匠人学院 JR Academy
Skip to article
Learning guide
Nano Banana Image Editing Guide

Learn image generation and editing workflows with Nano Banana for consistent visual output.

4 chapters·7 guides·Access varies by chapter
Prompt Framework
On this page

Nano Banana Prompt Framework

Treat a prompt as the start of a controlled editing conversation, not a fixed magic formula.

#Four elements

text
subject + setting/background + style + output requirements
text
An orange cat on a sunlit windowsill, warm afternoon light, realistic photography, landscape 16:9 composition.

Describe the subject, its environment, the visual treatment and the intended dimensions/orientation. A term such as “4K” in a prompt does not itself establish an actual export resolution.

#Be concrete

Replace “a person” with observable clothing, hairstyle, expression and pose. Replace “an office” with a specific room, window background and light direction. Choose compatible photography/illustration, mood and palette terms.

Useful light descriptions include soft side daylight, backlight outlining the subject, dramatic overhead light and colored neon. Change one important feature per editing round.

#Generation briefs

text
Generate [subject] in [setting]. Use [style], [palette] and [lighting/material]. Place the subject [position] and reserve [text area]. Compose for [ratio/orientation].

For a product, specify shape, material and color. For a person, specify appearance, posture and setting. For a poster/concept, specify the central element, background and information space.

text
A silver smartwatch with a round black face and gray silicone strap, floating on a dark-blue gradient, soft upper-right light, subtle reflections, minimal product photography, square composition.

#Editing briefs

text
Keep the subject unchanged; replace the background with [setting]. Keep the content; change only the visual style to [direction]. Keep everything else; change [element at position] to [replacement]. Add [element] at [position], with a matching shadow and light direction.

#Exclusions

State unwanted elements where useful, but confirm whether the interface has a separate negative-prompt control. In a conversational brief, describe a clean background and required anatomy/details explicitly rather than assuming exclusion words guarantee correctness.

#Iterate and record

Start with direction, refine unsatisfactory details, then finish. To compare variables, change only color, lighting or style at one time. Save successful product/portrait briefs with the result, not only the text.

#Questions

Longer is not necessarily better: conflicting instructions can be ignored or averaged. For a Chinese-language task, bilingual style keywords may help, but evaluate the actual result. If the image diverges, remove ambiguity, resolve contradictions, split the change into rounds and replace abstract preferences with observable requirements.

#Next steps

Published by
JR Academy
Learning resources

Individual authors and reviewers are credited where recorded.

Free Resources

Curated free tools, courses, and study materials

Find practical learning resources in one place.

Browse Free Resources →

Related Roadmaps

FAQ

Nano Banana 是什么?
Nano Banana 是 Google 基于 Gemini 模型推出的 AI 图像编辑工具,支持对话式编辑,用自然语言描述即可完成复杂的图像操作。
Nano Banana 和 Midjourney 有什么区别?
Nano Banana 更擅长对话式编辑和改图,Midjourney 更擅长从零生成。Nano Banana 对中文支持更好,且可在 Gemini App 中免费使用基础功能。
Nano Banana 有哪些模型可选?
三个层级:Nano Banana Fast(快速预览)、Nano Banana Pro(高质量输出)、Nano Banana Ultra(专业级 4K)。
如何提高风格一致性?
使用多图参考、建立风格关键词清单、每次都引用第一张图作为风格锚点,并减少单次描述的变化量。

Done reading? Next steps