HappyHorse 1.1 image-to-video: 300 px, 20 MB and ratio 1:2.5 to 2.5:1

Alibaba's reference for happyhorse-1.1-i2v says the first-frame image must be JPEG, JPG, PNG or WEBP, with both sides at least 300 pixels, an aspect ratio between 1:2.5 and 2.5:1, and a file of up to 20 MB (Alibaba Model Studio, read 2026-10-09). Output is 480P, 720P or 1080P (default) and 3 to 15 seconds (default 5). Sume lists no HappyHorse id (catalog read 2026-10-09).

What is the full input sheet?

Where does Sume fit?

For a first-frame job on Sume, send a public HTTPS image_url, optionally with end_image_url. gemini-omni-flash-1.1 takes 3 to 10 seconds at 360p to 4K in 16:9 or 9:16, so a square or 4:5 first frame needs a crop first. The Video Router docs list the envelope.

curl -X POST https://api.sume.com/v1/video-router/generate \
  -H "Authorization: Bearer $SUME_API_KEY" \
  -H "Content-Type: application/json" \
  -H "Idempotency-Key: i2v-001" \
  -d '{"model":"gemini-omni-flash-1.1","prompt":"Slow push-in, steam rising","image_url":"https://example.com/first-frame.png","duration":5,"resolution":"1080p","aspect_ratio":"16:9","mode":"async"}'

How do the lengths and prices compare?

A 5-second 1080p clip on Sume's Omni row is 5 x $0.1875 = $0.9375, with sound included. For a 15-second clip you need a row that reaches 15 seconds: the Video Router docs list seedance-2.5 at 4 to 30 seconds and wan-3.0 at 2 to 30 (check the live catalog for each row's envelope).