Generate and edit images via the Gemini 3 Pro Image API.
npx skills add https://github.com/antoniolg/agent-kit --skill nano-banana-pro-antoniolg
Please help me install this Agent Skill. Skill: nano-banana-pro Source: https://github.com/antoniolg/agent-kit/tree/main/skills/3rd-nano-banana-pro Command: npx skills add https://github.com/antoniolg/agent-kit --skill nano-banana-pro-antoniolg
Generate and edit visuals efficiently using Gemini 3 Pro Image API, enabling rapid creative iteration without manual tooling.
Generate a 2K image from the prompt 'A serene futuristic cityscape' and save as output.png.
High-intent search queries and answers about installing and using this skill.
To generate images from text prompts using the Gemini 3 Pro API, you provide a text prompt, your Gemini API key, and a model path to create high-quality visuals like marketing assets or concept art.
Yes, you can edit existing images with Gemini 3 Pro using instruction-based image-to-image modifications at 1K, 2K, or 4K resolutions by providing optional input-image paths.
Yes, you need a Gemini API key and a specified model path to drive text-to-image generation and image editing workflows with the Gemini 3 Pro API.
The best way to automate marketing asset creation with Gemini 3 Pro is using text-to-image and image-to-image API workflows for rapid creative iteration without manual tooling.
Yes, the Gemini 3 Pro API supports image-to-image workflows by accepting optional input-image paths to guide instruction-based modifications and edits.
zzafergokAccess Google Gemini models via CLI or API for reasoning and multimodal tasks.
SJTU-IPADSAutomate deterministic image editing tasks on image collections with Pillow.
secondskyIntegrate Google Gemini API via @google/genai SDK for text generation and function calling.
hsliuustc0106Generate and edit images from text prompts using vLLM-Omni diffusion models.
