---
license: other
license_name: bespoke-lora-trained-license
license_link: https://multimodal.art/civitai-licenses?allowNoCredit=False&allowCommercialUse=RentCivit&allowDerivatives=False&allowDifferentLicense=False
tags:
- text-to-image
- stable-diffusion
- lora
- diffusers
- template:sd-lora
- migrated
- character

base_model: black-forest-labs/FLUX.1-dev
instance_prompt: Cinematic style
widget:
- text: 'Beauty, realism, chiaroscuro, cinematic quality, rays of light, play of shadow and light, Abstract lighting effects, Victorian style. Gothic girl in a masquerade mask in the Baroque style, with gold and indigo decorative details, rough style'
  
  output:
    url: >-
      31773249.jpeg

---

# Magic of Art  2  (FLUX) 

<Gallery />



([CivitAI](https://civitai.com/models/))

## Model description

<p>CFG Scale: 2.0 - 3.5 experiment with the values</p><p>Steps: 14 - 22 experiment with the values</p><p>Weight: 0.3 - 1.</p><p>Works well with weight: ( 0.6 - 0.8 ), experiment with weights up to 1</p>

## Trigger words
You should use `Cinematic style`, `Beauty`, `Realism`, `Photorealism`, `Chiaroscuro`, `High quality` to trigger the image generation.
    

## Download model

Weights for this model are available in Safetensors format.

[Download](/Keltezaa/magic-of-art-2-flux/tree/main) them in the Files & versions tab.

## Use it with the [🧨 diffusers library](https://github.com/huggingface/diffusers)

```py
from diffusers import AutoPipelineForText2Image
import torch

device = "cuda" if torch.cuda.is_available() else "cpu"

pipeline = AutoPipelineForText2Image.from_pretrained('black-forest-labs/FLUX.1-dev', torch_dtype=torch.bfloat16).to(device)
pipeline.load_lora_weights('Keltezaa/magic-of-art-2-flux', weight_name='Magic of Art  2  (FLUX).safetensors')
image = pipeline('Beauty, realism, chiaroscuro, cinematic quality, rays of light, play of shadow and light, Abstract lighting effects, Victorian style. Gothic girl in a masquerade mask in the Baroque style, with gold and indigo decorative details, rough style').images[0]
```

For more details, including weighting, merging and fusing LoRAs, check the [documentation on loading LoRAs in diffusers](https://huggingface.co/docs/diffusers/main/en/using-diffusers/loading_adapters)