![]() ![]() A month later, Google showed off Imagen Video. We first covered text-to-video models in September 2022 with Meta's Make-A-Video. How (we think) they pulled it offĪI video synthesis has progressed by leaps and bounds over the past two years. There's no synchronized sound yet, but that might be solved in future models. In other words, this is the "worst" AI-generated video is ever going to look. Given far more powerful computers behind the scenes, AI video fidelity could improve considerably over time. ![]() OpenAI has found that, like other AI models that use the transformer architecture, Sora scales with available compute. Prompt: Reflections in the window of a train traveling through the Tokyo suburbs. Even when the kid jumped over the lava, there was at least a kid and a room. That gave people a baseline level of comfort that what they were seeing remotely was likely to be true, or at least representative of some kind of underlying truth. When video was faked (say, for Hollywood films), it took a lot of time, money, and effort to do so, and the results weren't perfect. "Every single one of these videos is AI-generated, and if this doesn't concern you at least a little bit, nothing will," tweeted YouTube tech journalist Marques Brownlee.įor future reference-since this type of panic will some day appear ridiculous-there's a generation of people who grew up believing that photorealistic video must be created by cameras. "This could be the 'holy shit' moment of AI," wrote Tom Warren of The Verge. Please tell your grandchildren about my videos and the lengths we went to to actually record them," wrote Wall Street Journal tech reporter Joanna Stern on X. Further Reading AI-generated video of Will Smith eating spaghetti astounds with terrible beauty ![]()
0 Comments
Leave a Reply. |
AuthorWrite something about yourself. No need to be fancy, just an overview. ArchivesCategories |