---
tags:
- text-to-image
- lora
- diffusers
- template:diffusion-lora
widget:
- text: 'ctoon, A cartoon drawing of a white cat with a black sunglasses around its eyes. The cats eyes are squinted and the cats ears are a light pink color. There are two yellow stars on the wall to the right of the cat.'
  output:
    url: images/C1.png
- text: 'ctoon, A cartoon drawing of a white penguin sitting on a red chair. The penguin has a yellow beak and yellow feet. The background of the penguin is a bright blue color.'
  output:
    url: images/C4.png
- text: 'ctoon, A cartoon drawing of a cat wearing sunglasses. The cat is facing towards the left side of the image. It is holding a wine glass with wine in it. There is a bottle of wine to the right of the cat. There are two stars to the left of the animal. The background is a light beige color.'
  output:
    url: images/C3.png
base_model: black-forest-labs/FLUX.1-dev
instance_prompt: ctoon
license: creativeml-openrail-m
---
# Flux.1-Dev-Ctoon-LoRA

<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 

**prithivMLmods/Flux.1-Dev-Ctoon-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           | 20 & 2700 |
| Epoch                     | 15    | Save Every N Epochs       | 1     |

    Labeling: florence2-en(natural language & English)
    
    Total Images Used for Training : 22

## 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 = "prithivMLmods/Flux.1-Dev-Ctoon-LoRA"
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](/prithivMLmods/Flux.1-Dev-Ctoon-LoRA/tree/main) them in the Files & versions tab.