reloadium.com

generateImage

Generate a brand-new image from a text description and show it in the chat as a real image, not a text description of one. Use this when the user wants an illustration, concept art, a mockup, or any picture created from scratch. This is for GENERATING an image from nothing, not editing a photo the user already has — there's no way to pass an existing image into this tool; if the user wants to modify a photo they attached, tell them to use an image-editing app instead. Each call is a real, billed generation — don't call it speculatively, don't generate more than one image per request unless the user explicitly asks for multiple, and don't regenerate one that already exists earlier in this conversation just to re-show it. To modify the image THIS tool just produced (a follow-up like 'make it a night scene' or 'add snow'), use editImage instead of calling this again — regenerating from the text prompt alone won't preserve what was actually in the image.

Page: /

Input schema

{
  "type": "object",
  "properties": {
    "prompt": {
      "type": "string",
      "description": "A detailed description of the image to generate — concrete subject, style, composition, mood. Vaguer prompts produce vaguer images."
    },
    "aspectRatio": {
      "type": "string",
      "enum": [
        "1:1",
        "16:9",
        "9:16",
        "4:3",
        "3:4",
        "4:5",
        "5:4",
        "3:2",
        "2:3",
        "21:9"
      ],
      "description": "Optional, defaults to 1:1 (square). Use 16:9/9:16 for a widescreen/portrait scene, 4:3/3:4 for a more traditional photo/print shape, 4:5/5:4 for a social-media portrait/landscape post, 3:2/2:3 for a classic camera-photo shape, 21:9 for a cinematic ultrawide."
    }
  },
  "required": [
    "prompt"
  ]
}