Create Stunning AI Images Directly from WhatsApp with Gemini

This n8n workflow turns your WhatsApp into a seamless AI image generation studio. It listens for incoming messages on your connected WhatsApp number, captures your simple text prompt (e.g., 'a knight on a horse'), and uses Gemini 2.5 Pro via LangChain to expand it into a richly detailed, artistic description optimized for image creation. The enhanced prompt is then sent to Gemini 2.0 Flash to generate a high-quality image in Base64 format, which is converted to a binary file and instantly replied back in the same chat.

The benefits are immense: no need for dedicated apps or complex setups—just chat naturally on WhatsApp to create professional-grade images on the fly. It saves time by automating prompt refinement and generation, ensuring consistently stunning results with cinematic lighting, ultra-detail, and photorealistic quality. Perfect for creators, marketers, or anyone needing quick visuals without design skills.

Use cases include brainstorming marketing visuals, generating concept art for stories or games, creating personalized avatars, or even social media content. Ideal for solopreneurs, content creators, or teams wanting instant AI art from mobile. Setup requires WhatsApp Business API credentials and Google Gemini API keys—deploy once and enjoy endless creativity.

Key nodes: WhatsApp Trigger, LangChain Chain (Gemini 2.5 Pro), Gemini Image Gen, Base64 to Binary, WhatsApp Reply.