2 分鐘 → 30 秒 + 多輪

提示詞

I’ve been using GPT Image 2 for visual work for a long time, and 2.5 feels like a really big improvement. With the same prompt and image input, what used to take around two minutes now takes about 20–30 seconds.

I’ve tried splitting generated images into layers. For infographics, I separated the background, text, and other elements, erased and edited them individually, then put them back together. The regenerated content would often shift slightly. It looked fine on its own, but didn’t line up when I put the layers back together.

When I tried the same workflow with 2.5 this time, that drift was barely noticeable.

I later noticed OpenAI has a demo of this on its website, under “Multi-turn editing consistency.” Earlier edits stay more consistent through later rounds of editing. For my workflow, I think this makes all the difference.

Another change stood out. I like using it for images with lots of text, but the old model would often leave marks around the text that looked like water stains. I didn’t see any in the images I generated this time. Much cleaner.

I ran a few sets of infographic editing tests using the same prompt and image input, all at 2K with quality set to high. Average times:

GPT Image 2: 122.2 seconds
GPT Image 2.5 Flare: 25.28 seconds
GPT Image 2.5 Sunburst: 30.89 seconds

OpenAI says image generation latency is up to 50% lower than Images 2, but the drop in generation time was even larger in my tests.

There are two versions this time: Flare and Sunburst. Flare is aimed at fast, everyday, high-volume generation. Sunburst is for more demanding generation and precise editing, and OpenAI says it takes longer.

Generating a good-looking image is one thing. Being able to keep editing it and put the pieces back together is another. I think this makes image editing much more practical.

中文翻譯

我長期用 GPT Image 2 做視覺工作，2.5 感覺是一次非常大的提升。在相同的 prompt 和圖像輸入下，過去大約要兩分鐘，現在只需約 20–30 秒。

我試過把生成的圖像拆成圖層。做信息圖時，我會把背景、文字和其他元素分開，逐一擦除和編輯，然後再拼回去。重新生成的內容常常會有輕微偏移。單獨看沒問題，但把圖層拼回去時卻對不上。

這次用 2.5 跑同樣的流程時，這種偏移幾乎察覺不到。

後來我發現 OpenAI 官網上有一個相關演示，名爲 “Multi-turn editing consistency（多輪編輯一致性）”。較早的編輯在後續多輪編輯中能保持更高的一致性。對我的工作流來說，我覺得這就是決定性的差別。

還有一處變化很明顯。我喜歡用它生成文字很多的圖像，但舊模型常常會在文字周圍留下看起來像水漬的痕跡。這次我生成的圖像裏一點都沒看到。乾淨多了。

我用相同的 prompt 和圖像輸入跑了幾組信息圖編輯測試，全部爲 2K 分辨率、quality 設爲 high。平均耗時：

GPT Image 2：122.2 秒
GPT Image 2.5 Flare：25.28 秒
GPT Image 2.5 Sunburst：30.89 秒

OpenAI 表示圖像生成延遲比 Images 2 最多降低 50%，但在我的測試中，生成時間的下降幅度還要更大。

這次有兩個版本：Flare 和 Sunburst。Flare 面向快速、日常、大批量的生成。Sunburst 面向要求更高的生成和精細編輯，OpenAI 說它耗時更長。

生成一張好看的圖是一回事。能持續編輯它、並把各部分重新拼回去是另一回事。我覺得這讓圖像編輯實用多了。

溯源

原作者

Voxyz_ai

發佈日期

2026-09-09

原始出處

查看原帖 ↗

收錄來源

xianyu110/awesome-gpt-image2.5 · 2097621370389581931 · MIT