Generates and edits images using Google Nano Banana models with Gemini API.
npx skills add https://github.com/Xipher-Labs/walter-os --skill nanobanana-xipher-labs
Please help me install this Agent Skill. Skill: nanobanana Source: https://github.com/Xipher-Labs/walter-os/tree/main/skills/nanobanana Command: npx skills add https://github.com/Xipher-Labs/walter-os --skill nanobanana-xipher-labs
It turns image requests into generated or edited visuals so you can produce marketing, product, and content imagery without manual design work.
Use the nanobanana skill to generate an image from a prompt like: "Create an isometric 45° hero illustration of a glowing data pipeline made of hexagonal nodes, electric purple and warm amber accents, soft cream background, no text."
High-intent search queries and answers about installing and using this skill.
To generate marketing assets from text prompts using Google Gemini models, you provide detailed descriptions including composition and lighting. This skill creates hero images and visual assets deterministically, saving outputs alongside a reproducibility sidecar prompt file.
Yes, you can edit existing product mockups to change backgrounds or remove objects with Google Nano Banana. The skill supports targeted image transformations, allowing you to modify images with instructions to re-light or remove objects while preserving identity.
Multi-image blending for brand-consistent marketing visuals is the process of combining multiple reference images, like logos and product mockups. This skill uses Google Nano Banana to blend these inputs into final artwork that maintains your brand identity.
Yes, you need a GEMINI_API_KEY to use multimodal image generation scripts. This skill requires the API key to access the Google Gemini image generation API for text-to-image creation, image editing, and multi-image blending tasks.
To save generated images deterministically with a reproducible prompt file, the skill automatically stores output images alongside a sidecar prompt file. This ensures your text-to-image generation and image editing results can be reproduced consistently.
Yes, Pillow is required for image editing and logo placement in generated marketing assets. The skill lists Pillow as a dependency to handle image processing tasks when executing text-to-image creation and multi-image blending workflows.
gvkhoslaGenerate and edit images via the Gemini API with text prompts.
phuhao00Optimize short-video content for Douyin and TikTok recommendation algorithms.
JerichoCruzGenerate and edit images via Google's Gemini API.
shiqkuangsanCreate Next.js apps for text-to-image generation and iterative editing with Gemini APIs.
