跳到正文
Artificial Analysis· @ArtificialAnlys · X·· 3 小时前AI 评分42

LLM 与视频模型比拼生成视频,GPT-6.2 Astra 对阵 Seedance 2.5

AI 导读

Artificial Analysis 用 GPT-6.2 Astra 与 Dreamina Seedance 2.5 做同题对比:前者以 three.js 代码构建悉尼歌剧院、机械表爆炸图和巨龙袭击中世纪城镇三个场景,后者用相同相机路径的文本提示加路线参考图生成。

正文 · 原文

Can language models make better videos than video models?

LLMs now make motion graphics, edit video as code and drive Blender to build 3D scenes. Can LLMs compete with video generation models?

We put GPT-6.2 Astra from @OpenAI, the current #1 on AA-3D, to the test, building the Sydney Opera House, an exploded mechanical watch, and a dragon attacking a medieval town as three.js code. We flew a scripted camera through each scene in a browser: 15 s, 1080p, 24 fps.

Dreamina Seedance 2.5 from @ByteDanceSeed_ got the same camera path as a text prompt with reference images of the route, at the same settings.

  • Top: GPT-6.2 Astra (LLM, AA-3D)
  • Bottom: Dreamina Seedance 2.5 (video model, AA-Video-T2V)

来源:Artificial Analysis · x.com