What's the best AI model to use with this prompt?

This prompt works well with most text-to-image models, including DALL·E 3, Midjourney, and Stable Diffusion. Models with strong instruction-following capabilities yield the most accurate layouts.

Can I change the recipe or the number of steps?

Yes! Modify the `recipe subject` and panel descriptions to any recipe. You can also adjust the grid dimensions by editing the `layout` parameters.

Will the text overlays be perfectly rendered?

AI may sometimes misspell or misplace text. For perfect results, consider adding text in post-processing, but the prompt ensures the visual placement is correct.

GPT Image 2AI 提示词

Butter Cookie Recipe — 9-Step AI Photo Grid

Generate a stunning 3x3 photo grid of each step in a butter cookie recipe, complete with text overlays for easy sharing.

提示词 · EN

type

分步照片教程网格

subject

{argument name="recipe subject" default="黄油曲奇"}

style

俯视美食摄影，明亮的自然光，简洁美观

background

{argument name="background surface" default="白色大理石台面"}

layout

grid

3x3

panel_count

panels

item 1

step

image_description

在透明玻璃碗中用手动打蛋器搅拌黄油和糖

text_overlay

1. 黄油室温软化，加糖打发至蓬松发白

item 2

step

image_description

在黄油混合物中加入生蛋黄，打蛋器放在碗中

text_overlay

2. 分次加入鸡蛋，每次搅拌均匀再加下一次

item 3

step

image_description

向混合物中加入深色香草精

text_overlay

3. 加入香草精，搅拌均匀

item 4

step

image_description

通过金属筛网将白面粉筛入玻璃碗中

text_overlay

4. 低筋面粉过筛后，加入盐，拌匀

item 5

step

image_description

用刮刀搅拌酥松的面团

text_overlay

5. 翻拌成无干粉的面团

item 6

step

image_description

用透明保鲜膜紧紧包裹的光滑面团球

text_overlay

6. 包上保鲜膜，冷藏 30 分钟

item 7

step

image_description

擀平的面团，用金属饼干模具压出星星和扇形圆圈形状

text_overlay

7. 擀成约 0.5cm 厚，用模具压出形状

item 8

step

image_description

生饼干坯整齐地排列在铺有烘焙纸的烤盘上

text_overlay

8. 放入烤盘，预热烤箱至 180°C

item 9

step

image_description

成品金黄色的饼干堆放在白色花边盘子上，角落里放着一些干薰衣草

text_overlay

{argument name="final step text" default="9. 烘烤 12-15 分钟，表面微金黄即可"}

关于这个提示词

Generate a stunning 3x3 photo grid of each step in a butter cookie recipe, complete with text overlays for easy sharing. 它更适合作为 GPT Image 2 的概念艺术起点：先保留画面结构、主体关系和风格约束，再替换成你的品牌、人物或场景。

这条提示词使用结构化 JSON 组织信息，包含 type、subject、style、background、layout 等字段。保留这种层级能让模型更清楚地区分画面主题、布局、界面元素和细节约束。

使用时建议先小幅修改主体、场景、镜头和色调，再生成多个版本对比构图与细节。这样页面内容对用户有实际帮助，也避免把模型名或标签机械堆在正文里。

如何使用这个提示词

Copy the prompt from this page.
Paste it into your preferred AI image generator (e.g., DALL·E 3, Midjourney).
Customize the variables (like recipe subject, background surface, or final step text) to fit your recipe.
Generate the image and refine prompts as needed for exact layouts.

Butter Cookie Recipe — 9-Step AI Photo Grid

关于这个提示词

如何使用这个提示词

常见问题

更多来自 GPT Image 2

AI-Generated Crossover Fighter Screenshot — Sora 2 Prompt

Sacred Dragon Dome Ceiling Mural — Sora 2 Prompt

Cubist Minimalist Fashion Portrait — Sora 2 Prompt

用 Sora2Hub 提示词更快创作。