metadata
license: creativeml-openrail-m
**Update: ** Arcane Diffusion v2 now available!
This is the fine-tuned Stable Diffusion model trained on images from the TV Show Arcane. Use the tokens arcane style in your prompts for the effect.
Sample images used for training:
Sample images from the model:
Update: Version 2 uses the diffusers based dreambooth training and prior-preservation loss is way more effective. The .ckpt was converted with a script and works with automatics repo.
Disclaimer v1 (arcane-diffusion-5k): This model was trained using Unfrozen Model Textual Inversion utilizing the Training with prior-preservation loss methods. There is still a slight shift towards the style, while not using the arcane token.