TE
科技回声
首页24小时热榜最新最佳问答展示工作
GitHubTwitter
首页

科技回声

基于 Next.js 构建的科技新闻平台,提供全球科技新闻和讨论内容。

GitHubTwitter

首页

首页最新最佳问答展示工作

资源链接

HackerNews API原版 HackerNewsNext.js

© 2025 科技回声. 版权所有。

Make Pixels Dance: High-Dynamic Video Generation

96 点作者 trueduke超过 1 年前

7 条评论

bryanrasmussen超过 1 年前
So my company says &quot;This site is blocked due to a security threat that was discovered by the Cisco Umbrella security researchers.&quot;<p>Anyone have any idea why?
评论 #38370302 未加载
评论 #38376514 未加载
评论 #38368621 未加载
mdrzn超过 1 年前
ByteDance Research working hard to generate all future content on TikTok via AI
评论 #38367522 未加载
评论 #38362818 未加载
whelp_24超过 1 年前
They won&#x27;t give out the model due to &quot;Security Risks&quot;
mg794613超过 1 年前
On their example page you can sometimes see what data it got to train on. <a href="https:&#x2F;&#x2F;imgur.com&#x2F;a&#x2F;CuXNATp" rel="nofollow noreferrer">https:&#x2F;&#x2F;imgur.com&#x2F;a&#x2F;CuXNATp</a> for example is without a doubt &quot;Ragnaros&quot; from the game &quot;World of Warcraft&quot;.<p>Probably due to not having much different sources for &quot;A fiery humanoid monster with flames burning&quot;.
cubefox超过 1 年前
I guess Pixar will be safe for a while. While text-to-image models work pretty well, text-to-video is pretty hard to look at, judging from the example video.
评论 #38376433 未加载
judiisis超过 1 年前
The sample video with a lovely story for children looks good. This has the potential to bring down costs in content production
twilightzone超过 1 年前
Lovely story.