【Hacker News搬运】元电影生成
-
Title: Meta Movie Gen
元电影生成
Text:
Url: https://ai.meta.com/research/movie-gen/?_fb_noscript=1
很抱歉,我无法直接访问互联网或外部链接,包括您提供的链接。因此,我无法使用JinaReader或其他工具来抓取和分析了您提供的网页内容。 不过,我可以提供一些关于如何使用JinaReader进行内容抓取和分析的指导步骤,如果您想要自行操作: 1. **安装JinaReader**:首先,您需要安装JinaReader。JinaReader通常是一个Python库,您可以通过pip来安装它。 ```bash pip install jina
-
配置JinaReader:配置您的JinaReader实例,这可能包括指定索引器、处理器和路由器。
from jina import Jina # 创建一个Jina客户端实例 client = Jina() # 加载或定义您的处理器和索引器 # ... # 启动Jina客户端 client.load()
-
抓取内容:使用JinaReader抓取网页内容。这通常涉及到使用一个HTTP客户端来请求网页,并将其传递给JinaReader。
from requests import get # 使用requests获取网页内容 url = 'https://ai.meta.com/research/movie-gen/?_fb_noscript=1' response = get(url) # 将内容传递给JinaReader # ...
-
分析内容:在JinaReader中配置或添加一个分析处理器来处理抓取的内容。
# 假设我们有一个处理器来分析内容 from jina import Document # 创建一个Document对象 doc = Document() doc.text = response.text # 使用处理器分析文档 # ...
-
翻译非中文内容:如果抓取到的内容不是中文,您可能需要一个翻译API来将其翻译成中文。这通常需要您在JinaReader中添加一个翻译处理器。
# 假设我们有一个翻译处理器 # ... # 如果内容不是中文,进行翻译 if not is_chinese(doc.text): doc.text = translate_to_chinese(doc.text)
-
总结内容:最后,您可以使用一个摘要处理器来生成内容的总结。
# 假设我们有一个摘要处理器 # ... # 生成内容的总结 summary = summarize_content(doc.text) print(summary)
-
关闭JinaReader:完成处理后,不要忘记关闭JinaReader客户端。
client.destroy()
请注意,以上代码仅为示例,具体实现将取决于您的具体需求和JinaReader的实际API。您可能需要根据实际情况调整代码。
## Post by: brianjking ### Comments: **famahar**: I've kinda given up on the internet at this point. It's sad but comforting. My social networks are just my friends and I've started to get back into reading books and long form blogs. Don't want to be exposed to this endless slop. Every day it gets harder to find something that was so easy before. It's all being buried by endless content. I'm hoping some non AI generative content branch of the internet will be created. Don't know if something like that is possible. Curation seems like the next best step. > **famahar**: 我;我现在有点放弃上网了。它;这很可悲,但令人欣慰。我的社交网络只是我的朋友;我开始重新开始阅读书籍和长篇博客。不要;我不想暴露在这无尽的污秽中。每天都很难找到以前那么容易的东西。它;一切都被无尽的内容所淹没。我;我希望互联网上能创建一些非人工智能生成的内容分支。不要;我不知道这样的事情是否可能。策展似乎是下一个最好的步骤。 **gorgoiler**: Photo sharing websites (including Facebook) used to be wrappers around ImageMagick with extra features. I love how the backbone of their training involves calling out to ffmpeg. It gives a little hope to those of us who, too, are working on a smaller scale but with similar techniques.<p>Scale? I have access to an H100. Meta trained their cat video stuff on <i>six thousand</i> H100s.<p>They mention that these consume 700W each. Do they pay domestic rates for power? Is that really only $500 per hour of electricity? > **gorgoiler**: 照片共享网站(包括脸书)曾经是ImageMagick的包装,具有额外的功能。我喜欢他们训练的支柱是如何呼唤ffmpeg。这给我们这些也在小规模但使用类似技术的人带来了一点希望<p> 规模?我有权使用H100。Meta在6000台H100上训练了他们的猫视频<p> 他们提到,这些每台消耗700W。他们支付国内电费吗?每小时电费真的只有500美元吗? **reneberlin**: We humans are so excessively dependent on vision input and with entertaining through visuals, too. But more and more all those visuals become meaningless to me and it all just feels like fast-food-junk to me.<p>As any pre-schooler will be able to produce anything (watch out parents) imaginable in seconds doesn't make it better to me or is of any real value.<p>Ok, i needed to edit it again to add: maybe this IS the value of it. We can totally forget about phantasizing stories with visuals (movies) because nobody will care anymore. > **reneberlin**: 我们人类过于依赖视觉输入,也过于依赖视觉娱乐。但越来越多的视觉效果对我来说变得毫无意义,对我来说,这一切都像快餐垃圾。<p>任何学龄前儿童都能在几秒钟内制作出任何可以想象的东西(家长们要小心);这对我来说没有什么好处,也没有任何真正的价值<p> 好吧,我需要再次编辑它以添加:也许这就是它的价值。我们可以完全忘记用视觉效果(电影)来想象故事,因为没有人会再关心了。 **syntaxing**: I find the edit video with text the most fascinating aspect. I can see this being used for indie films that doesn’t have a CGI budget. Like the scene with the movie theater, you can film them on lounge chairs first and then edit it to seem like a movie theater. > **syntaxing**: 我发现带文本的编辑视频是最吸引人的方面。我可以看到这被用于没有CGI预算的独立电影。就像电影院的场景一样,你可以先在躺椅上拍摄它们,然后将其编辑成电影院的样子。 **woggy**: It's already bad, but the amount of garbage that is going to flood YouTube now is going to make it unusable. > **woggy**: 它;这已经很糟糕了,但现在涌入YouTube的垃圾量将使其无法使用。
-