Fractured-Line-Flare

Prompt

Fractured Line Flare, Captured at eye-level, a close-up shot captures a hamburger, adorned with sesame seeds on a brown bun. The bun is adorned with a variety of vibrant colors, including pink, purple, and white. The hamburger is situated on a black surface, with a backdrop of a trees leaves, adding a pop of color to the scene. The burger is encased in a thick layer of melted cheese, a dark brown meat, and a few slices of onion are arranged in the middle of the bun, adding depth to the composition. The lighting is subdued in a vibrant hue, creating a stark contrast to the burger.

Prompt

Fractured Line Flare, Captured at eye-level on a low-angle perspective, a medium-sized bull stands on a grassy field. The bulls head is encircled by a wire fence, its horns protruding from the top of its head, adding a pop of color to the otherwise monochromatic scene. The cows body is covered in a pattern of small, square-shaped pieces of wire, adding depth to the composition. The background is a deep, vibrant purple, with a pink hue to the scene, creating a stunning contrast. The sky is filled with stars, adding to the overall composition of the image.

Prompt

Fractured Line Flare, two women are seated on stools, playing violins. The woman on the left is wearing a long-sleeved black shirt and blue pants, while the other woman is on the right. Both women are dressed in dark clothing, their hair is styled in a bob, and their eyes are closed. The background is dark, and there are pink and blue lights strung across the image.

• Hosted Here🧨: https://huggingface.co./spaces/prithivMLmods/FLUX-LoRA-DLC

The model is still in the training phase. This is not the final version and may contain artifacts and perform poorly in some cases.

Model description

prithivMLmods/Fractured-Line-Flare

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	22 & 2.2K
Epoch	15	Save Every N Epochs	1

Labeling: florence2-en(natural language & English)

Total Images Used for Training : 17 [ Hi-RES ]

Other Sample Images

Best Dimensions

• 1024 x 1024 (Default)

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 = "prithivMLmods/Fractured-Line-Flare"
trigger_word = "Fractured Line Flare"  
pipe.load_lora_weights(lora_repo)

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

Data source

- https://freeflo.ai/

Trigger words

You should use Fractured Line Flare to trigger the image generation.

Download model

Weights for this model are available in Safetensors format.

Download them in the Files & versions tab.