---
tags:
- text-to-image
- lora
- diffusers
- template:diffusion-lora
widget:
- text: 'Coloring Book, A black and white drawing of a truck parked in front of a house. The truck is facing towards the right side of the image. There is a large tree to the right of the truck. There are small bushes to the left of the house. A fence is behind the truck on the right. The house has a roof that is made up of wood. The sky above the house is filled with fluffy white clouds.'
  output:
    url: images/EB1.png
- text: 'Coloring Book, A black and white pencil sketch of a fox standing on its hind legs. The foxs fur is a light brown color, and its ears are a darker brown. Its eyes are black, and the foxs mouth is slightly open, as if it is about to go into the water. Thefoxs ears are sticking up, and it has a black nose and black eyes. There is a tree trunk on the left side of the image, and there are clouds in the sky. There are plants on the right and left of the fox.'
  output:
    url: images/EB2.png
- text: 'Coloring Book, An eye-level view of a white sports car, the car is facing towards the right. The car is positioned in front of a backdrop of a cityscape, with the city skyline in the background. It is a black and white monochromatic image, with black accents on the cars body and the hood. The front of the car has a large headlight in the center of the front, and a black bumper with a yellow emblem on the right side of the headlight. On the left side, there are two large black tires with silver rims on them.'
  output:
    url: images/EB3.png
base_model: black-forest-labs/FLUX.1-dev
instance_prompt: Coloring Book
license: creativeml-openrail-m
---
# Coloring-Book-Flux-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/Coloring-Book-Flux-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 & 2000|
| Epoch                     | 10   | Save Every N Epochs       | 1      |

    Labeling: florence2-en(natural language & English)
    
    Total Images Used for Training : 10 [ Hi-RES ]

## Best Dimensions

- 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 = "prithivMLmods/Coloring-Book-Flux-LoRA"
trigger_word = "Coloring Book"  
pipe.load_lora_weights(lora_repo)

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

## Data source
    
    - https://playground.com/
    
## Trigger words

You should use `Coloring Book` to trigger the image generation.


## Download model

Weights for this model are available in Safetensors format.

[Download](/prithivMLmods/Coloring-Book-Flux-LoRA/tree/main) them in the Files & versions tab.