How to download Threads videos from the browser and without using websites or applications

Let’s explain you in a simple way How to download Threads videosthe social microblogging network of X and Bluesky of Instagram. In this way, if there is any video that someone publishes and wants to keep, you will know a simple way to do so. We are going to tell you how you can download the Threads videos without using any website or applicationso that you do not expose your privacy. Because even though you open them and click on them the option does not appear, there is a method that you can follow to get it easily. How to lower Threads videos The first thing you have to do is press the video you want to download. When you do, right click, and in the menu that appears click on the option of Inspect That will appear below. Depending on the browser you use, this option can be a bit different, but in general it will be inspection of this element. This will open a window with many data on the side of the browser. In this window, click on your tab Grid. What this tab does is show you the contents that are loaded from the page where you are. Then, click on the video to stop it or reproduce it again, or to advance its content. With that, a row with a code will be shown on the list, where In the column Guy You will see what it puts Average. When there is a marked element on this list as averageIt means that it is a multimedia element. It is the name of the video file. Here, what you have to do is right click on the file, and Choose the option New In the menu that will appear. This will open the video in another tab. But it will open the video directly from the source and without going through the protections imposed by the Threads website. Now, right click on the video, and you can now click on the option to download or save it That will appear. In Xataka Basics | Threads guide: 28 functions and tricks to be able to squeeze the social network to the maximum

How to block so that your messages from your WhatsApp chats can not be shared or photos or videos can be downloaded

Let’s explain how to configure whatsapp for prevent others from sharing your messages In the chats you have with them. It is a new option that will gradually reach all users, and we will explain its operation. We are going to start explaining the operation of this adjustment, which has not yet reached everyone but will start doing it in the next few days. And then, we will explain how its operation is and activate. How this option works When you are talking to another person, any message you send can be shared. This means that the other people with whom you speak have the option of Share your message and send it to another chat or group to show what you have said. In addition to avoiding messages, this adjustment allows Other people cannot download your photos or videosyour content cannot be lowered to your phones. In addition, your messages cannot be used for AI functions. This allows you to give important information in an individual group or chat, it can be disseminated. You can share your text messages, your photos, videos, everything you send. However, It can also be a problem for your privacy In the event that others decide to share what you do not want to share. Now, WhatsApp has decided to give you the flexibility of activating an option that allows Do not allow any of your messages in a chat to be sharedand thus make sure that nothing you say is disseminated. This adjustment It is individual of each chat or group. This means that you will have to activate it one by one in all the chats where you do not want anything you say to spread. By default, everything you say can be shared, but in the chats and groups you want you can activate the option to do not. How to prevent your messages from sharing To prevent your messages from sharing in an individual group or chat, you have to click on the chat name To access the screen where some options appear on it. Once you are inside, you have to click on the option Advanced Chat Privacy That will appear inside. Here, you can activate the function so that your chats cannot be exported or shared. Remember that this you will have to activate in each chat individually and in each group where you do not want to download or share what you say. It is a good option for those conversations where there are people with whom you still have no confidence. In Xataka Basics | WhatsApp news in April 2025: What changes and what adds the application for Android and iOS

What is it, what is it for and what functions the new Meta Videos editor offers

Let’s explain WHAT IS AND HOW EDITS WORKSthe new Instagram application. Once again, it is the classic finish movement by launching its own version of a successful application, and in this case it is its alternative of the Capcut editor. We are going to start the article explaining what this application is, so that you understand where it comes from and what it is for. Then we are going to tell you What can you do with itreviewing its main options and their functions. What is Instagram edits Edits is A video editing application created by Meta for Instagram. It is an app adapted to your mobile that will allow you to make several types of compositions, aimed at creating Reels in a more professional way. Being clear, Edits is like Capcut for Tiktokbut an own version made for Instagram reels. We could say that it is a copy, just as Instagram copied the Tiktok reels or their Snapchat stories, bringing what was working on other social networks to his. Instagram has optimized edits so that The videos uploaded from this app have the highest quality. This means that there will be a difference between creating your videos using this tool and not doing so. Edits is aimed and oriented to content creatorssince it also integrates a statistics panel. The idea is to offer everything for creators to stop using tools such as Capcut Pro, and begin to make the goal of the goal. This application is completely free, and is available In Google Play For Android, and In the App Store of iOS. To use it you will not have to create an account, since You will enter directly with your Instagram profile. It is like an extension of the social network, but with an independent app. What can you do with edits The main edits function is to allow you to edit videos to upload them to Reels. To do this, on the main screen you have a + button that serves to create a new edition. Then you just have to load the photo or video you want from your gallery and ready, you can start. When editing the videos, above you have a visualization, and downstream. In them, You can add other elementsas audios of the sources you want or images through the chamber or the gallery. When selecting a temporal line, such as your video, and to have different options. You will be able to divide the videoadjust your volume or speed. You can also add filters, or make adjustments to image quality, such as brightness, contrast, warmth, saturation, etc. When you do not have anything selected in the temporal line, below you will have the options to Add the elements you want. You can add audio, text or voice. You can also create subtitles, add overlays or sound effects, and there are even cuts or add stickers. Then you have a button Exportwhich serves to finish the creation of the video and Prepare it to send it with the highest image quality May possible. When this process ends, Edits will save your creation in the photo gallery and videos of your mobile, and will show you options to share it directly on Instagram or Facebook. Edits also have an option to See the creations of other usersas if navigating the Instagram reels themselves. The difference is that all the creations you see have been created with the app, and you will have options such as saving it, adding it as an adhesive note or using the audio for your creation. There is a section of ideas Where you can add adhesive notes with things that happen to you. You can also create content collections and see them, or see the reels and elements that you have seen in the app and saved. Another of your options is to record videos directly from the app. Thus, you will have several recording options that will not depend on the native photos of photos you have on the mobile. And finally, you have A statistics sectionwhere you can see the scope and data of all the reels of your Instagram account, even those that you have not edited or uploaded using this application. In Xataka Basics | How to prevent Instagram from using your data to train goal AI

The images of AI already flood the Internet. Google and see 2 will serve to start filling it with videos generated by AI

The Images that mimic the Ghibli style They are very good, but be careful, because we can soon make small animation shorts that imitate that or any other style. The models of the generative video are closer more than ever to the general public by Google, which now offers its spectacular model I see 2 as part of the subscription to Gemini Advanced. Hello, Gemini Advanced. When it appeared on the scene I see 2 could only be used through the VERTEX AI and Videofx platforms, but the scope of both proposals was limited and was intended for a more expert audience. Now this model reaches Gemini Advanced, which allows you to transform our text prompts into dynamic videos. Interestingly, the option that now comes to Gemini Advanced It is available for weeks on the Spanish Freepik platformwhich was the first to offer that generation of ia videos using this same model. Eight seconds of artificial creativity. The model, created by DEEPMIND, is available as one more of the options of the GEMINI models drop -down menu. If we use it, we can generate an eight -second video clip with 720p resolution, MP4 format and 16: 9 appearance ratio. In Google they point out that there is a monthly limit for the number of videos that each Gemini Advanced user can create, but do not indicate which, only that we will receive a warning when we approach that limit. A text prompt is enough. To create videos with Gemini we will only have to describe the scene – as always, the details will help create it with greater loyalty – and Gemini will be responsible for materializing that idea and turning it into a video generated by AI. To conquer the Internet. In Google they also wanted to convert these videos into content that can be shared easy and quickly. Thus, it is enough to choose any of the videos that we have generated and then select the option “Share” and be able to upload it to platforms such as Tiktok or YouTube Shorts. Flood of videos from AI in view. We could already live how the phenomenon of the Image ghiblation He won the Internet, and AI models have shown that this type of uses are those that attract the general public at least temporarily. The images generated by AI are already everywhere and are flooding the Internet, but now we face that with the video generated by AI. That Google bets on this type of content and invites you to share it without tapujos is a declaration of forceful intent. The video generated by AI remains for those who pay. The AI ​​models to generate images have long offered their options to users even in free services —Chatgpt and Gemini do it – although with limitations. With the video at the moment that does not happen, and so much Sora as Runway Or now I see 2 are oriented to users who pay for this intensive use of resources to generate these videos. Already available, Spain included. The new option for generating videos in Gemini through View 2 begins to gradually deploy from today for Gemini Advanced subscribers worldwide, including Spain. We can write our Prompts in Spanish as well, which makes Gemini more and more versatile to be able to generate both text and images and video (for Gemini Advanced subscribers, we insist). Water brand in each frame. To avoid bad uses of this tool, Gemini can refuse to create some videos that are contrary to Google’s use policies. In addition, all the videos generated with I see 2 include a digital water mark embedded in each frame Thanks to Synthid technology. Whisk, the other option. I see 2 too will be available through whiskan experimental platform of AI that is not available in Spain. With it the advantage is that not only prompts of text are accepted, but also starting images that then serve as base frames for the rest of the animation. Thus, choosing a Studio Ghibli style frame makes us obtain an eight -second miniClip that also mimics that style, as Google shows in its promotional videos. The Whisk Animate function based on VI 2 is available from today for the subscribers of the Google One Premium Plan in various countries of the world, although for the moment not in Spain. Image | Google In Xataka | The Spanish Startup Freepik is already one of the most important ‘success’ in the history of Spain after being bought by the EQT fund

That will improve the experience of watching videos in goal

Hispanic countries have a wide dubbing culture for the contents in other languages, so that we consume films, series and programs bent with Voices in the local language. As one of the main content creators From YouTube, Mrbeast knows. That is why he said that if he were CEO of Facebook, the first thing he would implement would be a dubbing system of his videos as Youtube already has. Mark Zuckerberg agreed. Speak the same language as the audience. Mrbeast and Mark Zuckerberg agreed In the podcast Colin and Samir Show Where the interviewers asked Jimmy Donaldson (real name of the YouTuber), what would he do if Mark Zuckerberg appointed him CEO of Meta. Donaldson made Mark Zuckerberg see that the finishing video platforms are staying behind in terms of the ability to offer content in several languages. According to Mrbeast, this lack of dubbing options is negatively affecting the scope of videos on the platform. In another language you don’t get the same. As the Youtuber explained, the audience’s commitment is not the same when they see a video in their language as in English, therefore, the Content creator with more subscribers From YouTube he was especially concerned with the target tools in translation. “Something that seems really bad (finish) is that on YouTube you can have different audio clues. 70% of my audience on YouTube does not speak English, so I upload videos and then you simply upload a lot of different files. If you click on my video in Mexico, it automatically reproduces in Spanish. What is brutal is that when I publish those same videos on Facebook or in any of your platforms, I can not care about the dubbing. Audience is always infinitely lower because people from Mexico, Brazil and others cannot see them with dubbing, “Donaldson explained in his speech. Audience of India Brazil, Indonesia and Mexico. No traffic data of Mrbeast has been revealed, but According to data From the GMI consultant, some 2.7 billion people around the world use YouTube every month, of which 476 million users are from India, 147 million Brazil, 139 million Indonesia and 84.2 million users see content from Mexico. His videos are reproduced in more than 100 countries with 80 different languages, so for Mrbeast, speaking the same language as his audience is the key to the success of his videos. There click Facebook. Mrbeast was very clear: “If he were the Meta CEO, one of the first things he would be would be to improve the dubbing options.” For him, it is essential that goal helps creators reach more people and to increase the engagement With its content. One of those tools is the language. “It is quite overwhelming once you understand it. You think: ‘uf!, Only 15 or 20% of the world, or the figure that is, consume content in English.’ It is brutal. It is almost barbaric to use a platform in which you have to choose a language,” said Donaldson. The interesting thing is that Mark Zuckerberg agreed with Mrbeast. He acknowledged that the lack of dubbing options is a problem and that artificial intelligence could be the solution. Mrbeast has already proven that the Use of dubbing generated by AI With his own voice, hearing retention on other platforms has increased. The multilingual future with the finish line. Zuckerberg agreed that the youtuber in the importance of languages ​​when reaching the audiences, and added that there could have the AI ​​could have A very important role. “Actually, retention is 1% greater in that language because when you do dubbing with AI you can use my voice instead of sounding like a dubbing actor,” Donaldson explained, indicating that her producer already uses cloned voice tools with voice with AI to fold your videosinstead of applying a neutral dubbing voice or simply applying subtitles. For the goal, which seeks to have a global presence returning to the origin Without Facebook algorithmthis option is even more important. By incorporating dubbing generated by AI, the goal could increase audience retention, expand its user base and compete more effectively in the panorama of social networks. In Xataka | One in three employees uses AI at work: your position is not in danger because most use it as a translator In Xataka | If the question is “how much money you can earn sleeping on Twitch”, the answer is Muroonh: $ 17,000 Image | Goal

Mrbeast has discovered a much more lucrative business than making videos on YouTube: Sell chocolate

Mrbeast became a Internet superstar globally Thanks to his video and challenges on YouTube. However, far from beating content creation, the youtuber has managed to transform its fame into A business empire diversified valued in billions of dollars. Ironically, the main engine of this empire is no longer the more than 377 million Mrbeast followers and its most crazy challenges: selling chocolate has been much more profitable. The teenager who became a millionaire playing. Jimmy Donaldson, the name behind Mrbeast, began his adventure on YouTube in 2012 with only 11 years. Like most kids of his age, his first videos showed him playing fashion video games: Call of Duty and Minecraft. For years, he analyzed what type of content he worked better on the platform, learning the secrets of the algorithm and how to capture the audience’s attention. YouTube was small. He cannot be denied that he knew how to find the correct key and turned what began as a hobby, into a lucrative business that It led him to leave the university to devote yourself completely to your career on YouTube. In recent years, their videos have almost become blockbusters with hundreds of millions of visualizations worldwide, with challenges as popular as the recreation of “The squid game “in real lifetheir experiences of survival in extreme situations or Your own program In Amazon Prime Video. Diversify the business. However, despite the fact that the YouTube channel continues to be a pillar in the Holding of Beast Industries companies that Donaldson has created, it is not, from afar, the most profitable. The conglomerate of MRBASET companies has Lunchly under its umbrella, a brand of snacks, ViewStats, a software company for content creators. However, the real Crown jewel It is feastable, its chocolate bars brand. Feastable: nobody bites a sweet. Mrbeast’s incursion into the chocolate world began in 2021 with the launch of feastable. The brand became popular immediately because youtuber and their adventure companions usually consume them in their videos, and have even turned their chocolates into the protagonist of some of them. To promote their chocolates, Mrbeast challenged his followers to find a golden ticket on their chocolate bars, and invited the winners to compete for a boat of $ 500,000 in cash in one of their videos, to the purest Willy Wonka style. This strategy, combined with the quality of Your chocolate barscatapulted feastable to sales success. The chocolate empire surpasses the media empire. According to published Bloombergdocuments sent to possible investors, feastable registered sales valued at 250 million dollars last year, with benefits that exceeded 20 million. In contrast, the media business of MRBAST, which includes its YouTube channel and its reality show for Prime Video, generated a similar sales volume, but recorded losses close to 80 million dollars. “I lost dozens of millions of dollars in Beast Games,” Donaldson confessed a few days ago In the podcast The Diary of A CEO. The food business ate YouTube. These figures published in Bloomberg’s article reveal that The chocolate business Mrbeast is currently more profitable than what the YouTuber generates with its videos. In fact, Beast Industries forecasts suggest that feastable will triple its size in the next two years. According to that data, last year, the United Arab Emirates investor Alpha Wave directed An investment round For Beast Industries, and valued Donaldson’s holding company in about 5,000 million dollarscompared to its last 2023 valuation that was 1.5 billion dollars. By 2026, the company of MR.BaAST estimates that the income from the business creation business will represent only a fifth of its total income. In Xataka | If the question is “how much money you can earn sleeping on Twitch”, the answer is Muroonh: $ 17,000 Image | Feastable

The videos of AI have broken the Instagram and Tiktok algorithms. Welcome to the new “AI landscape”

A little over a month ago This unpleasant video De Instagram went viral in that social network. In him a strange creature half -spider of a man made a strange appearance in a mall. At this time the video has 3.5 million “like” and more than 23,000, but the truly worrying is not that. Collapse of the videos generated by AI. What is worrisome is that this video is part of an avalanche of videos generated by AI that is collapsing networks such as Instagram or Tiktok. And broken algorithms. As they explain in 404 averagethe algorithm of these platforms has ended up breaking through a unique brute force attack. One in which these networks do not stop receiving content generated by AI to end up saturating those recommendation algorithms. A LEA. Brute force attacks try, for example, to find out a password testing one by one all possible combinations. In this case, what they try is to saturate the algorithms so that they end up showing these videos generated by AI, and they are achieving it. Some already call Instagram Ya Tiktok “Villagers of AI” for the enormous amount of these contents, and that have made the conventional contents generated by human users have lost great relevance to the algorithm. Reality has changed. For many these networks they serve not only to entertain themselves, but to be aware of the present. Videos often try to profile reality, but that reality has now been disrupted and those Instagram or Tiktok accounts barely show anything that is real. Some videos are deep -to -detecting unappokes, and as we verify in the past, the paradoxical is that sometimes we are not even able to detect what is real and what is not. AI seeks virality and ends up finding it. The creators in social networks seek to get their videos viral, and for this they dedicate huge resources and time. In spite of this, success is not assured, but spammers that make video content generated with AI do not need to think so much: they can generate thousands of videos with very little effort, flood social networks and wait for some of those contents to be successful. The lottery of the virality is not so much if you have a lot of tickets. The influencers who are earning money with the landfills of AI. As usual in this type of phenomena, influencers have appeared with new formulas to get rich quickly and with hardly any effort. One of them, a 17 -year -old named Daniel Bittonpresumes having already won two million dollars and has a clear message. “While others invest 5 or 6 hours making a perfect video, we can generate 8 or 10 shorts in less than 30 minutes.” As? Using AI tools. The “Hot Dog” method. One of Bitton’s friends is a known spammer of Tiktok called Musa Mustafa. His method to go viral is that of the “sad hot dog”: “When you are hungry at two in the morning, even a sad hot dog knows better than any Michelin restaurant meal. Tiktok works in a similar way. Your audience does not expect (you don’t even want) perfectly polished videos.” Mustafa wonders, not without some reason, “when it was the last time you saw a viral video of Tiktok and thought: ‘Uauh, the degree of color in this video is incredible.” Or what is the same: the amount wins by a win to quality. But platforms embrace these contents. In The Guardian They already warned us Recently: social networks and networks are not stopping this type of spam, but are benefiting from it, they accept it and are even promoting it. In fact they offer tools to facilitate the generation of content through AI, which means that rather than trying to solve the problem, they are aggravating it. An example: Facebook. Meta’s firm recently launched a tool for advertisers called Advantage+. With it it is possible to create with different versions of an advertisement to try them all with the method of A/b test and then select the one that works best. For advertisers (and for the finish line, of course), all this is fantastic, because they can get more effective ads with much less investment of time and money. Are there limits? There will undoubtedly users who They reject This type of content: precisely networks such as Bluesky either Mastodon They move away from the algorithm and are more similar to how they were Twitter or Facebook years ago. But it seems clear that a vast majority of them have no problem with these contents generated by AI, which in fact have an example of success in that porn generated by the impossible combinations –A fish generated by the kissing to a woman generated by AI, an orco generated by AI marrying a girlfriend also generated by AI – they are also becoming viral. More wood for dead Internet theory. It has been talking about how the growing presence of bots on the Internet It will end that the human presence in these contents will be marginal. What we already saw with texts or images generated by the flooding Internet now we are seeing it with videos of the flooding social networks or with Virtual avatars generated by AI. The AI ​​landfill extends, and the worst thing is that not even users – which we contribute to making these contents viral – or the companies – which as we said not only do not stop them, but also promote them – seem to have a greater problem with this situation. Image | Kenneth Schipper In Xataka | Meta follows the steps of X: we not only work writing for her, now we will also work moderating her

Alibaba has new Open Source to generate videos. The problem is that it is being used to generate pornographic deepfakes

Last week Alibaba launched Wanx 2.1a new AI model for video generation that competes with others such as Sorafrom OpenAi, or I see 2from Google. The tool ended up becoming 24 hours later the person responsible for dozens of pornographic videos They will be published on the Internet. Wanx 2.1 is also an Open Source model whose code It is available in github. Very soon users fond of pornographic content and who also possessed the appropriate technical knowledge took advantage of that fair model for that: to generate porn videos. They told it in 404 averagewhere they indicated how in communities dedicated to producing and sharing pornographic deepfakes without the consent of the people represented, the users were “salivating” because of the advanced Alibaba model. Some of those videos were shared in Civitai, A platform in which users share images and videos generated with AI tools, but in which such images are also bought and sold. The statistics that we can find in the pages of the AI ​​models used to create those images and video show how These models have already been downloaded hundreds of times by users. There are already dozens of pornographic videos created with WAN 2.1, indicate in 404 average. In Civitai, users are allowed to share AI models, but unseeled pornographic content is not allowed. That does not prevent users from discharging the models and use them to produce these models themselves, they affirm in this medium. The problem is once again the use of tools that, of course, allow perfectly appropriate and spectacular videos, but can also be used for uses such as these. We already saw how this type of Deepfakes They can become very profitableand the advance of these tools makes it difficult to control this type of content. In Xataka | In South Korea, Deepfake Porn has become a nightmare. Your solution: three years in jail for those who see it

Two videos show how 80 people from a plane have saved life in the last plane crash. There is triple explanation

After the tragic accident last month Between an American Airlines plane and an United States army helicopter that left 67 dead, on Monday there was a similar scene when it occurred A forced landing of Delta Air Lines’s flight 4819 In Toronto. Two videos showed rawly the scene that the 80 people who went on board and who ended the plane turned. And yet, it did not end in tragedy. How could they be saved? The “miracle.” Delta Air Lines’s flight 4819, operated by Endeavor Air, made a seemingly normal landing at the Pearson International Airport in Toronto until, Suddenly, everything went wrong. As soon as the wheels began to touch the wheel, the plane slipped, hit its right wing, turned on its axis and ended upside down, leaving an absolute chaos scene. But as we said, and despite the violence of the accident, The 80 passengers and crew managed to survivealthough 18 were injured, including an adult and a child in critical condition, although already out of danger. The impact and the fight to escape. They counted at the Washington Post in a report report that the passengers described the impact as “collide with a wall” before the plane turned. When they were face down, many remained suspended by their seat belts, seeing how the fuel slid through the windows and the fire consumed part of the aircraft. Pete Carlson, a paramedic on board, managed to unbutch and drop to the roof of the planenow turned into the ground, before helping others free from their seats. Meanwhile, passengers, in shock, collaborated with each other to get out as quickly as possible. A video recorded by Pete Koukovanother passenger, showed the crew organizing the evacuation with firm and urgent instructions, guiding people through emergency doors in an inverted plane, a rare scenario in aerial accidents. Outside, firefighters sprayed fushes with foam, while black smoke and flames hindered visibility in full snowstorm. How tragedy was avoided. In front of many Other aerial catastrophes More or less recent, experts have been detailing these days how the “miracle” was possible. Actually and as we will see, there is not a single factor, but several that helped that finally there was not a single death. Three were the main factors that we describe. Plane design and safety measures. He Bombardier CRJ900like all modern commercial planes, it is built with standards called “Crashworthiness”which means that its structure, safety belts and seats are designed to maximize survival in case of impact. In this regard, the cabin absorbed much of the strength of the crash without disintegrating, allowing passengers to go alive. According to Graham Braithwaiteexpert in aeronautics at the University of Cranfield, these elements were fundamental for passengers to resist the impact of the overturn without fatal injuries. Professor Michael J. McCormickfrom the Embry-Riddle University, stood out in the post That engineering and aeronautical regulations have advanced so much that accidents that in the past would have been lethal can now result in total survival. Assessment of the crew. Equally important that the design of the aircraft was crew trainingdecisive to organize a rapid and effective evacuation. Despite confusion and chaos, they managed to maintain order and get everyone out of the plane in a matter of minutes, even with the aircraft dump. Here it is important to remember that the regulations of the Federal Aviation Administration (FAA) require that Any plane with more than 44 passengers can be evacuated in less than 90 seconds. However, in this case, the evacuation was more complex because the plane was overturned, hindering the orientation and exit of the passengers. Immediate response of emergency equipment. The third of the key legs. Toronto airport authorities acted rapidlyensuring the area and preventing the fire from extending to fuel deposits. The first air control reports confirmed the severity of the situation: “The plane is face down and in flames”, which led to a rapid mobilization of rescue equipment. According to the norms of the International Civil Aviation Organization (ICAO), rescue teams They must respond in less than two minutes. In this case, firefighters and paramedics arrived at the place in a matter of minutes, stifled the fire and helped evacuate passengers. Causes of the accident. Although the exact cause of the accident has not yet been determined, it is known that landing occurred under wind conditions up to 70 km/hyve accumulated On the track after two recent storms. Thus, the airport firefighters ruled out problems with the track, which suggests that other factors, such as mechanical failure or human error, could have influenced. Be that as it may, in a context where Recent air accidents They have resulted in fatal tragediesthe total survival of flight passengers 4819 is a real testimony of the advance in aeronautical engineering, security protocols and emergency response. Although The images of the airplane burned and overturned They suggest an inevitable disaster, the combination of these factors allowed to avoid the worst. As Carlson underlined In his interview, after leaving the plane I only thought about one thing: “I didn’t care about the cold, I didn’t care how much I had to walk, all we wanted to be out of the plane.” Image | Yyzbrennan In Xataka | The main suspect of the plane crash in South Korea is common in aviation. The problem is that it does not usually end like this In Xataka | We have always thought that the rear seats of the plane are the deadliest in case of accident. We were wrong

What is it, how does this Chinese artificial intelligence of open source do for the creation of videos

Let’s explain What is Goku Aia new artificial intelligence model of video generation. When we were still recovering from the irruption of Deepseek In the sector, the Chinese technology company Bytedance has launched a totally revolutionary model fear. We are going to start this article telling you what exactly Goku AI is, and the two reasons why this model is so revolutionary. Then we will try to explain how it works inside, and we will end up telling you the possibilities offered This new model. What is Goku ai Goku ai is a new artificial intelligence model trained to be able to Generate video from the text. It becomes something like the AIs that generate images, you tell him what you want it to appear in the video, and this will generate one from scratch. This model is completely revolutionary for two things. The first is by The incredible quality of its results. The IA of videos creation has not yet reached the general public, and we have been seeing how realistic mediocre results pass. This AI is positioned among the most realistic in what can be generated with it. But the most disruptive is that it is again An open source model Available for everyone in GITHUB. As with others such as Deepseek, this means that anyone can access it and replicate it, and you can also use your code to settle for free on devices. Of course, there is currently no distilled models of Goku that can be used in normal computers, and the complete model needs very powerful GPUs and technical knowledge to settle. Even so, we should soon see the arrival of distilled models that you can use with Some of the free tools To install an AI on your computer. But come on, for you to get the idea, so far the most popular artificial intelligence models were closed and could only be used paying. Meanwhile, Goku arrives in this new wave of China with open source models that can be used for free. How Goku AI works This artificial intelligence model works as a video generation model based on flow and fed by a rectified flow transformer (RTF), which helps Improve your quality and efficacy. With this technology you can refine the images and each frame of the video progressively, making movements transitions soft and have a high visual fidelity. The video creation process begins when a user writes in text format what he wants to see, or even when he shares images. Then, the model understands what you are asking for with your natural language and converts these elements into structured representations. Then use a rectified flow dynamic to improve photograms interpolation, reduce noise, and try to guarantee good continuity. As a final step, Goku synthesizes coherent video sequences with fluid transitions. As for its technologies, the RFT allows you to maintain a good quality minimizing the computational load of the process. The process also uses A neural rendering with which to guarantee that the generated video has realistic movements and fluid transitions, and that there are no grotesque results. An architecture based on transformers is also used to model temporary units in video sequences. With all this, the resulting videos should be very realistic, and even static images can be encouraged. What can this AI do The main function that can be expected of this AI is the possibility of Generate videos from text. You write what you want the video to have, and generate an animated video with natural movements and realistic environments from nothing. It can also be used to convert images into animated clips. You can give you an image that will analyze and understand, and then you will describe what you want me to generate from it and make you an animation. This can be a real revolution in many areas, because the resulting people are realistic, the effects of clothing and textures are also, and objects move normally. Everything you can think of you can ask for it, and as it will be open source it is logical to think that it will have fewer restrictions. In Xataka Basics | Deepseek guide: 36 functions and things you can do for free with this artificial intelligence

Log In

Forgot password?

Forgot password?

Enter your account data and we will send you a link to reset your password.

Your password reset link appears to be invalid or expired.

Log in

Privacy Policy

Add to Collection

No Collections

Here you'll find all collections you've created before.