Yummy Gen Image

生成 Image

创建 or edit images with yummy命令行工具 gemini nanobanana.

When to Use

Load this 技能 when the user asks to 生成, 创建, or edit an image using AI — including text-to-image generation, style transfer, image editing with a reference photo, or multi-image compositing.

Prerequisite: 应用ly the yummy-分享d 技能 first.

This 技能 uses one command for all Gemini image flows:

Prompt-only generation Single-image editing Multi-image reference editing Command Contract

Two equivalent entry points are avAIlable:

Entry point When to use yummy命令行工具 gemini nanobanana Default — human-friendly, Gemini pre设置s 应用lied yummy命令行工具 image 生成 --提供者 gemini Scripting / 自动化 — explicit, 提供者-agnostic form

机器人h 分享 the same flags and the same Gemini defaults. Prefer gemini nanobanana unless the task explicitly requires the 提供者-agnostic form.

Basic usage:

yummy命令行工具 gemini nanobanana --prompt ""

添加 one or more reference images when needed:

yummy命令行工具 gemini nanobanana \ --prompt "" \ --输入-image ./source-a.png \ --输入-image ./source-b.png

Optional 输出 controls:

--输出 --模型 <模型> --aspect-ratio --image-size

Default values when omitted: --aspect-ratio 16:9, --image-size 1K, --模型 gemini-3.1-flash-image-preview.

Execution Rules Use prompt-only generation when no reference images are provided. Use one --输入-image flag per local image file. Preserve the user-provided order of reference images. Prefer the default 模型 unless the user asks for a specific 模型. 模型 Selection

Use the following 模型 m应用ing rules:

If the user explicitly says gemini pro, pro 模型, or simply pro in the 模型-selection 上下文, use: --模型 gemini-3-pro-image-preview

If the user explicitly says gemini flash, flash 模型, or simply flash in the 模型-selection 上下文, use: --模型 gemini-3.1-flash-image-preview

If the user does not explicitly 请求 a 模型, omit --模型 and let yummy命令行工具 use its default 模型.

Do not switch 模型s implicitly from vague 质量 words alone. Only 应用ly the pro or flash m应用ing when the user's wording clearly refers to 模型 choice.

模型 Compatibility Aspect ratio 模型 Supported values gemini-3.1-flash-image-preview 1:1 1:4 1:8 2:3 3:2 3:4 4:1 4:3 4:5 5:4 8:1 9:16 16:9 21:9 gemini-3-pro-image-preview 1:1 2:3 3:2 3:4 4:3 4:5 5:4 9:16 16:9 21:9 (default / other) 1:1 3:4 4:3 9:16 16:9

1:4, 1:8, 4:1, 8:1 are flash-only. Do not use them with the pro 模型.

Image size 模型 Supported values gemini-3.1-flash-image-preview 512 0.5K 1K 2K 4K gemini-3-pro-image-preview 1K 2K 4K (default / other) 1K 2K 4K

512 and 0.5K are flash-only. Do not use them with the pro 模型.

Intent to Parameters

Translate clear user intent into 命令行工具 flags when the m应用ing is obvious.

Aspect-ratio 图形界面dance:

Use --aspect-ratio 9:16 for 请求s such as phone wallpaper, vertical poster, story 格式化, or other clearly vertical 移动 输出s. Use --aspect-ratio 16:9 for 请求s such as 桌面 wallpaper, presentation cover, horizontal banner, or other clearly widescreen 输出s. Use --aspect-ratio 1:1 for square social images, avatars, or other explicitly square 输出s. If the user already provides a specific ratio, pass it through directly. If the 输出 shape is unclear, omit --aspect-ratio and let yummy命令行工具 use its default.

Image-size 图形界面dance:

Use --image-size 4K when the user explicitly asks for 4K or a clearly print-grade / high-resolution deliverable. Use --image-size 2K when the user explicitly asks for 2K or a medium-resolution deliverable. Use --image-size 1K when the user explicitly asks for 1K or a lightweight preview-sized 结果. Use --image-size 512 or --image-size 0.5K only when the user explicitly asks for a minimal-size 输出 and the flash 模型 is in use. If the user does not explicitly 请求 输出 size, omit --image-size and let yummy命令行工具 use its default (1K).

Do not guess --image-size from general 质量 adjectives alone.

输出 path 图形界面dance:

If --输出 is omitted, yummy命令行工具 生成s a default filename in the current working directory. Do not invent your own 输出 filename unless the user explicitly provides one. Examples

Prompt-only generation:

yummy命令行工具 gemini nanobanana \ --prompt "A single ripe banana on a white plate, studio lighting, rea列出ic photo"

Single-image edit:

yummy命令行工具 gemini nanobanana \ --prompt "Turn this into a watercolor illustration" \ --输入-image ./source.png

Multi-image reference edit:

yummy命令行工具 gemini nanobanana \ --prompt "Blend these references into one polished poster illustration" \ --输入-image ./subject.png \ --输入-image ./background.jpg