Alibaba's flagship video model, upgraded — and cheaper than 1.0
HappyHorse 1.1 — Alibaba's Flagship AI Video Model
Run Alibaba's HappyHorse 1.1 on gVideo alongside 11 other models — Kling 3.0, Veo 3.1, Sora 2 Pro, Luma Ray 2, Wan 2.7, Seedance 2.0, Hailuo 2.3, Kling 2.5 Turbo, and Pika 2.2. One subscription, one credit pool, no extra setup. 1.1 succeeds the model that topped the Artificial Analysis blind tests in April 2026 — same native audio synthesis, more aspect ratios, lower price.
What’s different
Why creators reach for HappyHorse 1.1
Successor to a chart-topper
HappyHorse 1.0 climbed to the top of the Artificial Analysis blind-test leaderboards for both text-to-video and image-to-video in April 2026. Version 1.1 is Alibaba's direct upgrade — same native-audio pipeline, refreshed generation quality, and a lower per-second price than 1.0 ever had.
Native audio + lip-sync
Audio is synthesized in the same pass as video — no separate dubbing step. Speech, ambient sound, and music are all generated together, with precise lip-sync when characters speak.
Multimodal reference inputs
Combine a text prompt with reference photos for character, product, or style consistency across the clip. Text-to-video, image-to-video, and reference-to-video all run natively on gVideo.
9 aspect ratios — the most on gVideo
16:9, 9:16, 1:1, 4:3, 3:4, 21:9 ultrawide, 9:21, 5:4, and 4:5. No other model on gVideo covers cinema ultrawide and every social format in one engine.
Sample generations
Best prompts for HappyHorse 1.1
Hover to preview. Click any example to prefill the generator.
Cinematic close-up of a young woman in a sunlit Parisian cafe, gentle steam from her espresso, slow push-in, warm tungsten light
Anime: a teenage girl in school uniform on a rooftop at golden hour, wind blowing her hair, cherry blossom petals drifting past, painterly background
Macro 360-degree rotation of a luxury silver watch on black velvet, dramatic key light, dust motes through shaft of light, realistic chrome reflections
Vertical 9:16 cinematic — rainy neon-lit Tokyo street at night, lone figure with umbrella walking past noodle shop, reflections in puddles
Skateboarder landing a kickflip in slow motion at sun-bathed concrete plaza, dust kicking up on impact, dynamic camera tracking, motion blur
Documentary handheld shot of a fishmonger at Tokyo market preparing tuna, steam, natural daylight, ambient market chatter
One prompt · 19 engines
Same prompt, 10 models
This is what aggregator access unlocks: one prompt, run in parallel against every model on gVideo — Sora 2 Pro, Kling, Veo, Luma, Seedance, Hailuo, Wan. You see the style differences side by side before committing credits to a final render.
Prompt: “A golden retriever sprinting through shallow waves at sunset, slow motion, cinematic 35mm, warm backlight”
Samples are placeholders — real gVideo generations will replace these in the next release.
Head-to-head
HappyHorse 1.1 vs the other models on gVideo
| Model | Price | Speed | Max duration | Best for |
|---|---|---|---|---|
| Veo 3.1 Lite | 💰Economy | 60–120s | 8s | Cheapest audio-native · Google Veo |
| Pika 2.2 | 💰Economy | 30–75s | 10s | Stylized · 720p default |
| Hailuo 2.3 | 💰Economy | 40–90s | 10s | Chinese realism · 768p default |
| Kling 2.5 Turbo | 💰Economy | 30–60s | 10s | Fast Kling renders |
| Wan 2.7 | 💰💰Standard | 30–75s | 15s | Native audio + 2-15s + multi-aspect |
| Veo 3.1 | 💰💰Standard | 90–180s | 8s | Photoreal + audio |
| Sora 2 | 💰💰Standard | 90–180s | 20s | OpenAI cinematic · budget 720p |
| Kling 3.0 | 💰💰Standard | 60–120s | 10s | Lifelike motion |
| Luma Ray 2 | 💰💰Standard | 40–90s | 9s | Dream Machine · base default |
| HappyHorse 1.1THIS PAGE | 💰💰Standard | 90–150s | 15s | Native audio · 9 aspect ratios · 720p default |
| Veo 3.1 Pro | 💰💰Standard | 120–240s | 8s | Top-tier cinematic · 4K |
| Seedance 2.0 | 💰💰💰Premium | 40–90s | 10s | Speed + adherence |
| Sora 2 Pro | 💰💰💰Premium | 90–180s | 20s | OpenAI cinematic · HD default |
Credits
HappyHorse 1.1 credit cost on gVideo
HappyHorse 1.1 costs 50 credits per 5-second video, or 100 credits for 10 seconds. All 19 models share a single credit pool under your gVideo subscription.
HappyHorse 1.1 Standard 720p costs 50 credits per 5-second video — cheaper than 1.0 was — with native audio baked into every render. HD 1080p (65 credits per 5s) is available when you need maximum quality, and clips run from 3 to 15 seconds. Free 100-credit signup covers two renders to test.
Common questions about HappyHorse 1.1
What is HappyHorse 1.1?
HappyHorse 1.1 is Alibaba's flagship AI video model — the direct upgrade to HappyHorse 1.1, which topped the Artificial Analysis blind-test leaderboards for both text-to-video and image-to-video in April 2026. Version 1.1 keeps the native audio synthesis, expands to 9 aspect ratios, and ships at a lower per-second price.
What changed from HappyHorse 1.0 to 1.1?
Three things on gVideo: price dropped (50 credits per 5s at 720p, down from 60; 1080p dropped even more), aspect ratio support grew from 5 to 9 formats including 21:9 ultrawide, and generation quality was refreshed. Duration (3-15s) and native audio are unchanged.
How does HappyHorse 1.1 compare to Sora 2 Pro?
HappyHorse 1.1 costs less than a third of Sora 2 Pro per 5-second render on gVideo (50 credits vs 164) and generates audio natively. Sora still has the edge on very long-form coherence (up to 20s); HappyHorse runs 3–15s on gVideo.
Does HappyHorse 1.1 support audio?
Yes — natively. Audio (speech, ambient, music) is synthesized in the same pass as video, with precise lip-sync when characters speak. This puts it in the same audio class as Veo 3.1 and Sora 2 Pro.
What aspect ratios does HappyHorse 1.1 support on gVideo?
Nine: 16:9, 9:16 vertical, 1:1 square, 4:3, 3:4, 21:9 ultrawide, 9:21, 5:4, and 4:5. More aspect ratios than any other model on gVideo.
Can I use HappyHorse 1.1 for commercial work?
Yes on all paid plans. The free tier is personal-use only. Using the model via gVideo wraps it under our standard commercial license for paying users.
Ready to generate with HappyHorse 1.1?
Start free — 100 credits on signup, no credit card required.