strangerzonehf/Flux-Isometric-3D-LoRA

Prompt

Isometric 3D, a 3D model of a tropical island is displayed on a light blue backdrop. The island features a small body of water, surrounded by gray rocks and green grass. There are palm trees and small bushes scattered throughout the island, adding a pop of color to the scene.

Prompt

Isometric 3D, a 3D rendering of a yellow jeep is positioned on a sandy desert-like surface. The jeep has a white roof with a black ladder on the top of it, adding a pop of color to the scene. The background is a light peach color, with a large rock formation in the upper right corner of the frame. There are small green plants scattered around the jeep, adding depth and texture to the image.

Prompt

Isometric 3D, a small miniature landscape is displayed on a light green backdrop. The landscape features a circular pond with a winding walkway in the middle. The pond is surrounded by trees and shrubs, and there is a small wooden bridge crossing the pond. The bridge is made up of gray stones, and the trees are arranged in a circular pattern. A small wooden cross is positioned at the center of the pond, and a small sign is placed at the bottom of the bridge.

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

strangerzonehf/Flux-Isometric-3D-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 & 3400
Epoch	20	Save Every N Epochs	1

Labeling: florence2-en(natural language & English)

Total Images Used for Training : 20

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 = "strangerzonehf/Flux-Isometric-3D-LoRA"
trigger_word = "Isometric 3D"  
pipe.load_lora_weights(lora_repo)

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

Trigger words

You should use Isometric 3D to trigger the image generation.

Download model

Weights for this model are available in Safetensors format.

Download them in the Files & versions tab.