Figured with the new ‘WAI’ image gen model, it would be a good suggestion to supplement that feature with text-to-speech anime voice options.
This would allow users to essentially generate complete anime stories, and would also complement any image-to-video models once added in the near future. Ideally, more voice options the better — or could also supplement voice settings on the app to adjust the EQ/pitch/tone of voices for further customization.