Flux-GArt-LoRA

Prompt

GArt, a man in a blue jacket and blue jeans is riding a brown horse down a dirt road in the middle of a desert. The man is wearing a black cowboy hat, a blue long sleeved shirt, and black boots. The horse is facing the left side of the road, and the sun is setting in the background, casting a shadow on the road. The road is divided into two sections, each section having a yellow line painted on it. To the left and right of the image, there are cactus plants with yellow flowers growing on the ground. In the distance, there is a mountain range. The sky is a deep orange, with a few wispy clouds in the sky.

Prompt

GArt, Captured at night, a vibrant orange van is parked on a sandy beach. The van is facing the viewer, with its door open, revealing the interior of the van. A fire is burning on the beach, creating a warm glow. Two folding chairs are positioned in front of the fire, adding a pop of color to the scene. The sky is a deep blue, dotted with white stars, and a mountain range can be seen in the background.

Prompt

GArt, Captured from a high-angle perspective on a sunny day, a view of a baseball stadium is seen. The stadium is surrounded by lush green grass and trees, with a winding track running along the center of the field. The field is adorned with a few people playing a game of tennis, and there are a few empty stands on either side of the track. In the distance, a city can be seen, with tall buildings and a mountain range in the background. The sky is a deep blue, dotted with white clouds.

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/Flux-GArt-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	15 & 2500
Epoch	10	Save Every N Epochs	1

Labeling: florence2-en(natural language & English)

Total Images Used for Training : 14

Best Dimensions

768 x 1024 (Best)
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/Flux-GArt-LoRA"
trigger_word = "GArt"  
pipe.load_lora_weights(lora_repo)

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