attribution

mise uses data and images from these sources.

• TMDB — film titles, posters, and cast and crew credits.

  This application uses TMDB and the TMDB APIs but is not endorsed, certified, or otherwise approved by TMDB.

• Hardcover — book titles, covers, and editions.

• Last.fm — listening and tag data for songs.

  Data from Last.fm.

• Deezer — song previews, cover art, and links to full tracks.

• MusicBrainz and ListenBrainz — matching songs and artists across sources. Public domain (CC0).

• The Metropolitan Museum of Art — public-domain artwork images and data. Public domain (CC0).

• Art Institute of Chicago — public-domain artwork images and data. Public domain (CC0).

• Cleveland Museum of Art — public-domain artwork images and data. Public domain (CC0).

• Wikimedia Commons — public-domain scans of artwork.

• Open Library — book cover images, as a fallback.

• PoetryDB — public-domain poems.

• Text2Colors (Bahng et al.) — training data for the color-palette model.

  Hyojin Bahng, Seungjoo Yoo, Wonwoong Cho, David Keetae Park, Ziming Wu, Xiaojuan Ma, and Jaegul Choo, "Coloring with Words: Guiding Image Colorization through Text-based Palette Generation," ECCV 2018.

• Google Fonts — typefaces, loaded to match each mood.