text-to-image-prompt-optimizer by manzxiao/text-to-image-prompt-optimizer
npx skills add https://github.com/manzxiao/text-to-image-prompt-optimizer --skill text-to-image-prompt-optimizer为 AI 图像生成工具生成专业、优化的提示词,主要支持 Google Gemini (Nano Banana),同时兼容 Midjourney、Stable Diffusion、DALL-E、Leonardo.ai 等平台。
当用户请求生成或优化提示词时:
[主题] + [环境] + [风格] + [灯光] + [构图] + [质量] 来构建--ar、--s、--q 等参数广告位招租
在这里展示您的产品或服务
触达数万 AI 开发者,精准高效
按以下结构组织回复(优先使用 Gemini 格式):
## 🎨 生成的提示词
### ⭐ 变体 1: Google Gemini (Nano Banana) - 推荐
**英文(对话式):**
[使用摄影/电影术语的清晰、描述性句子组成的自然语言提示]
**中文版本:**
[对话式风格的中文翻译]
**适用平台:** Google Gemini (Nano Banana / Nano Banana Pro)
**推荐模型:** [测试用 Nano Banana / 专业输出用 Nano Banana Pro]
---
### 变体 2: [替代风格/平台]
**英文:**
[平台特定格式 - Midjourney 的关键词,SD 的结构化格式等]
**中文版本:**
[中文翻译]
**适用平台:** [Midjourney / Stable Diffusion / DALL-E / Leonardo.ai]
---
### 变体 3: [另一个替代方案]
[如有帮助,可选的第三个变体]
---
## 📝 提示词解析
- **主题:** [解释]
- **构图:** [元素如何排列 - 对 Gemini 很重要]
- **灯光:** [使用的摄影/电影术语]
- **风格:** [视觉美学描述]
- **技术:** [Gemini 使用的相机术语、角度等]
## ⚙️ 平台指南
**🌟 Gemini(主要):**
- 模型选择:[何时使用 Nano Banana 与 Pro]
- 编辑技巧:[如何进行对话式迭代]
- 特殊功能:[角色一致性、多图像生成等]
**其他平台(次要):**
[如有需要,提供 Midjourney/SD 等平台的参数简要说明]
## 💡 优化技巧
[优先提供 Gemini 相关建议,然后是其他平台]
## 🎯 后续步骤
**对于 Gemini:**
1. [如何在 Gemini 应用/AI Studio 中使用]
2. [如何通过对话式编辑进行迭代]
3. [如何利用角色一致性 / 多图像生成功能]
**对于其他平台:**
[如果用户请求,提供平台特定的使用说明]
如需全面的提示词模板和关键词库,请参考:
在以下情况下加载这些参考资料:
First prompt: "Generate a character: [detailed description]"
Follow-up: "Show the same character [in new scenario/pose/style]"
# Gemini will maintain character likeness across images
Initial: "Create [image description]"
Edits:
- "Make the background darker"
- "Add [element] to the scene"
- "Change [attribute] to [new value]"
# Each edit builds on the previous image
Use technical terms:
- "85mm portrait lens at f/1.8" (lens + aperture)
- "wide-angle shot from low angle" (lens + perspective)
- "shallow depth of field with bokeh" (focus effect)
- "golden hour lighting from left" (lighting direction)
Instead of: "no cars, no people"
Use: "an empty, peaceful street with no signs of activity"
Instead of: "not blurry"
Use: "sharp focus, crystal clear, professional quality"
(red flower)::2 (blue flower)::1
# Red flower weighted 2x more than blue
Negative prompt: ugly, blurry, low quality, distorted,
bad anatomy, watermark, text
in the style of [Artist A] combined with [Artist B]
a fusion of [concept 1] and [concept 2]
Create/Generate [subject description] [action/state].
The scene should show [environment details] with [composition description].
Use [lighting description] to create [mood/atmosphere].
The style should be [visual style] with [quality description].
Generate a professional portrait of [age/gender], [appearance details],
wearing [clothing]. The subject should have [expression/mood].
Use [lens/angle] perspective with [lighting description].
The background should be [background details]. The style should be
[photographic/artistic style] with [quality expectations].
Create a [location/scene type] during [time/season]. The scene should
feature [key elements] with [weather/atmosphere]. Use [angle/perspective]
to capture [compositional focus]. The lighting should be [lighting type]
creating [mood]. Style: [photographic/artistic approach].
Generate a product photograph of [product] made of [material].
Position it on/against [background/surface] with [arrangement details].
Use [lighting setup] from [direction] creating [shadow/highlight effect].
Shot with [camera/lens details] at [angle]. The aesthetic should be
[style] suitable for [purpose].
Create a character: [description of person/creature] with [physical features].
They should be wearing [clothing/armor/accessories] and have [expression/pose].
The setting is [environment]. Use [art style] with [detail level].
[subject], [environment], [style], [lighting], [composition], [quality]
[age/gender], [appearance], [clothing], [expression], [background],
[style], portrait photography, [quality]
[location], [time/season], [weather], [color mood],
landscape photography, [angle], [quality]
[product], [material], [background], product photography,
[lighting], [angle], commercial, [quality]
[subject], [details], [genre] art, [atmosphere],
concept art, highly detailed, trending on ArtStation, [quality]
质量:
灯光:
构图:
风格:
氛围:
用合理的假设扩展想法,提供 2-3 个变体,解释选择。
分析现有提示词,找出弱点,提供改进版本并附上解释。
使用风格特定的关键词和艺术家参考,提供示例。
添加质量关键词,优化构图,增强具体性。
生成 3-4 个具有不同风格、氛围或构图的变体。
每周安装量
113
仓库
首次出现
2026年2月11日
安全审计
安装于
codex111
opencode111
gemini-cli110
amp110
kimi-cli110
github-copilot110
AI 代码实施计划编写技能 | 自动化开发任务分解与 TDD 流程规划工具
49,000 周安装
Kibana Vega 技能:使用 ES|QL 与 Vega 语法创建高度定制化 Kibana 仪表板和数据可视化
223 周安装
TanStack Query (React Query) 教程:React 异步状态管理与数据获取库
227 周安装
React/React Native 组件脚手架生成器 - 自动化创建生产级组件
228 周安装
WCAG无障碍审计与测试工具 - 自动化扫描与手动验证,确保网站可访问性合规
228 周安装
安全套件 (security-suite) - 二进制与仓库安全测试、行为契约分析与CI门控工具
237 周安装
AI子代理创建指南:构建高效、可并行执行的专用助手 | 代理开发教程
226 周安装