| This application uses diffusion to create **Multi-View Optical Illusions** (or “Visual Anagrams”) - a method developed by [Daniel Geng et al. at the University of Michigan](https://dangeng.github.io/visual_anagrams/). See their original post for good examples and an overview of how it works. | |
| Their code can be found [here](https://github.com/dangeng/visual_anagrams) (along with tips for choosing prompts) and is used heavily in this app. The method is zero-shot, so this Space uses the pretrained diffusion model [DeepFloyd](https://huggingface.co/DeepFloyd), as in the original paper. | |
| Please report any issues to Callum Canavan on [Hugging Face](https://huggingface.co/callum-canavan) or [Twitter/X](https://twitter.com/CallumCanavan3). |