Generate and edit images using Gemini via Corespeed AI Gateway. Use when a user asks to create, draw, design, or generate an image, picture, illustration, icon, logo, banner, thumbnail, or screenshot mockup. Also triggers on image editing (remove background, resize, recolor, combine photos), image analysis (describe, compare, OCR), and text generation with Gemini models (gemini-2.5-flash-image, gemini-2.5-flash, gemini-2.5-pro). Trigger phrases include: "画一个", "生成图片", "做一张图", "帮我P图", "make me an image", "generate a picture", "edit this photo", "what's in this image".
Render Excalidraw (.excalidraw) files to PNG images and take screenshots of web pages using headless Chrome via the brow CLI. Use when a user asks to render an Excalidraw diagram to an image, capture a website as a screenshot, or convert a drawing to PNG.
Generate professional PowerPoint (.pptx) presentations using JSX/TSX with Deno. Supports slides, text, shapes, tables, charts (bar, line, pie, donut), images, gradients, shadows, and flexible layouts. Use when a user asks to create presentations, slide decks, pitch decks, reports, or any PPTX file.
Generate video, images, audio, and music using 40+ AI models via fal.ai. Use for video generation (Kling v3, Sora 2, Veo 3.1, LTX 2.3, Pixverse v5), image generation (Nano Banana 2, FLUX 2 Pro/Schnell, GPT Image 1.5, Qwen Image 2 Pro, Recraft V4, Seedream 5), text-to-speech (MiniMax Speech-02 HD), music/sound effects (Beatoven), and utilities (Topaz upscale, background removal, lipsync). Use when a user asks to create videos, generate images, produce voiceovers, create music/sound effects, upscale media, remove backgrounds, or combine multiple AI media models in a single workflow.