---
tags:
- text-to-image
- lora
- diffusers
- template:diffusion-lora
widget:
- text: 'Cute 3d Kawaii, a cartoon figure stands on a light blue surface. The figures face is adorned with a yellow t-shirt, a pair of light blue shorts, and yellow and orange shoes. Its eyes, a smile, and a few small black dots dot the face. The head of the figure has long dark brown hair, and two ears are sticking out from the sides of her head. The background is a light teal, with a few white clouds floating in the air.'
  output:
    url: images/CK2.png
- text: 'Cute 3d Kawaii, Captured from a low-angle perspective on a light blue backdrop, a cartoon ghost is positioned in the center of the frame. The ghost is adorned with a smiley face, adorned with black eyes, black circles, and pink circles. Its mouth is open, revealing a pink tongue. Its teeth are adorned with small white dots, adding a pop of color to the scene. Above the ghost are three white clouds floating in the air. The background is a muted blue, creating a stark contrast to the ghost.'
  output:
    url: images/CK3.png
- text: 'Cute 3d Kawaii, a 3D rendering of a female dolls head is displayed against a pink backdrop. The dolls face is adorned with a white collar, a white shirt, and brown suspenders. Her hair is styled in a ponytail, adding a pop of color to the scene. Her eyes are tinted brown, and her eyebrows are a darker shade of brown. Her lips are a lighter shade of pink, and shes wearing a white button-down shirt underneath her. Her ears are slender and pointy. Her mouth is slightly slightly parted, as if shes looking at the viewer.'
  output:
    url: images/CK4.png
base_model: black-forest-labs/FLUX.1-dev
instance_prompt: Cute 3d Kawaii
license: creativeml-openrail-m
---
![strangerzonehf/Flux-Cute-3D-Kawaii-LoRA](images/3D.png)

<Gallery />

**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-Cute-3D-Kawaii-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 & 3270 |
| Epoch                     | 18    | Save Every N Epochs       | 1     |

    Labeling: florence2-en(natural language & English)
    
    Total Images Used for Training : 24

## Best Dimensions

- 768 x 1024 (Best)
- 1024 x 1024 (Default)
    
## Setting Up
```python
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-Cute-3D-Kawaii-LoRA"
trigger_word = "Cute 3d Kawaii"  
pipe.load_lora_weights(lora_repo)

device = torch.device("cuda")
pipe.to(device)
```
## Trigger words

You should use `Cute 3d Kawaii` to trigger the image generation.

## Download model

Weights for this model are available in Safetensors format.

[Download](/strangerzonehf/Flux-Cute-3D-Kawaii-LoRA/tree/main) them in the Files & versions tab.