fal-qwen-image-edit

Required inputs

• A text prompt describing the desired result.
• One or more reference images (--ref) as local files or URLs.
  • Typically: 1 “base” image to edit + optional extra reference/style images.
• A fal.ai API key in workers.jsonc (fal.key).

Optional inputs

• Output sizes / aspect ratios:
  • --image-size <preset> (repeatable) or --sizes a,b,c (comma-separated presets)
  • --size <WxH> (repeatable pixel-size hint; mapped to the closest supported preset)
  • Presets: square_hd, square, portrait_4_3, landscape_4_3, portrait_16_9, landscape_16_9
• --negative-prompt, --seed, --num-images, and other quality controls supported by the script.

Workflow