Which should you pick?
Gemini Omni Video is the cheaper job: 36-90 credits against 42-270 credits for Happy Horse 1.1 Image to Video. Those are the credits one complete generation costs, not a headline rate, so they are directly comparable even though the two models bill differently.
At their most expensive settings the gap widens: Happy Horse 1.1 Image to Video tops out at 270 credits a job versus 90, driven by output resolution.
Gemini Omni Video supports up to 4K, the higher of the two.
Gemini Omni Video supports more aspect ratios (2: 16:9, 9:16), giving it more format flexibility.
Happy Horse 1.1 Image to Video requires a starting image; Gemini Omni Video can generate from a text prompt alone.
What a job costs
Gemini Omni Video
36-90 credits
It bills per second of output, and the price moves with clip length.
- Price9 credits
Happy Horse 1.1 Image to Video
42-270 credits
It bills per second, at a rate that changes with output resolution, and the price moves with output resolution.
- SD/HD14 credits
- 4K18 credits
All figures are Versely credits. Your plan's credit allowance is on the pricing page.
Spec comparison
| Spec | Gemini Omni Video | Happy Horse 1.1 Image to Video |
|---|---|---|
| Provider | Alibaba | |
| Cost per job | 36-90 credits | 42-270 credits |
| Billing | per second of output | per second, at a rate that changes with output resolution |
| Max resolution | 4K | 1080p |
| Aspect ratios | 16:9, 9:16 | — |
| Durations | 4s, 6s, 8s, 10s | 3s, 4s, 5s, 6s, 7s, 8s, 9s, 10s, 11s, 12s, 13s, 14s, 15s |
| Frame rates | — | — |
| Qualities | 720p, 1080p, 4K | 720p, 1080p |
| Requires starting image | No | Yes |
| Accepts video input | No | No |
| Reference images | — | — |
| Leaderboard | Unranked | #7 in image to video |
| Released | May 19, 2026 | Jun 23, 2026 |
What each one does that the other doesn't
Only Gemini Omni Video
text to video, reference to video, multimodal, character ref, audio driven, 4k
Only Happy Horse 1.1 Image to Video
first frame, native audio, multilingual lipsync, 1080p
Both list: image to video.
Leaderboard positions
Versely ranks each capability on its own leaderboard, so a position is only comparable between two models within the same row.
Gemini Omni Video
Not on a Versely leaderboard yet.
Happy Horse 1.1 Image to Video
- Image to video#7
Full Gemini Omni Video spec sheet →
Google Gemini Omni multimodal video generation. Accepts a prompt plus optional reference images, source video clips, character IDs, and audio IDs. Supports 720p / 1080p / 4k output at 4-10 seconds (16:9 or 9:16). Quota: images + videos*2 + character_ids <= 7.
Full Happy Horse 1.1 Image to Video spec sheet →
Happy Horse 1.1 animates a first-frame image into 1080p video with synchronized native audio and multilingual lip-sync (aspect ratio inferred from the image, 3–15s)
More comparisons
Frequently asked questions
Which is cheaper, Gemini Omni Video or Happy Horse 1.1 Image to Video?+
Gemini Omni Video is cheaper per job: 36-90 credits against 42-270 credits for Happy Horse 1.1 Image to Video.
What can Gemini Omni Video do that Happy Horse 1.1 Image to Video can't, or vice versa?+
Only Gemini Omni Video lists text to video, reference to video, multimodal, character ref, audio driven, 4k. Only Happy Horse 1.1 Image to Video lists first frame, native audio, multilingual lipsync, 1080p. Both list image to video.
How do Gemini Omni Video and Happy Horse 1.1 Image to Video bill?+
Gemini Omni Video bills per second of output, and its price moves with clip length. Happy Horse 1.1 Image to Video bills per second, at a rate that changes with output resolution, and its price moves with output resolution. Both are charged in Versely credits.
Which has higher output resolution, Gemini Omni Video or Happy Horse 1.1 Image to Video?+
Gemini Omni Video supports higher output (4K against 1080p).
How long a clip can Gemini Omni Video and Happy Horse 1.1 Image to Video generate?+
Gemini Omni Video supports 4s, 6s, 8s, 10s; Happy Horse 1.1 Image to Video supports 3s, 4s, 5s, 6s, 7s, 8s, 9s, 10s, 11s, 12s, 13s, 14s, 15s.
Try both inside Versely
The all-in-one AI studio for creators. 60+ models for video, image, voice, music and lipsync in a single app.