Event ·Multi-source

GPT-6 Astra 110分钟完成视频制作

用户使用GPT-6 Astra medium模型，在110分钟内完成从Blender建模到剪映剪辑的全流程视频制作。该模型经历了6轮迭代，保留了18张过程图，并生成了1分钟运镜视频和30秒精华版。最终成片包含悟空偷桃场景、六角亭、云海等细节，以及6段趣味字幕。

Current read

GPT-6 Astra能独立完成建模、运镜、剪辑全流程，110分钟产出专业级短片，创意执行效率惊人。

11 sources73° AI heatLast updated 2026/9/5 17:33:06

Evidence

11 sources

Primary source宝玉

2026/9/5 17:33:06View source

Related source 1歸藏(guizang.ai)

2026/9/5 03:35:43View source

Related source 2@OpenAIDevs

2026/9/3 19:33:51View source

Related source 3Cognition

2026/9/3 19:40:14View source

Related source 4Latent Space (swyx)

2026/9/3 21:09:41View source

Related source 5theverge

2026/9/4 10:41:48View source

Related source 6AI SDK

2026/9/4 15:06:56View source

Related source 7lmarena.ai

2026/9/4 19:21:10View source

Related source 8GitHub

2026/9/4 20:24:55View source

Related source 9v0

2026/9/4 21:25:19View source

Related source 10OpenAI

2026/9/4 22:12:46View source

Conflict check

Dedup data only shows that these sources discuss the same event, not that they agree. There is no structured supporting or refuting evidence yet, so no conflict is inferred automatically.

Open the story