Orange-Chroma-Flux-LoRA

Prompt

Orange Chroma, a close-up shot of a womans face is adorned with shiny silver paint. The womans eyes are covered in a shiny, reflective paint, adding a touch of sparkle to her face. Her hair is a vibrant shade of brown, cascading down her shoulders. She is wearing a white collared shirt, adorned with a white collar and a shiny red cape. Her lips are painted a darker shade of pink, while her hair is styled in a wavy bob. The background is a deep orange, creating a vibrant contrast to the womans skin.

Prompt

Orange Chroma, A close-up of a cats face, the cats eyes are a piercing blue. The cats whiskers are long and white, adding a touch of color to the scene. The background is a vibrant orange, creating a striking contrast with the cat and its vibrant colors.

Prompt

Orange Chroma, A close-up eye-level shot of a young mans face, adorned with a vibrant blue wig. The wigs bangs are a mix of pink, blue, and purple, adding a pop of color to the scene. The mans eyes are a piercing blue, while his lips are a lighter shade of green. He is wearing a colorful shirt with a pattern of red, yellow, and green. The background is a vibrant orange, creating a striking contrast to the mans head.

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/Orange-Chroma-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	25 & 2K
Epoch	14	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/Orange-Chroma-Flux-LoRA"
trigger_word = "Orange Chroma"  
pipe.load_lora_weights(lora_repo)

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