Sunburst object-swap：換物 match-cut，其餘幾乎釘死

提示詞

OpenAI launched GPT‑Image‑2.5 Sunburst a few days ago. We stress-tested it's object-swap capabilities using the the invideo editor to create this cool match-cut video.

Why? The biggest unlock with Sunburst is that when you edit images - NOTHING except the item you're swapping changes in your frame. Most models before this would do a good job editing images, but the rest of the frame changed ever so slightly. With 2.5 Sunburst, that doesn't happen anymore.

Combine that with an agent building your timeline and lining up your edited images for that perfect match cut feel - without you having to manually line-up, cut, and re-insert edited images on the timeline at the exact right spot, is where the biggest unlock is.

We created this in a few hours, with our in-house creator directing the idea and an invideo editing agent building and polishing the timeline.

中文翻譯

OpenAI 幾天前發佈了 GPT‑Image‑2.5 Sunburst。我們用 invideo 編輯器對它所謂的物體替換能力做了壓力測試，製作出這段很酷的 match-cut 視頻。

爲什麼？Sunburst 最大的突破在於：當你編輯圖像時——除了你正在替換的那件物品之外，畫面中其他任何東西都不會改變。在此之前的大多數模型編輯圖像的效果都不錯，但畫面其餘部分總會有極其細微的變化。有了 2.5 Sunburst，這種情況不再發生。

再結合一個爲你搭建時間線、並排布好已編輯圖像以營造完美 match cut 感覺的 agent——無需你手動在時間線上精確對齊、剪切並重新插入已編輯圖像，這纔是最大的突破所在。

我們用幾個小時就做出了這個，由我們的內部創作者主導創意，一個 invideo 剪輯 agent 負責搭建並打磨時間線。

溯源

原作者

invideoOfficial

發佈日期

2026-09-11

原始出處

查看原帖 ↗

收錄來源

xianyu110/awesome-gpt-image2.5 · 2098430230079984063 · MIT