12,275
edits
m (→Idea: formatting) |
(→Idea) |
||
(One intermediate revision by one other user not shown) | |||
Line 4: | Line 4: | ||
=== Idea === | === Idea === | ||
In the 1980s, British [https://www.channel4.com Channel 4] tried to imagine the TV of the future. They created Max Headroom as the host of a music show. He was supposed to be an AI character although played by an actual human actor, [[wikipedia:Matt Frewer|Matt Frewer]]. After shooting, the fragments were cut in a way that would be called “[https://www.pbs.org/video/off-book-art-glitch glitchy]” nowadays. This imperfection is a very important part of the character, serving as a signifier for an artificial humanoid character. | |||
In the 1980s, British [https://www.channel4.com | |||
{{#ev:youtube|vS17G1MXzLk}} | {{#ev:youtube|vS17G1MXzLk}} | ||
When so called neural networks came up, a discussion | When so called neural networks came up, a discussion started about which kinds of labour can be done by so called artificial intelligence. Some people are convinced even artists and musicians will be replaced by computer systems. | ||
[ | [[wikipedia:Hatsune Miku|Hatsune Miku]] was originally the name voicebank which can be used with Yamaha’s Vocaloid software. From 2010 on, albums for Hatsune Miku have been produced. In 2012 “she” gave her first concert as a holograph, gaining huge popularity. | ||
{{#ev:youtube|YSyWtESoeOc}} | {{#ev:youtube|YSyWtESoeOc}} | ||
Line 23: | Line 22: | ||
[[File:dog_01.gif]] | [[File:dog_01.gif]] | ||
[https://runwayml.com/ RunwayML] is a SaaS company providing shared machine learning models. For this experiment, the StyleGAN (to be more precise [https://github.com/NVlabs/stylegan2 StyleGAN2]) framework by NVIDIA was used, which gained popularity due to its ability of generating almost photorealistic faces. The model was trained with the [http://niessnerlab.org/projects/roessler2018faceforensics.html FaceForensics dataset] by Technische Universität München, consisting of videos of news hosts. Using [http://ffmpeg.org/ | [https://runwayml.com/ RunwayML] is a SaaS company providing shared machine learning models. For this experiment, the StyleGAN (to be more precise [https://github.com/NVlabs/stylegan2 StyleGAN2]) framework by NVIDIA was used, which gained popularity due to its ability of generating almost photorealistic faces. The model was trained with the [http://niessnerlab.org/projects/roessler2018faceforensics.html FaceForensics dataset] by Technische Universität München, consisting of videos of news hosts. Using [http://ffmpeg.org/ ffmpeg] a part of these video files were converted to image sequences and fed into RunwayML’s training system. After completing the training, a video was generated walking through different parameters for image generation, creating this fluid transition from one host to another. | ||
This training was completed after 2000 steps. The model can be expanded and the quality improved by continuing the training. | This training was completed after 2000 steps. The model can be expanded and the quality improved by continuing the training. | ||
[[File:runway.png]] | [[File:runway.png]] |