Digital-Chaos-Flux-LoRA + HDR { Incl }

Prompt

Digital Chaos, An abstract painting of a hamburger. The hamburger is made up of a variety of colors, including red, orange, yellow, green, blue, and purple. The bun is adorned with sesame seeds, adding a pop of color to the painting. The background is a vibrant shade of red, purple, and blue, creating a striking contrast with the burger. The burger is positioned in the center of the frame, with the bun facing the viewer.

Prompt

Digital Chaos, An abstract painting of a womans face, the womans head is covered in black hair. The womans eyes are closed, and her lips are slightly parted. The background is a mix of blue, purple, orange, and yellow, and white. The painting has splashes of white, red, and blue, and black, creating a vibrant and colorful effect.

Prompt

Digital Chaos, A detailed painting of a black and white Dachshund dog. The dogs eyes are a vibrant orange, while the dogs nose is a darker shade of red. The background is a mix of pink, orange, and yellow, creating a vibrant contrast to the black dogs fur.

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/Digital-Chaos-Flux-LoRA

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 & 2170
Epoch	15	Save Every N Epochs	1

Labeling: florence2-en(natural language & English)

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

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/Digital-Chaos-Flux-LoRA"
trigger_word = "Digital Chaos"  
pipe.load_lora_weights(lora_repo)

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