YouTube2Text

Как бесплатно генерировать видео с помощью Gemini Omni 1.1 топовый ИИ для генерации роликов — Transcript

by Yevgeniy Kovalenko · 2,466 words · 367 segments · language en · Watch on YouTube

Full transcript

  1. 0:00Hi. My name is Evgeny Kovalenko, and on
  2. 0:03September 23rd, so yesterday, Google
  3. 0:05announced that anyone can now create
  4. 0:07stunning videos. These are, how can I
  5. 0:11say, amazing, yes, such delightful,
  6. 0:16stunning videos in HD format, that is,
  7. 0:191.280 x 720 with Gemini Omni. Yes,
  8. 0:24that's their model, it's the top model
  9. 0:27for video generation. They integrated
  10. 0:30their latest model into Google, so
  11. 0:33anyone with a Google account can create
  12. 0:36videos for free. It's free. That is,
  13. 0:40anyone with a Google account can do
  14. 0:42this for free since yesterday. I'll
  15. 0:45quickly run through the release and try
  16. 0:47to see what they updated there, how to
  17. 0:50use it. Yes, Google writes in its
  18. 0:52release that they are sharing the magic
  19. 0:54of video creation with anyone. Yes, it
  20. 0:57is expanding access to Google. Now
  21. 1:00anyone with a Google account or Google
  22. 1:02Workspace account can generate
  23. 1:04high-quality videos. No cost using our
  24. 1:08latest model, meaning no financial
  25. 1:11outlay, using their latest Gemini Omni
  26. 1:131.1 Flash model. I went to Artificial
  27. 1:17Analysis Arena—they took my word for
  28. 1:20it, right? So, we can see the
  29. 1:22leaderboard. Gemini Omni Flash is a
  30. 1:26slight lead over Omni 3.0. It's not
  31. 1:29specified which version, but we can see
  32. 1:32it's from Google, meaning it's either
  33. 1:3411 or 1.0. So, we can see Google is in
  34. 1:37the lead. Returning to the release, the
  35. 1:40model and its creative settings. Yes,
  36. 1:43it doesn't matter whether you're
  37. 1:45launching a business, uniting a
  38. 1:46community, or presenting your product.
  39. 1:51You can use Google's latest advanced EI
  40. 1:54model to create inspiring videos
  41. 1:57without professional editing skills or
  42. 2:00a big budget. Here, in the background,
  43. 2:03we can see all sorts of promotional
  44. 2:05opportunities from the release. Yes,
  45. 2:08look how people can generate and edit
  46. 2:10video scenes using OMNI 1.1 in GoogleS
  47. 2:13at no cost. They seem to point out in
  48. 2:17every block that it's free, no money,
  49. 2:20for everyone. To use the generation
  50. 2:23feature, go to the wiids.new website,
  51. 2:25and everything will happen there. I'll
  52. 2:28go there now and try it out. And here,
  53. 2:30going down a bit, yes, they have a good
  54. 2:33look at Omni 1.1 in GoogleS. In general
  55. 2:36, this model—I filmed a separate
  56. 2:37video, but I'll quickly say it here.
  57. 2:40The first feature they highlight is
  58. 2:42scene expansion with, uh, smooth, yes,
  59. 2:44transitions. That is, you can make a
  60. 2:48scene longer, extend it, while
  61. 2:50maintaining the visual context,
  62. 2:51maintaining the lighting, maintaining
  63. 2:53the characters, maintaining the way
  64. 2:55everything looks, yes, and, uh, the
  65. 2:57consistency of the environment. The
  66. 3:00second thing they highlight is the
  67. 3:02ability to control how long the scene
  68. 3:05should be, right? That is, choose the
  69. 3:08duration of your generated clip that
  70. 3:11suits you, yes, so that it clearly
  71. 3:15matches your story and your voiceover.
  72. 3:19The third thing they highlight is the
  73. 3:21ability to create new videos and videos
  74. 3:23of generated scenes in Full HD. It's
  75. 3:27strange, they say HD here, but Full HD
  76. 3:29here. Yeah, right. So 1920 x 1080 is
  77. 3:31Full HD. HD is just 1.280 x 720. Well,
  78. 3:37they indicate that it's possible. It
  79. 3:39doesn't say it's free, but it does say
  80. 3:41it's possible. And upscaling, yes,
  81. 3:44meaning you can already improve, expand
  82. 3:47, and enlarge existing AI-generated
  83. 3:49videos, yes, using their features, yes,
  84. 3:52video enhancement, expansion. Then they
  85. 3:55say it's created for all audiences. And
  86. 3:59then they say that every video
  87. 4:01generated with Gemini Omni has a Synth
  88. 4:03ID embedded. Synth ID is an invisible
  89. 4:06watermark, yes, which is embedded in
  90. 4:09every frame of the video. It's being
  91. 4:12done so that if someone, anyone, wants
  92. 4:15to check whether a video was generated
  93. 4:18using artificial intelligence, they can
  94. 4:22do so thanks to this built-in watermark
  95. 4:25. Yes, this is simply designed to
  96. 4:28create and share transparency, so that
  97. 4:31everything is, well, so that people
  98. 4:33know what's real and what's generated,
  99. 4:35right? Let's go to the very bottom of
  100. 4:39the release, it says again, go to
  101. 4:40visit.ne new, I click on "vits new."
  102. 4:43I'm redirected to a website where
  103. 4:44everything is quite simple. There's a
  104. 4:46window with choices, yes, I don't think
  105. 4:47I'm blocking anything. The only thing
  106. 4:49here is simply creating a video, right?
  107. 4:53Among the new features, GoogleS has
  108. 4:55created AI Videos, which is video
  109. 4:58creation using artificial intelligence,
  110. 5:00avatar creation, and document
  111. 5:02conversion. So, if you have a Word
  112. 5:05document, you can upload it and turn it
  113. 5:07into a video. There are also video
  114. 5:10slides. There's just a standard video
  115. 5:13recording. There's the ability to
  116. 5:15upload, uh, videos, just store a
  117. 5:17template, yes, that is, use, uh,
  118. 5:20standard templates for beautiful videos
  119. 5:22with transitions, like here. And
  120. 5:25there's Edit Videos. It's a pretty cool
  121. 5:28thing, as you can see. The girl snaps
  122. 5:30her fingers, and her style changes
  123. 5:32every time. Yeah, I think you've seen a
  124. 5:35similar video. It's only for a premium
  125. 5:37account. Basically, they didn't promise
  126. 5:41that video editing would be free or for
  127. 5:44anyone and so on. But let's move on to
  128. 5:47creating a video. I'll click Create
  129. 5:49Video. This is the interface that opens
  130. 5:51up for me, yes, where I can use it. The
  131. 5:54studio is like this, yes, where I can
  132. 5:55use the tools. So, I have Create,
  133. 5:57describe your video. You can add
  134. 6:00ingredients like brand images,
  135. 6:02characters, and more. Yes, you can
  136. 6:05create an avatar right away. And the
  137. 6:07ingredients are up to three images,
  138. 6:09which are described here, right? So,
  139. 6:12these could be parts of clothing, it
  140. 6:14could be some kind of appearance, and
  141. 6:16so on. We switch at the bottom. We can
  142. 6:20choose landscape—this is a landscape,
  143. 6:23uh, photo, like this, yeah, wide—and
  144. 6:25portrait—this is a vertical
  145. 6:27resolution. So, as I said, you see,
  146. 6:31they didn't mention in the release that
  147. 6:331080 is free to generate, but they did
  148. 6:36mention that it's possible. So, this is
  149. 6:391.280 by 720. The video model is the
  150. 6:43latest. Omni has no other choice here.
  151. 6:46And you can choose duration, which is a
  152. 6:48duration of no less than 3 seconds and
  153. 6:50no more than 10 seconds. We can
  154. 6:54basically leave these settings and try
  155. 6:56something and try generating something.
  156. 7:00Here I have an empty frame for 5
  157. 7:02seconds. You can click the plus sign,
  158. 7:07so you can insert a generated video
  159. 7:09into this empty frame, you can delete
  160. 7:11it, you can put some real video, and
  161. 7:14then build it up with a generated one,
  162. 7:16right? The plus sign adds another frame
  163. 7:20for 5 seconds. And here in the middle,
  164. 7:23we can create a transition, that is,
  165. 7:25add a transition. And you can delete it
  166. 7:28: just select it, press delete, and
  167. 7:30it’s deleted. I select it, press
  168. 7:32Delete, and everything is deleted.
  169. 7:34There’s an empty space, I select it,
  170. 7:36yes, I click on AI video. And now I can
  171. 7:38start generating. That is, if you
  172. 7:40don’t have this, then you need to
  173. 7:42click on the plus sign, create, select
  174. 7:44it from the left sidebar, in the right
  175. 7:46sidebar, click on A video, and start
  176. 7:48generating the video. There is also the
  177. 7:51option to simply create a video from an
  178. 7:53image, yes, Animate. That is, we click
  179. 7:56on Animate, and we need to add an image
  180. 7:58here and describe how we want this
  181. 8:01image to be animated. Let me click on
  182. 8:03add image. I’ll upload this image
  183. 8:07here. It’s Henry Cavell. Cavil. Cavil
  184. 8:11Superman there. Who else is he? The
  185. 8:13Witcher. Anyway, Kenny, who knows,
  186. 8:16knows. Who doesn’t know, well, what
  187. 8:18can I do? I generated it, by the way, I
  188. 8:19generated it on the RF model. A fairly
  189. 8:22old model f, but it handled it quite
  190. 8:25well. And now I'll set it, that is, we
  191. 8:28have 10 seconds left. I hope, well,
  192. 8:31let's say 10 seconds, I guess. I think
  193. 8:33it will be faster, but it's better to
  194. 8:35leave it just in case. 10 seconds. I
  195. 8:37wrote a prompt. And I wrote a prompt
  196. 8:39not just so that it would do some
  197. 8:41animation, but also so that it would
  198. 8:43speak, yes, that is, so that it would
  199. 8:45not just do something in the frame, but
  200. 8:47also speak and write text in Russian.
  201. 8:50Let's see how this works in Google. I
  202. 8:53send it, and your video starts
  203. 8:56generating. 100%written. Ah, so, I
  204. 9:00can't do this with him because it
  205. 9:04determined his appearance. and told me
  206. 9:07that I was violating the terms of use.
  207. 9:09Okay, fine. Let me try to take a simply
  208. 9:12generated woman who doesn't really
  209. 9:14exist. So, I said I'd upload a girl.
  210. 9:17And let's try animating her. Here I
  211. 9:21have her completely, damn, it's a
  212. 9:23square landscape. I wonder if it will
  213. 9:26turn it from square to rectangular or
  214. 9:29not? That's the question. The girl is
  215. 9:32completely generated, so there
  216. 9:33shouldn't be any problems with
  217. 9:35generation. I used the "create a video
  218. 9:38from a prompt" function, but that was
  219. 9:40also a bit of a mess. I'll only share
  220. 9:43this result for sponsors because I
  221. 9:45can't put such things in a regular
  222. 9:47video or on the cover. YouTube will
  223. 9:49simply censor me and won't show it to
  224. 9:52anyone. That means it will have 10
  225. 9:53views. There you go. Um, so if anyone
  226. 9:55is interested in the result, please
  227. 9:57sponsor. There are many other videos
  228. 9:59out there, I'll keep trying. Look,
  229. 10:01decide for yourself. No one is forcing
  230. 10:04you, or go to Google and try, test. I
  231. 10:07entered the prompt and sent the video
  232. 10:09for generation. It should now generate
  233. 10:11without any problems. In principle, the
  234. 10:13video is generated pretty quickly. So,
  235. 10:15while I'm talking, you can see the
  236. 10:16percentages flashing on the screen. As
  237. 10:18soon as it reaches 100, the video will
  238. 10:20be ready. I created a video generator,
  239. 10:23a specific action for the girl to
  240. 10:25perform, and for her to say a phrase in
  241. 10:27Russian. Now that's quite an
  242. 10:29interesting point. If I can do it. If
  243. 10:32not, well, then for now, it will
  244. 10:34probably be in English as standard. But
  245. 10:36in general, Gemini, Google, they
  246. 10:39generally brag and boast about having
  247. 10:42the ability to generate videos in
  248. 10:44seventy languages, 110 languages. So,
  249. 10:47if that's true, you can, uh, give it a
  250. 10:50try. Let's listen.
  251. 10:52I'm a fan of Evgeniy Kovalenko.
  252. 10:54Subscribe to his channel so you don't
  253. 10:56miss new videos about.
  254. 10:57Yes, only such fangirls can be
  255. 10:59generated for me using AI.
  256. 11:01Hi,
  257. 11:02I'm a fan of Evgeniy Kovalenko.
  258. 11:04Subscribe to his channel so you don't
  259. 11:06miss new videos. It was generated with
  260. 11:08the help of some amazing quality,
  261. 11:10meaning everything that was on the
  262. 11:12video is preserved. She gestures, she
  263. 11:14speaks beautifully, the voice is
  264. 11:16perfectly placed. Basically, as you saw
  265. 11:18before, I don't think you need to
  266. 11:19listen to it 50 times. Basically, you
  267. 11:21can rewind and listen to it. There's a
  268. 11:24Jiminy marker, and we can insert this
  269. 11:26frame down here. It's ten seconds long,
  270. 11:29as I said, it will take less than a
  271. 11:32second, but overall, honestly, I'm
  272. 11:34happy with the result of the generation
  273. 11:37, I'm happy with the quality, I'm happy
  274. 11:40with the way she speaks, the way she
  275. 11:43gestures, how beautifully it's all
  276. 11:45created, how it sounds. Well, honestly,
  277. 11:48my impression is, well, probably a nine
  278. 11:52out of ten. Well, close to perfect, yes
  279. 11:55. There is this one moment here that I
  280. 11:57didn't like. Now, just a second. That
  281. 12:00is, yes, this initial moment, when it
  282. 12:02somehow somehow cuts off. Well,
  283. 12:06basically, there's a certain trick to
  284. 12:08it, yeah, it's like a setup, like, with
  285. 12:11a frame behind the scenes, yeah, like a
  286. 12:14frame before, something that shouldn't
  287. 12:17have been there, but it's kind of
  288. 12:19inserted specifically here, yeah, to
  289. 12:22create this kind of style, yeah, but
  290. 12:24overall, it's pretty cool and
  291. 12:26well-written, so I don't know, I really
  292. 12:29like it. I generated it like this. The
  293. 12:33first video, it blocked me because of
  294. 12:34Henry Cavel's appearance. The second
  295. 12:37video, it generated for me, I'll only
  296. 12:39show it to sponsors. And the third, uh,
  297. 12:42you see it generated right before your
  298. 12:44eyes. So far, it doesn't ask for any...
  299. 12:47That is, I created the video through
  300. 12:49create, generated it completely and
  301. 12:51created it through animate, uploaded it
  302. 12:53. Yeah. Uh, so far it looks pretty cool
  303. 12:56. You can use this girl as an avatar.
  304. 12:59See, it stays right here. It's labeled
  305. 13:01A image, so we can link to it with a
  306. 13:03dog. So, any asset, any of yours, how
  307. 13:06should I say, assets, yes, you can
  308. 13:08specify them using the "at" sign, yes,
  309. 13:11so instead of constantly uploading the
  310. 13:13same photo, the same bag, the same
  311. 13:15clothes, the same person, the same
  312. 13:18talking head, and so on, you can press
  313. 13:20the "at" sign and write the caption. So
  314. 13:23, we have one image here, but we can,
  315. 13:24in principle, rename it or, in
  316. 13:26principle, access it as one image,
  317. 13:27right? So, I'll type like this with the
  318. 13:29"at" sign, and it will prompt me. And
  319. 13:32in principle, they won't all line up
  320. 13:34and prompt you one by one, right? Again
  321. 13:37, we can, for example, extend this
  322. 13:39video, yes, by 15 seconds. We can
  323. 13:42extend it, we can add another video
  324. 13:44here, create a transition. So, we can
  325. 13:46generate additional videos and create a
  326. 13:48transition between them, a smooth
  327. 13:50transition. Yes, something like, I
  328. 13:53don't know, it splits the screen or it
  329. 13:55zooms in and out—depending on how,
  330. 13:56what you choose. Yes, when I press "
  331. 13:59dissolve," one transitions into another
  332. 14:01. Fate is fading, yes, it even
  333. 14:03basically suggests on the screen what
  334. 14:04transitions there can be, right? That
  335. 14:06is, "zzolv," well, you can't see it
  336. 14:08because one transitions into another,
  337. 14:10and "fay" is from light to dark. "Push"
  338. 14:12pushes the slide. Well, basically, you
  339. 14:14can experiment. It's a pretty simple,
  340. 14:17easy, and intuitive studio. Volume
  341. 14:21control, play the video at the top,
  342. 14:22insert it at the bottom using the "
  343. 14:24insert" button. Yes, we press "insert,"
  344. 14:26it inserts. "Extend" expands the clip,
  345. 14:28right? So, seamlessly, so-called,
  346. 14:31expands it, continues it, right? That
  347. 14:34is, we press "extend" and describe how
  348. 14:36we want the video to continue. "
  349. 14:38Recreate" simply regenerates it, and "
  350. 14:41remove" deletes it. And, of course, the
  351. 14:43most important thing is how do we save
  352. 14:46it? Let's click on the file. And we can
  353. 14:52download it. We can download this video
  354. 14:54in MP4 format. And it's preparing to
  355. 14:57download. I would really like to
  356. 14:59download it and use it in my video so
  357. 15:02that people can watch. Yes, the video
  358. 15:04has downloaded, here it is, 3.5 MB, 10
  359. 15:06seconds. If you liked this video, you
  360. 15:10can give it a thumbs up, subscribe to
  361. 15:12the channel and click the bell so you
  362. 15:14don't miss new videos on this channel.
  363. 15:17And that's all. Thanks for watching.
  364. 15:19See you later. Good luck. Bye.
  365. 15:21Hello. I'm a fan of Evgeny Kovalenko.
  366. 15:24Subscribe to his channel so you don't
  367. 15:26miss new videos about And good luck.

About this transcript

This page contains the full transcript of Как бесплатно генерировать видео с помощью Gemini Omni 1.1 топовый ИИ для генерации роликов by Yevgeniy Kovalenko, generated from the public captions YouTube serves with the video. The transcript has 2,466 words across 367 segments, with the original timestamps preserved so you can click any line to jump to that moment in the embedded player.

What you can do with it

Use the transcript to take notes, quote the speaker, build a study guide, generate a summary with ChatGPT or Claude via the YouTube Summary tool, or export it as a timed subtitle file with YouTube to SRT. You can also re-open it in the transcriber to translate the transcript into 100+ languages.

Free YouTube transcript tool

YouTube2Text is a free YouTube transcript generator — no signup, no daily limit. Paste any YouTube link and get the full transcript instantly, with timestamps, click-to-jump, translation to 100+ languages, AI prompts for ChatGPT, Claude, and Gemini, and exports to TXT, SRT, VTT, or Markdown.