All language subtitles for 1. What the Future brings with AI-Video creation

af Afrikaans
sq Albanian
am Amharic
ar Arabic Download
hy Armenian
az Azerbaijani
eu Basque
be Belarusian
bn Bengali
bs Bosnian
bg Bulgarian
ca Catalan
ceb Cebuano
ny Chichewa
zh-CN Chinese (Simplified)
zh-TW Chinese (Traditional)
co Corsican
hr Croatian
cs Czech
da Danish
nl Dutch
en English
eo Esperanto
et Estonian
tl Filipino
fi Finnish
fr French
fy Frisian
gl Galician
ka Georgian
de German
el Greek
gu Gujarati
ht Haitian Creole
ha Hausa
haw Hawaiian
iw Hebrew
hi Hindi
hmn Hmong
hu Hungarian
is Icelandic
ig Igbo
id Indonesian
ga Irish
it Italian
ja Japanese
jw Javanese
kn Kannada
kk Kazakh
km Khmer
ko Korean
ku Kurdish (Kurmanji)
ky Kyrgyz
lo Lao
la Latin
lv Latvian
lt Lithuanian
lb Luxembourgish
mk Macedonian
mg Malagasy
ms Malay
ml Malayalam
mt Maltese
mi Maori
mr Marathi
mn Mongolian
my Myanmar (Burmese)
ne Nepali
no Norwegian
ps Pashto
fa Persian
pl Polish
pt Portuguese
pa Punjabi
ro Romanian
ru Russian
sm Samoan
gd Scots Gaelic
sr Serbian
st Sesotho
sn Shona
sd Sindhi
si Sinhala
sk Slovak
sl Slovenian
so Somali
es Spanish
su Sundanese
sw Swahili
sv Swedish
tg Tajik
ta Tamil
te Telugu
th Thai
tr Turkish
uk Ukrainian
ur Urdu
uz Uzbek
vi Vietnamese
cy Welsh
xh Xhosa
yi Yiddish
yo Yoruba
zu Zulu
or Odia (Oriya)
rw Kinyarwanda
tk Turkmen
tt Tatar
ug Uyghur
Would you like to inspect the original subtitles? These are the user uploaded subtitles that are being translated: 1 00:00:00,200 --> 00:00:06,830 I hope you have created some pictures, because now we dive deeper and look how we can make videos of 2 00:00:06,830 --> 00:00:08,840 our AI influencer. 3 00:00:08,840 --> 00:00:15,170 And I need to say, there are a lot of ways in this video, I will give you a quick overview of what 4 00:00:15,170 --> 00:00:22,790 the future brings, because we have a nice research paper and as soon as this code is out, I will immediately 5 00:00:22,790 --> 00:00:29,510 update the course because I think this is the real stuff and I think this will change TikTok. 6 00:00:29,510 --> 00:00:32,180 So look at a second at this. 7 00:00:32,300 --> 00:00:38,090 You see here all this dancing woman or even enemies and so on. 8 00:00:38,090 --> 00:00:41,060 And this is all created via code. 9 00:00:41,060 --> 00:00:44,720 Yes, this was a picture and it was animated. 10 00:00:44,720 --> 00:00:48,200 This research paper is from the Alibaba Group. 11 00:00:48,200 --> 00:00:51,290 And they have a really, really cool program. 12 00:00:51,290 --> 00:00:55,010 If we scroll down a bit, you can also look the YouTube videos. 13 00:00:55,010 --> 00:01:01,910 And if you want you can also look how the technique behind this work to dive too deep in this I only 14 00:01:01,910 --> 00:01:03,200 want to show you this. 15 00:01:03,200 --> 00:01:06,440 You simply have a picture and then the program. 16 00:01:06,440 --> 00:01:07,460 The code works. 17 00:01:07,460 --> 00:01:11,330 You can simply drag and drop a video of a dancing person. 18 00:01:11,330 --> 00:01:20,330 The dances will get extracted and after they are extracted, they will get used on your picture. 19 00:01:20,330 --> 00:01:23,150 And I think this works really, really cool. 20 00:01:23,150 --> 00:01:28,400 At least in this research paper you can animate whatever you want. 21 00:01:28,400 --> 00:01:34,940 You can animate a picture of Iron Man, of animates, of everything that you like and down a bit. 22 00:01:34,940 --> 00:01:38,990 Yes, there is also realistic stuff here possible. 23 00:01:38,990 --> 00:01:43,340 If we go back to this video, I think this is like really impressive. 24 00:01:43,340 --> 00:01:45,170 These are old models. 25 00:01:45,170 --> 00:01:46,640 They don't work that well. 26 00:01:46,640 --> 00:01:51,200 But the new model from the Alibaba Group, this works like really really cool. 27 00:01:51,200 --> 00:01:54,290 So this is the output from the research paper. 28 00:01:54,290 --> 00:01:57,680 And they did a really really good job on this. 29 00:01:57,680 --> 00:02:01,340 And they can do this with nearly every picture. 30 00:02:01,340 --> 00:02:05,090 And this is I think this is like really really nice. 31 00:02:05,090 --> 00:02:11,510 I must admit we will make videos that look even better, but we do it in a different way. 32 00:02:11,510 --> 00:02:12,860 So I'm excited. 33 00:02:12,860 --> 00:02:16,370 As soon as this is out, you can also change outfits and so on. 34 00:02:16,370 --> 00:02:19,430 If you look at this, this is like really cool. 35 00:02:19,430 --> 00:02:20,330 I think. 36 00:02:20,330 --> 00:02:25,700 Of course, there are also other ways and also ways that you can use right now. 37 00:02:25,700 --> 00:02:31,490 One way is for example stable diffusion web UI move to move yes. 38 00:02:31,490 --> 00:02:36,200 With move to move you can create similar videos that you already saw. 39 00:02:36,200 --> 00:02:40,070 But I must say this works a little bit tough. 40 00:02:40,070 --> 00:02:43,220 So you need to install a lot of stuff. 41 00:02:43,220 --> 00:02:46,610 And I don't like this too much. 42 00:02:46,610 --> 00:02:54,020 But there are other ways we will use a Google Colab notebook, and we will swap our faces. 43 00:02:54,020 --> 00:03:00,080 In the next video we will search for target videos and after that we will do our face swaps. 44 00:03:00,080 --> 00:03:04,850 And I think this is right now the absolute best way to do this. 45 00:03:04,850 --> 00:03:06,020 So stay tuned. 46 00:03:06,020 --> 00:03:10,190 In the next video we will search for our source videos. 47 00:03:10,190 --> 00:03:17,330 And of course, as soon as the research paper from Alibaba is out, I will update this course immediately. 4491

Can't find what you're looking for?
Get subtitles in any language from opensubtitles.com, and translate them here.