Belle

Prompt

Belle, the female character, a medium-sized woman stands in front of a window. She is dressed in a gray sleeveless t-shirt with a white bra and a blue cardigan over it. Her hair is pulled back in a ponytail, and she is wearing a silver necklace with a pendant. The womans expression is neutral, with a slight smile on her face. The backdrop of the scene is a cloudy sky, adding a touch of warmth to the scene.

Prompt

Belle, the female character, Captured at eye-level, a close-up shot of a young woman with dark brown hair, wearing a white blouse and a blue and red apron. She is smiling, her lips are slightly parted, and her eyes are slightly open. The womans hair is pulled back, framing her face, and she is wearing a silver necklace with a charm on it, adding a touch of charm to her outfit. In the background, a bouquet of flowers is visible, and a man in a gray shirt and a white hat can be seen to the right of her.

Prompt

Belle, the female character, a young woman stands in front of a stone wall. She is dressed in a white long-sleeved shirt, a blue sleeveless top, and a plaid skirt. Her hair is pulled back in a ponytail, adding a touch of color to her face. She is wearing a silver necklace with a pendant hanging from it, and her lips are pursed. The womans hair is a light brown, and she is looking to the right side of the frame. In the background, a man in a brown vest and a red scarf is walking towards the wall.

Prompt

Belle, the female character, Captured at eye-level, a close-up shot of a young woman with long dark brown hair, wearing a green button-down shirt with a beige collar. The womans shirt is adorned with a white embroidery with small black dots. The background is blurred, with a green cabinet visible in the background.

Model description for Belle

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 & 2100
Epoch	21	Save Every N Epochs	1

Labeling: florence2-en(natural language & English)

Total Images Used for Training : 14

Source : Pinterest

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/Belle"
trigger_word = "Belle the female character"  
pipe.load_lora_weights(lora_repo)

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

Trigger words

You should use Belle the female character to trigger the image generation.

Download model

Weights for this model are available in Safetensors format.

Download them in the Files & versions tab.