---
tags:
- text-to-image
- lora
- diffusers
- template:diffusion-lora
widget:
- text: 'Clouds Illusion, a vibrant green tree stands out against a backdrop of a blue sky dotted with fluffy white clouds. The trees trunk is adorned with a thick layer of green leaves, adding a touch of nature to the scene. The leaves are a mix of green and yellow, while the roots of the tree are a darker darker green. The trunk is encircled by a series of brown vines, adding depth to the composition. The sky is a deep blue, with a few wispy clouds in the distance.'
  output:
    url: images/CI1.png
- text: 'Clouds Illusion, a whimsical bicycle is adorned with a vibrant array of vibrant colors, adding a pop of color to the scene. The bicycles frame is adorned in a variety of hues of red, yellow, green, and blue, creating a striking contrast against the backdrop of the bicycle and the sky. The sky is a deep blue, with a few wispy white clouds dotting the horizon.'
  output:
    url: images/CI2.png
- text: 'Clouds Illusion, A drawing of an man made out of Mountains, with a blue sky background, in the style of Stylized llustration, with soft pastel colors, pop art '
  output:
    url: images/CI3.png
base_model: black-forest-labs/FLUX.1-dev
instance_prompt: Clouds Illusion
license: creativeml-openrail-m
---
# Clouds-Illusion-Flux-LoRA

<Gallery />

- Hosted Here🧨: https://huggingface.co/spaces/prithivMLmods/FLUX-LoRA-DLC

**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/Clouds-Illusion-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           | 25 & 2.5K|
| Epoch                     | 10   | Save Every N Epochs       | 1      |

    Labeling: florence2-en(natural language & English)
    
    Total Images Used for Training : 16 [ 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/Clouds-Illusion-Flux-LoRA"
trigger_word = "Clouds Illusion"  
pipe.load_lora_weights(lora_repo)

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

## Data source
    
    - https://freeflo.ai/
    
## Trigger words

You should use `Clouds Illusion` to trigger the image generation.


## Download model

Weights for this model are available in Safetensors format.

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