Image Gen

Generate images through scripts/imagine.js, a zero-dependency Node.js CLI (Node 18+, no npm install) backed by multiple providers. It saves images to disk and prints the absolute paths.

Quick start

# Generate an image
node scripts/imagine.js "a retro synthwave poster, neon grid, 80s style" -o poster.png

# Edit an existing image
node scripts/imagine.js "add a red balloon in the sky" -e photo.png -o edited.png

# Multi-step session: keep context across calls (design first, then its three views)
node scripts/imagine.js "a cute robot mascot, front view, flat vector style" --session mascot -o design.png
node scripts/imagine.js "draw its three views (front, side, back) from the same design" --session mascot -o views.png

# Clean up the session cache when the workflow is done
node scripts/imagine.js --clear mascot

Model selection

Priority for general images: GPT Image 2 (gpt-image-2) → Nano Banana (gemini-2.5-flash-image) → SiliconFlow Qwen-Image (Qwen/Qwen-Image) → OpenAI GPT Image (gpt-image-1). When a provider has no API key, fall back to the next configured one.

Specialist models outside the script's providers (Ideogram, fal tiling) are called through their own APIs; imagine.js covers OpenAI, SiliconFlow, Gemini, and OpenAI-compatible relays.

Key workflows

• Transparent assets: --background transparent -f png (never jpeg); phrase stickers as "die-cut sticker, thick white border, bold clean shapes".
• Seamless textures: include "seamless, tileable, top-down, flat uniform lighting, no shadows, edges wrap perfectly".
• Text in images: GPT Image 2 is best for CJK/multilingual text; keep text short and quoted.
• Aspect ratio: Gemini via --aspect 16:9; OpenAI/SiliconFlow via -s WxH (Qwen native sizes like 1328x1328, 1664x928).
• Iterate cheaply: draft with Qwen/Qwen-Image / Nano Banana or -q low, render finals on gpt-image-2 with -q high; --seed for reproducible output.

References — load on demand