Thread-of-Art-Flux

Prompt

Thread of Art, A black and white sketch of a woman smoking a cigarette. The woman is wearing a white button up shirt, a black tie, and white pants. Her hair is pulled back in a ponytail, and she is wearing a pair of white gloves. Her left hand is raised in the air, while her right hand is resting on her hip. Her mouth is slightly open, as if she is smoking. She has a black belt around her waist, and a white jacket on her right. The background is a plain white.

Prompt

Thread of Art, A black and white sketch of a mans head is drawn on a white paper. The mans face is facing the right side of the frame. He has short hair that is tied up at the top of his head. His eyes are closed and his mouth is slightly open. His hair is slicked back. He is wearing a white shirt with a black stripe on the front of the shirt. A black stripe is running down the side of his shirt.

Prompt

Thread of Art – A black and white sketch of a man sitting at a café table, a coffee cup in front of him. He is wearing a fitted black suit, a white shirt, and a black tie. His hand is resting against his cheek as he looks off to the side. His neatly styled hair adds to his polished appearance. The background is plain white.

Prompt

Thread of Art – A black and white sketch of a man leaning against a railing with his arms crossed. He is wearing a white button-up shirt with the sleeves rolled up, a black vest, and a pair of sunglasses resting on his head. His hair is styled back, and his jawline is sharp. His expression is calm and thoughtful. The bac

Model description for Thread-of-Art-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 & 3200
Epoch	25	Save Every N Epochs	1

Labeling: florence2-en(natural language & English)

Total Images Used for Training : 26

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/Thread-of-Art-Flux"
trigger_word = "Thread of Art"  
pipe.load_lora_weights(lora_repo)

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