HappyHorse 1.1 lists 9 aspect ratios; Omni on Sume lists 2
HappyHorse 1.1 reference-to-video offers nine ratios, from 9:21 to 21:9. Gemini Omni Flash offers 16:9 and 9:16. How to check a Sume model's ratios first.

Alibaba's HappyHorse reference-to-video reference lists nine aspect ratios: 16:9 (default), 9:16, 3:4, 4:3, 4:5, 5:4, 1:1, 9:21 and 21:9 (Alibaba Model Studio, read 2026-10-09). Google lists 9:16 and 16:9 for Gemini Omni Flash (Google Omni docs, read 2026-10-09), and Sume passes those two through. For 4:5 or 1:1 you need another model or a crop.
What does each row accept?
| Ratio | HappyHorse 1.1 r2v | Gemini Omni Flash |
|---|---|---|
| 16:9 | Yes (default) | Yes (default) |
| 9:16 | Yes | Yes |
| 1:1 | Yes | No |
| 4:5 and 5:4 | Yes | No |
| 3:4 and 4:3 | Yes | No |
| 21:9 and 9:21 | Yes | No |
Where do I read Sume's ratios?
Each Sume model reports its own supported_aspect_ratios from GET /v1/videos/models; the video docs list the full vocabulary (16:9, 9:16, 1:1, 4:3, 3:4, 3:2, 2:3, 21:9, 9:21) and say each model shows the subset it accepts. Its example seedance-2 row lists 21:9, 16:9, 4:3, 1:1, 3:4 and 9:16. Read the live list, not the example.
import os, requests
r = requests.get("https://api.sume.com/v1/videos/models",
headers={"Authorization": f"Bearer {os.environ['SUME_API_KEY']}"})
for m in r.json()["data"]:
print(m["id"], m.get("supported_aspect_ratios"))What if you need 4:5?
Find a model whose list includes 4:5, or generate 9:16 and crop with the video filter for $0.02 a job. Sume lists no HappyHorse id (catalog read 2026-10-09).
Sources
Related posts
More in Comparisons
- HeyGen Business 5 custom avatars vs five Sume avatars at $4.75
HeyGen Business lists $149 a month plus $20 per seat with 5 custom avatars; creating five avatars on Sume is 5 x $0.95 = $4.75, with video billed separately.
- 4K image prices: FLUX.3 is 6.07x its 2K, Nano Banana 2.1 on Sume 1.33x
FLUX.3 Image costs $0.607 at 4K and $0.100 at 2K, a 6.07x jump. Nano Banana 2.1 on Sume goes from $0.15 to $0.20, a 1.33x step, and Pro is flat from 1K to 2K.
- HunyuanVideo 1.5 vs Wan 2.2: memory, resolution and license lines
HunyuanVideo 1.5 vs Wan 2.2 from the vendors' own pages: 14 GB with offloading vs 24 GB and 80 GB minimums, resolutions, and the license lines that differ.
- Hy Image 3.0 or 3.5 Preview: 3 vs 20 references, size rules, seed
Tencent's Hy Image 3.0 and 3.5 Preview side by side: reference counts, prompt limits, size ranges, seed ranges and resize_max_pixels, with what Sume lists.
Written by Sume