Renders videos in a style similar to the one seen on the Netflix show "Arcane."

The primary and only trigger word is "ArcaneStyle."

Recommended Strength is 1.0 to 1.2.

At least 4 to 6 low noise steps are recommended.

If you are using it in conjunction with other LoRAs, the style bias in those models can overpower this one, so you will likely need to put tags like "Realistic" in the negative to compensate.

California AB 2013 Training Data Disclosure

• This LoRA was fine-tuned using visual data consisting of still frames captured from the television series Arcane, along with officially released promotional images and posters produced for the show. The training data includes copyrighted material owned by third parties, including the show’s producers, distributors, and associated rights holders. No training data was licensed or purchased. This LoRA is provided for non-commercial use only under the terms of its distribution.

• The dataset consists of approximately 150 images collected from publicly accessible sources between approximately 2021 and 2025. Data was processed through standard resizing, cropping, normalization, and labeling steps. No synthetic data was used.

• This model is intended for non-commercial, experimental, and educational use. Generated outputs may reflect copyrighted visual styles or themes associated with the underlying training data. Users are responsible for ensuring compliance with applicable copyright law, other intellectual property laws, and all other applicable laws.