touch of texture to the scene. The background is a plain white, and the womans skin is bare.

# Model description for BnW-Expressions-Flux

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 & 2800
Epoch	20	Save Every N Epochs	1

Labeling: florence2-en(natural language & English)

Total Images Used for Training : 27

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.1-dev"
pipe = DiffusionPipeline.from_pretrained(base_model, torch_dtype=torch.bfloat16)

lora_repo = "strangerzonehf/BnW-Expressions-Flux"
trigger_word = "BnW Expressions"  
pipe.load_lora_weights(lora_repo)

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

Trigger words

You should use BnW Expressions to trigger the image generation.

Download model

Weights for this model are available in Safetensors format.

Download them in the Files & versions tab.