This story was originally published on HackerNoon at: https://hackernoon.com/this-ai-can-translate-any-input-into-any-output-heres-why-its-a-big-deal).
Turning any kind of input into any kind of output using AI
Check more stories related to machine-learning at: https://hackernoon.com/c/machine-learning).
You can also check exclusive content about #ai), #artificial-intelligence), #software-development), #agi), #ml), #research), #art), #hackernoon-top-story), #hackernoon-es), #hackernoon-hi), #hackernoon-zh), #hackernoon-vi), #hackernoon-fr), #hackernoon-pt), #hackernoon-ja), and more.
This story was written by: [@mikeyoung44](https://hackernoon.com/u/mikeyoung44)). Learn more about this writer by checking [@mikeyoung44's](https://hackernoon.com/about/mikeyoung44)) about page,
and for more stories, please visit [hackernoon.com](https://hackernoon.com)).
CoDi is a game-changing generative model that can handle a mixed bag of inputs. It can handle text, audio, video, images and transmute them into any other combination of outputs. CoDi uses a multi-stage training scheme, meaning it can train on a variety of tasks.
