Payload and output preview

Payload example

{
  "version": "v1",
  "output": {
    "width": 1080,
    "height": 1920,
    "fps": 30
  },
  "assets": [
    { "id": "img-1", "type": "image", "url": "https://pub-2ad5592bc4ca44abb609acfc0b7c5ceb.r2.dev/reel-forge-website-assets/House%20exterior.jpeg" },
    { "id": "img-2", "type": "image", "url": "https://pub-2ad5592bc4ca44abb609acfc0b7c5ceb.r2.dev/reel-forge-website-assets/house%20lounge.jpeg" },
    { "id": "img-3", "type": "image", "url": "https://pub-2ad5592bc4ca44abb609acfc0b7c5ceb.r2.dev/reel-forge-website-assets/house%20kitchen.jpeg" },
    { "id": "img-4", "type": "image", "url": "https://pub-2ad5592bc4ca44abb609acfc0b7c5ceb.r2.dev/reel-forge-website-assets/house%20terrace.jpeg" }
  ],
  "composition": {
    "timeline": [
      { "id": "image-layer-1", "type": "image", "asset_id": "img-1", "time": { "start_seconds": 0, "duration_seconds": 4 } },
      { "id": "image-layer-2", "type": "image", "asset_id": "img-2", "time": { "start_seconds": 4, "duration_seconds": 4 } },
      { "id": "image-layer-3", "type": "image", "asset_id": "img-3", "time": { "start_seconds": 8, "duration_seconds": 4 } },
      { "id": "image-layer-4", "type": "image", "asset_id": "img-4", "time": { "start_seconds": 12, "duration_seconds": 4 } }
    ]
  }
}

Output preview

Four portrait house images stitched into a 16-second vertical sequence.

Stitch Together Images

Build image sequences by placing image layers with explicit timing. For sequence-style image stitching, each image should include full time values.

Input assets

This example uses four portrait house images in sequence:

Why this works

When stitching images:

  1. Explicit timing: Each image layer needs time with start_seconds and duration_seconds. Images are placed back-to-back (0–4s, 4–8s, 8–12s, 12–16s) to form a continuous sequence.
  2. Cover scaling: Images are scaled to fill the 9:16 output frame using cover logic; excess is cropped.
  3. No image auto-stitch sequencing: auto_stitch sequences video/audio clips, not image sequences. For slideshow-style image stitching, define each image layer timing explicitly.