$ loading_
Generate images with Gemini Nano Banana using configurable prompts, ratios, models, and output paths.
Copy the install command and let the AI configure it · recommended for beginners
No copy-paste install info for "gemini-nano-banana-mcp" yet — see the docs or source repo.
Use gemini-nano-banana-mcp to generate a minimalist product poster for wireless earbuds, with a clean composition, light background, and clear product focus. Use a 16:9 aspect ratio and save it to ./outputs/poster.png.
A poster-style image matching the prompt is generated and saved to the specified path.
Call gemini-nano-banana-mcp to generate a 1:1 social media image promoting a new summer coffee drink, with a bright and lifestyle-oriented style, and save the output to ./outputs/summer-coffee.png.
A square promotional image suitable for social media posting is produced as an image file.
Use gemini-nano-banana-mcp to generate two images from the same prompt: one in 3:2 landscape and one in 4:5 portrait. Save them to ./outputs/style-a.png and ./outputs/style-b.png for composition comparison.
Two images with different aspect ratios are generated for layout and composition comparison.
Marketers can generate visuals for campaign pages or social posts directly from prompts, while setting aspect ratios and output locations as needed. This helps them create first-draft creative assets faster.
Designers can generate multiple image variants with different model settings and aspect ratios for the same theme. This is useful for early concept exploration and layout comparison.
Developers can integrate this MCP tool into automated workflows to generate images from prompts and write them to specified directories. This makes downstream scripting and archiving easier.
It is an MCP tool for generating images with Google's Gemini Nano Banana image models. It supports configurable prompts, models, aspect ratios, and output locations.
Based on the description, you need a free Google AI Studio API key. The provided material does not include further installation or runtime details.
This tool explicitly supports configurable prompts, models, aspect ratios, and output locations, making it more suitable for controlled workflows. The provided material does not include further comparisons.
Generate images and perform background removal, upscaling, and format conversion.
Generate and edit images with natural language, storyboards, icons, and video-to-image.
Generate, edit, and enhance visuals with Gemini multimodal image APIs.
Generate images locally with Gemini models and save them as JPEG files.
Generate high-quality images with Gemini, smart model selection, and 4K output.
Connect Gemini image models so AI coding assistants can generate images from prompts.