"Sora"is a new model created by OpenAI, an American company. The cool model is surprising the world. It doesn't just make text and pictures for us anymore. It can turn your words into videos like magic! Just tell Sora your ideas and watch it make a video right before your eyes.
Whether on a large TV or a small smartphone, Sora's videos are always easy to watch and enjoy. Sora can also make scenes with lots of people doing different things with clear details(细节). It's also learning how things should look in real life.
Why is it so good? Sora is a good learner. It looks at many videos and learns from them by breaking them into very small parts. It uses these parts to make a new video. The new video is gray at first and you can't tell what's in it. Then, Sora overhauls the video until it looks fine. Sora also gets help from ChatGPT. It can turn the user's short sentences into clear instructions. This helps Sora make the video just as you asked.
OpenAI is still testing Sora, so it is far from perfect. Sora may find"busy"pictures hard to understand. For example, when a person moves, things around them change. Sora can' t make everything look real. In one video created by Sora, a grandma blows the candle on a birthday cake, but the flame(火焰) doesn't move. Besides, Sora may not be able to tell"left"from"right"and mess up a person's leg movements(移动).