GPT Image 2 Prompts

9:16 的图片比例，生成一张抖音直播的截图，里面是 刘亦菲 在直播，刘亦菲 手里拿着牌子，牌子里写着 今晚直播，欢迎来参亦菲畅聊！

👍프롬프트 : 태조 이성계의 X 페이지(위화도 회군을 벌이기 직전- 최영 장군과 서로 디스하는 내용이 담긴 게시글들)을 만들어 주세요. gpt-image-2

I'm honestly blown away. GPT IMAGE 2 doesn't "prompt" scenes, it directs them. Mark actions and camera moves right on a reference frame → 10x more context and near-total control in one shot #gptimage2 #seedance2

GPT-Image-2 is rolling out 👀 @OpenAI just leveled up image generation: • handwritten notes • realistic ads • posters • anime art All in seconds. Same prompt, wildly different styles.

Duct-tape-2 just solved the prompt ONE SHOT None of the current sota able to solve in 3 attempts Nanobanana Pro 🍌, Nano banana 2🍌 & Gpt-image-1.5 Prompt : A wooden bookshelf consisting of three shelves: On the top shelf, there should be one book, on the second shelf, there should be three books, and on the bottom shelf, there should be seven books.

generate an image of donald trump shaking hands with a confused joe biden as they stand in the oval office

GPT Image v2 almost beat Nano Banana 2 in every categories! UI replication, casual photos, you name it! Link in the comment👇

Tested GPT-Image 2 on Arena today. First impression: the jump in aesthetics is very noticeable. Portraits feel more cinematic, product shots look cleaner, and creative poster-style prompts are much stronger than before.

，gpt-image-2的效果真的太出彩了。 看到这张图的第一眼只觉得震撼， 眼睛的纹理，特效，文字样式竟然能精细准确到如此程度， 这完全就是奔着商业化方向去的。 提示词见原贴。

，你们觉得哪个更好？ 哪一个是香蕉的，哪一个是gpt 的？ 评论区揭晓答案

で ☝️GPT-Image-2 👇Nano Banana 2 スタイルもかなり違うけど、細かいレイアウティングになるほど GPT-Image-2 のほうがキレイに生成してくれる... そしてプロンプト追従性が圧倒的に高い

にする 4.そのプロンプトで Arena AI と ChatGPT を回す 5.日本語精度とビジュアルがどちらも強いものが出たら当たり コツは、1発で決めにいかないことです。 同じ題材を少しずつずらして回すと、急に当たりが出ます。 #AIart #GPT