---
tags:
- text-to-image
- lora
- diffusers
- template:diffusion-lora
widget:
- text: 'Ctoon++, A cartoon drawing of a man with black hair and brown eyes. He is wearing a white t-shirt with a blue jacket over his shoulders. The man has his hands on his shoulders and his eyes are closed. His hands are covered with brown gloves. The background is a light beige color with black writing on it.'
  output:
    url: images/1.png
- text: 'Ctoon++, A cartoon drawing of a girl with black hair tied up in a ponytail with a red bow. She is wearing a pink shirt with the words "CANTON YMCA" and "UHU HANUBALL" written on it. The girl is facing to the right of the image, with her right arm raised in the air. Her left hand is raised up, while her right hand is reaching out towards the girl. The background is a light beige, with a rough texture.'
  output:
    url: images/2.png
- text: 'Ctoon++, A cartoon drawing of a boy with short dark hair and glasses. He is wearing a white button up shirt with a brown tie around his neck. He has a backpack strap over his shoulders. The background is a light peach color.'
  output:
    url: images/3.png
- text: 'Ctoon++, A cartoon drawing of a woman with long dark brown hair. She is wearing a light blue button up shirt with a black collar. She has a white strap over her shoulder. The background is a light peach color.'
  output:
    url: images/4.png
- text: 'Ctoon++: A cartoon drawing of Elon Musk with short brown hair and a confident smile. He is wearing a black t-shirt with a blazer, standing in front of a large rocket. The background is a clear night sky filled with stars and a glowing moon.'
  output:
    url: images/5.png
- text: 'Ctoon++, A cartoon drawing of a playful orange tabby cat with green eyes. The cat is sitting on a blue cushion, holding a small fish toy in its paws. The background is a light yellow color with paw prints scattered across it.'
  output:
    url: images/6.png
base_model: black-forest-labs/FLUX.1-dev
instance_prompt: Ctoon++
license: creativeml-openrail-m
---
![lkjdfngldn.png](https://cdn-uploads.huggingface.co/production/uploads/65bb837dbfb878f46c77de4c/c521DJW_qdtQqtYIgM_0b.png)

<Gallery />

# Model description for Ctoon-Plus-Plus

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           | 16 & 2330 |
| Epoch                     |  15   | Save Every N Epochs       | 1     |

    Labeling: florence2-en(natural language & English)
    
    Total Images Used for Training : 33

## Best Dimensions & Inference

| **Dimensions** | **Aspect Ratio** | **Recommendation**       |
|-----------------|------------------|---------------------------|
| 1280 x 832      | 3:2              | Best                     |
| 1024 x 1024     | 1:1              | Default                  |

### Inference Range

- **Recommended Inference Steps:** 30–35

## 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/Ctoon-Plus-Plus"
trigger_word = "Ctoon++"  
pipe.load_lora_weights(lora_repo)

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

## Trigger words

You should use `Ctoon++` to trigger the image generation.

## Download model

Weights for this model are available in Safetensors format.

[Download](/strangerzonehf/Ctoon-Plus-Plus/tree/main) them in the Files & versions tab.