Skill2 steps

Social Resize

Extend one image to every social format without cropping.

How it runs

The right model for every step.

Instead of cropping, the skill paints new edges that match the original, then upscales each version, so one image becomes square, portrait, story and widescreen formats.

Every intermediate result is kept with the run, so you can inspect a step, reuse its output or rerun it with different settings.

Input
- Image
- Formats
01
Extend the canvasGemini 3.1 Flash Image
02
Upscale each formatTopaz Image Upscale
OutputSquare, portrait, story and widescreen versions

Run it

Call the skill by name.

Send the inputs, get back a run you can wait on or follow with a webhook. The same skill is available in the studio and to AI agents through the MCP server.

You get back

Square, portrait, story and widescreen versions

run.sh

curl https://api.monogram.dev/v1/skills/social-resize/runs \
  -H "Authorization: Bearer $MONOGRAM_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "input": {
      "image_url": "https://files.example.com/campaign.jpg",
      "formats": [
        "1:1",
        "4:5",
        "9:16",
        "16:9"
      ]
    }
  }'