HappyHorse 1.0 vs 1.1: which one renders 480P on Model Studio?
On Alibaba Model Studio only HappyHorse 1.1 lists 480P. Both versions take 3 to 15 seconds, and 1.0 adds a video-edit id. Neither is in Sume's catalog.
Only HappyHorse 1.1 lists 480P on Alibaba's model list: 480P, 720P and 1080P across its text, image and reference ids. HappyHorse 1.0 starts at 720P. Both take 3 to 15 seconds, and only 1.0 has a video-edit id. HappyHorse is not in the Sume video catalog.
The ids
| Id | Clip length | Resolution |
|---|---|---|
| happyhorse-1.1-t2v | 3 to 15 s | 480P, 720P, 1080P |
| happyhorse-1.1-i2v | 3 to 15 s | 480P, 720P, 1080P |
| happyhorse-1.1-r2v | 3 to 15 s | 480P, 720P, 1080P |
| happyhorse-1.0-t2v / i2v / r2v | 3 to 15 s | 720P, 1080P |
| happyhorse-1.0-video-edit | 3 to 15 s | 720P, 1080P |
What this means
- Cheap drafts: choose 1.1, the only one that renders at 480P.
- Editing a clip: 1.0 is the line with a video-edit id on this page; 1.1 lists none.
- Cloudflare's 1.1 page lists 720P and 1080P only, so a 480P request may need Alibaba directly.
On Sume
If a 480p draft is the goal, Sume lists Wan 3.0, Seedance 2.5, MiniMax H3 and Grok Imagine 1.5 at 480p, and Gemini Omni Flash 1.1 at 360p. For editing a clip, the Omni video_url route is documented in the Video Router docs.
Choosing between the two
Pick 1.1 unless you need the 1.0 video-edit id. The only quality claims here are the ones Alibaba's page makes about resolutions and lengths, which this post repeats; I have not compared outputs. If you need a 480P proof, 1.1 is the only one where the page lists the size.
If you only work through Sume, neither version is available, and the closest drafts are Wan 3.0 or Seedance 2.5 at 480p.
Sources
Related posts
More in Comparisons
- Headshot background to neutral grey: cutout plus Pillow or an AI edit
Swap a headshot background for grey: Sume RMBG at $0.0225 plus a Pillow composite keeps the face pixels exact; an Ideogram 4.5 edit costs $0.075 or more.
- HeyGen's X-RateLimit-Scope header vs Sume's error.details.scope
HeyGen's October 2026 429s add a scope header. Sume names the bucket in error.details.scope and sends ratelimit-* headers; one parser can read both.
- Higgsfield API vs Sume Videos API for a Sora port: five changes
Higgsfield's Sora migration guide changes auth, endpoints, body, response id and webhooks. What each costs in code, next to the Sume /v1/videos shape.
- How many AI videos has TikTok labeled? 37 million to 3 billion
TikTok's newsroom gives three numbers: 37 million creators used its label tool by May 2024, 1.3 billion videos labeled by Nov 2025, over 3 billion by July 2026.
Written by Sume