metadata
tags:
- text-to-image
- lora
- diffusers
- template:diffusion-lora
- 3D
- Isometric 3D
- OBJ
widget:
- text: >-
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.
output:
url: images/ID3.png
- text: >-
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.
output:
url: images/ID2.png
- text: >-
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.
output:
url: images/ID4.png
base_model: black-forest-labs/FLUX.1-dev
instance_prompt: Isometric 3D
license: creativeml-openrail-m
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.