Black-of-Art-Flux

Prompt

Black of Art, Captured in a black and white monochrome, a woman with short dark hair stands in front of a gray wall, her head tilted slightly to the left. The womans face is angled towards the left, her mouth is slightly open, as if she is looking at something. The wall behind her is adorned with white polka dots, adding a pop of color to the scene.

Prompt

Black of Art, a black and white monochromatic painting of a baseball player, dressed in a black jacket, white collared shirt, and a black baseball cap. He is holding a baseball in his right hand, and his left hand is positioned in a baseball glove. His right hand is resting on his left wrist, while his left arm is bent at the elbow. The baseball is in the air, and he is looking down at the ball. The background is a light gray, with a few birds flying in the background. The painting has a signature at the bottom right corner of the frame.

Prompt

Black of Art, Captured in a sepia toned photograph, a man in a black suit and tie is standing on the left side of the frame. He is holding a phone in his right hand, while his left hand is on the phone. The man in the foreground is sitting on a chair facing a row of black phones that have numbers on them. The phones are on a long, rectangular table that is set against a white wall with small white polka dots on it. To the right of the table, there is a window that is covered in shadows.

Prompt

Black of Art: A grainy, high-contrast monochrome photograph captures a jazz musician in a dimly lit club. He is hunched over his trumpet, his eyes closed as he plays. Smoke curls from a cigarette resting on the edge of a small, round table beside him. The neon glow from a sign outside the window faintly illuminates the scene, casting long, soft shadows across the checkered floor. A few empty glasses sit nearby, hinting at a long night of music and solitude.

Model description for Black-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	18 & 3180
Epoch	27	Save Every N Epochs	1

Labeling: florence2-en(natural language & English)

Total Images Used for Training : 19

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

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