You can add location information to your Tweets, such as your city or precise location, from the web and via third-party applications. You always have the option to delete your Tweet location history. Learn more
Deoldify doesn't have the ability for such distinctions, yet.
This is where a sort of "common sense" or understanding of the world might come in handy with this stuff. Really not sure what that would consist of but it's interesting to think about.
Have you tried running DeOldify on images that were produced grayscale, like charcoal/graphite drawings? I’d be really interested in what kind of color it assumes
Oh yes, it does a great job on some of those. Many examples of a wide variety: https://www.youtube.com/watch?v=J0VF0VudUEw&feature=youtu.be … https://twitter.com/citnaj/status/1203254759731236864 …https://twitter.com/citnaj/status/1153176850996191232 …
One idea is time buckets fed into the model. For example: [1800-1900],[1900-1930],[1930-1945],[1945-1960],[1960-1980], [1980-2020]
Twitter may be over capacity or experiencing a momentary hiccup. Try again or visit Twitter Status for more information.
