gemini-imagegen_skill

This skill helps you generate and edit images using the Gemini API, enabling prompts-driven visuals, style transfers, and multi-turn refinements.
  • TypeScript

10.5k

GitHub Stars

2

Bundled Files

2 months ago

Catalog Refreshed

4 months ago

First Indexed

Readme & install

Copy the install command, review bundled files from the catalogue, and read any extended description pulled from the listing source.

Installation

Preview and clipboard use veilstrat where the catalogue uses aiagentskills.

npx veilstrat add skill everyinc/compound-engineering-plugin --skill gemini-imagegen

  • requirements.txt35 B
  • SKILL.md6.3 KB

Overview

This skill provides a practical guide for generating and editing images using the Gemini API (Nano Banana Pro). It covers default model choices, resolution and aspect-ratio options, image editing, multi-turn refinement, and important file-format details. Use it to produce photorealistic scenes, stylized art, logos, stickers, and product mockups with repeatable settings.

How this skill works

The skill uses the gemini-3-pro-image-preview model as the default for text-to-image, image editing, and composition from multiple reference images. You send prompts and optional image files to the API, specify image_config for resolution and aspect ratio, and save returned inline image data (Gemini returns JPEG by default). It also supports chat-based multi-turn refinement and optional Google Search grounding for real-time data.

When to use it

  • Create new images from text prompts (logos, stickers, art, photorealistic scenes).
  • Edit or augment existing images by passing the original image with an instruction.
  • Iteratively refine images through a chat-style multi-turn workflow.
  • Compose scenes from multiple reference images (up to 14 inputs).
  • Produce product mockups or marketing visuals at different resolutions and aspect ratios.

Best practices

  • Always default to model gemini-3-pro-image-preview unless explicitly requested otherwise.
  • Use 1K for quick previews, 2K for balanced results, and 4K for maximum detail when needed.
  • Specify aspect ratio explicitly for final output (1:1, 16:9, 9:16, 21:9, etc.).
  • Include camera and lighting details for photorealism; state art style and linework for stylized images.
  • Save generated images with .jpg extension because Gemini returns JPEG by default; convert to PNG only when you explicitly re-save in PNG format.
  • Use conversational prompts for edits and take advantage of chat multi-turn refinement for iterative changes.

Example use cases

  • Design a clean sans-serif logo reading 'Daily Grind' with coffee-bean motif, export at 2K square.
  • Edit a product photo: add studio lighting and a polished concrete surface for mockups.
  • Generate a kawaii sticker of a red panda with bold outlines and white background.
  • Compose a group photo by combining multiple headshots into a cohesive office scene.
  • Create a weather infographic for Tokyo using Google Search grounding and save the visual.

FAQ

Use gemini-3-pro-image-preview by default. Start at 1K for speed, move to 2K/4K for higher quality, and pick the aspect ratio required for your use case.

Why must I use .jpg when saving images?

Gemini returns JPEG data by default. Saving with a .png extension can create media-type mismatches; convert explicitly to PNG if needed.

Built by
VeilStrat
AI signals for GTM teams
© 2026 VeilStrat. All rights reserved.All systems operational