A new video model dropped at #1 on the leaderboard 👀 It's called HappyHorse-1.0, and it's currently leading in both text-to-video and image-to-video. From my testing, it's particularly good at multi-shot videos and following detailed directions 👇
Video Models
HappyHorse 1.0 by Alibaba - #1 AI Video Model with Single-Stream Transformer & Unified Generation
Alibaba's HappyHorse 1.0, ranked #1 on the Artificial Analysis AI video leaderboard (Apr 2026). A single-stream Transformer with ~15B parameters delivering unified text-to-video, image-to-video, reference-to-video, video editing, and video extension. Generate 720p/1080p videos at 3-15 seconds with multiple aspect ratios.
Public
Live PipelineTake 01 / 02
Text-to-Video Showcase
Turn a single sentence into cinema-grade footage. HappyHorse renders prompts as fluid, photoreal scenes with rich lighting, dynamic camera moves, and feature-film polish.
Source Feeds00 Inputs
Pipeline
00%
Program · On AirAI · Generated
Output
Transcript · 01
Nostalgic Cassette Tape
Live PipelineTake 01 / 01
Image-to-Video Showcase
See how HappyHorse brings still images to life with cinematic motion, faithful character preservation, and natural lighting transitions across a range of scenes.
Source Feeds01 Inputs
Pipeline
00%
Program · On AirAI · Generated
Output
Transcript · 01
Reference Image to Video
Live PipelineTake 01 / 01
Reference-to-Video Showcase
See how HappyHorse fuses multiple reference images into a single coherent video. Each clip is driven by 2-3 source pictures that lock down character identity, wardrobe, and scene styling before motion is generated.
Source Feeds01 Inputs
Pipeline
00%
Program · On AirAI · Generated
Output
Transcript · 01
Desert Explorer Adventure
Live PipelineTake 01 / 01
Video Editing Showcase
Prompt-driven video editing powered by multi-image references. Swap objects, restyle scenes, and adjust the look while preserving the original motion.
Source Feeds01 Inputs
Pipeline
00%
Program · On AirAI · Generated
Output
Transcript · 01
Setting -> Fashion Runway
Live PipelineTake 01 / 01
Video Extension Showcase
Extend any existing clip with HappyHorse for a seamless continuation. The model preserves motion, lighting, and subject identity so the new footage feels like one unbroken take.
Source Feeds01 Inputs
Pipeline
00%
Program · On AirAI · Generated
Output
Transcript · 01
Rainy Alley Continuation
HappyHorse 1.0 on X
See what creators are saying about HappyHorse 1.0, the new #1 AI video model.
We’ve added a new pseudonymous video model to our Text to Video and Image to Video Arenas.‘HappyHorse-1.0’ is currently landing in the #1 spot for Text and Image to Video (No Audio) and the #2 spot for Text and Image to Video (With Audio). Further details coming soon. Example Show more
HappyHorse is still in the stable. 🐴 No official website yet — anything you've seen out there isn't us. We're part of Alibaba's ATH AI Innovation Unit, and when we're ready, you'll know. Stay tuned. #HappyHorse #Alibaba #ATH
Congratulations to @HappyHorseATH for securing #1 and #2 across the Artificial Analysis Video Arena leaderboards! A significant milestone, and the journey continues.🚀 #AlibabaAI #HappyHorse
Revealing HappyHorse-1.0 as the latest video model from Alibaba! @HappyHorseATH has landed in #1 or #2 across all of the leaderboards in the Artificial Analysis Video Arena. In our ‘without audio’ leaderboards, HappyHorse-1.0 is comfortably in first place. In our ‘with audio’
Revealing HappyHorse-1.0 as the latest video model from Alibaba! @HappyHorseATH has landed in #1 or #2 across all of the leaderboards in the Artificial Analysis Video Arena. In our ‘without audio’ leaderboards, HappyHorse-1.0 is comfortably in first place. In our ‘with audio’ Show more
New analysis: Alibaba’s HappyHorse topped the AI video leaderboard last week. The timing matters more than the score. It appeared during peak customer frustration with Bytedance’s pricing. Alibaba Cloud sales teams were already approaching Volcano Engine’s enterprise clients.
An anonymous model called HappyHorse appeared on Artificial Analysis’s Video Arena on April 7. Three days later, Alibaba claimed it. The model scored above Seedance 2.0 in both image-to-video and text-to-video categories. But the commercial logic matters more than the benchmark.
WHO IS HAPPYHORSE? IS IT WAN 2.7 VIDEO? Over the weekend a new MYSTERY AI VIDEO MODEL appeared on Artificial Analysis AI Video Arena as HAPPY HORSE V1 with a V2 variant. It definitely appears to be from Asia. If it is WAN 2.7 it is sizable leap from 2.6 Is it a Seedance 2.0 Show more
HappyHorse-1.0 is now live on Arena! 🚀 Early evals show exceptional performance in Video Edit. We are now in the final optimization sprint for the official launch in 2 weeks. We invite the community to get early access and test our capabilities at arena.ai. 🐎✨
🚀Exciting progress ahead. Can’t wait to see what @HappyHorseATH unlocks for creators in video edit! #AlibabaAI #HappyHorse
HappyHorse-1.0 is now live on Arena! 🚀 Early evals show exceptional performance in Video Edit. We are now in the final optimization sprint for the official launch in 2 weeks. We invite the community to get early access and test our capabilities at arena.ai. 🐎✨
Thrilled to see HappyHorse‑1.0 land #1 in the Video Edit Arena! 🎉@HappyHorseATH #AlibabaAI #HappyHorse
New video model HappyHorse-1.0 by Alibaba-ATH debuts at #1 in Video Edit Arena. It scores 1299, leading Grok Image Video by +42 points and Kling o3 Pro by +48 points. Video editing is an emerging frontier capability for video models, and only a small number of models support
HappyHorse 1.0 on YouTube
Watch demos and tutorials showcasing HappyHorse 1.0's video generation.
- Happy Horse 1.0 Takes the Lead! | API Tutorial - fal
- Happy Horse 1.0 Is Crushing SeeDance 2.0 (New #1 AI Model) - AI Factory
- Happy Horse 1.0 Just Destroyed Seedance 2.0 - Ai Chemy
- The Honest Truth About Happy Horse 1.0 (Watch Before You Buy) - AI Filmmaking Academy
- Happy Horse 1.0 is DESTROYING Seedance 2.0… This is Crazy 🤯 - AI Biceps
- Happy Horse: The Seedance Killer? Plus BIG 4k AI Video News! - Theoretically Media
HappyHorse 1.0 on YouTube
Watch demos and tutorials showcasing HappyHorse 1.0's video generation.
Reel · Specifications
What's HappyHorse 1.0
Alibaba's #1 AI video model on the global leaderboard.
- · 01#1#1Leaderboard Rank
- · 0215BParameters
- · 031080pResolution
- · 043-15sDuration
HappyHorse 1.0 is a single-stream Transformer with ~15B parameters that took the top spot on the Artificial Analysis video leaderboard in April 2026.
Reel · Capabilities
HappyHorse 1.0 Features
Discover the leaderboard-topping capabilities of HappyHorse 1.0's single-stream transformer video generation model
- Feature 01 / 08
Leaderboard #1
Ranked first on the Artificial Analysis video generation leaderboard, outperforming established competitors across motion fidelity, prompt adherence, and overall visual quality benchmarks.
- Feature 02 / 08
Single-Stream Transformer
Powered by an efficient single-stream transformer architecture with approximately 15B parameters, balancing high-quality output with reasonable compute requirements for production-ready generation.
- Feature 03 / 08
Cinematic 1080p
Generate broadcast-ready video at both 720p and 1080p resolution with crisp details, vibrant colors, and cinematic aesthetics suitable for professional content workflows.
- Feature 04 / 08
5 Endpoints
Five specialized endpoints cover every workflow: text-to-video, image-to-video, reference-to-video, video-edit for targeted modifications, and video-extend for seamless continuation.
- Feature 05 / 08
Multi-Image References
Guide generation with multiple reference images simultaneously to lock in characters, settings, and visual style across the entire output for consistent results.
- Feature 06 / 08
Flexible Duration
Choose any clip length from 3 to 15 seconds with a sensible 5-second default, giving creators precise control over pacing for shorts, ads, and narrative scenes.
- Feature 07 / 08
Five Aspect Ratios
Five native aspect ratios including 16:9, 9:16, 1:1, 4:3, and 3:4 cover horizontal cinema, vertical social, square posts, and traditional broadcast formats without cropping.
- Feature 08 / 08
Fast Generation
Produces a 1080p clip in roughly 38 seconds on a single H100 GPU, enabling rapid iteration cycles and cost-effective scaling for high-volume creative pipelines.
FAQ
Frequently Asked Questions
Common questions about HappyHorse 1.0 video generation
Still have questions?
HappyHorse 1.0 is Alibaba's flagship AI video model, ranked #1 on the Artificial Analysis leaderboard as of April 2026. Built on a single-stream Transformer architecture with approximately 15B parameters, it delivers state-of-the-art motion stability, prompt adherence, and visual fidelity across a unified pipeline.
HappyHorse exposes 5 endpoints covering the full creative lifecycle: text-to-video, image-to-video, reference-to-video (using subject or style references), prompt-driven video editing, and video extension. All endpoints support 720p and 1080p output with durations from 3 to 15 seconds.
Generated clips can run from 3 to 15 seconds, with a default of 5 seconds. Pricing scales linearly with duration, so a 10-second clip costs exactly twice as much as a 5-second clip at the same resolution.
HappyHorse supports five aspect ratios: 16:9 (landscape), 9:16 (portrait), 1:1 (square), 4:3 (classic), and 3:4 (portrait classic). This covers cinematic, social, and traditional formats out of the box.
HappyHorse uses straightforward per-second pricing: 20 credits per second at 720p and 35 credits per second at 1080p. Total cost equals credits-per-second multiplied by duration. For example, a 5-second 720p clip costs 100 credits, and a 5-second 1080p clip costs 175 credits.
As of April 2026, HappyHorse 1.0 ranks #1 on the Artificial Analysis leaderboard for both text-to-video and image-to-video, ahead of Seedance 2.0 and Wan 2.7. Its single-stream Transformer architecture delivers particularly strong motion stability and prompt adherence compared to dual-branch and MoE-style competitors.
How to Use HappyHorse 1.0 Text to Video
Render short cinematic clips from text in roughly 38 seconds on H100
Write Your Prompt
Describe the scene cinematically: subject, action, camera movement, and lighting. Concrete visual detail produces sharper, more coherent shots.
Pricing · Choose Yours
Flexible AI Pricing
Pay-as-you-go credits or subscription plans. No hidden fees, cancel anytime.
One Time supports crypto payment (BTC, USDT, ETH, 350+)
Monthly billing