fal Launches HappyHorse-1.0, the #1-Ranked AI Video Model, as Official API Partner
Happy Horse, a new state of the art video model is now available April 27th via fal's generative media cloud for developers and enterprises
SAN FRANCISCO, April 27, 2026 /PRNewswire/ -- On April 27, 2026 fal launched developer and enterprise access to HappyHorse-1.0, the AI video model holding the #1 Elo ranking on the Artificial Analysis Video Arena in both Text-to-Video and Image-to-Video. fal is among the first official API providers for the model, giving developers immediate access through its generative media platform on the day of launch.
Access The HappyHorse-1.0 API & Happy Horse Playground Website
Developers and enterprise customers can access HappyHorse through four API endpoints on fal: image-to-video, reference-to-video, text-to-video, and video-edit. fal offers developer-friendly python and javascript SDKs to reduce manual REST integration time. fal's API endpoint actually exposes the model's unified multimodal capabilities (lip-sync and Foley sounds) rather than just silent video. With fal you have the option to pick between 720p or 1080p resolution and it supports formats like 16:9, 9:16, 1:1, 4:3, 3:4 to ensure your content fits various social platforms. fal also guarantees full commercial rights for all generated outputs. fal's lightning inference speed is optimized with the latest AI infrastructure technology, making it one of the fastest ways to generate content via the HappyHorse-1.0 API.
Official Happy Horse API Endpoints
You can access the official API via fal with 4 API endpoints. You can get an API key from the API Keys page in your dashboard at fal.ai:
About HappyHorse-1.0
HappyHorse-1.0, built by Alibaba's Taotian Future Life Lab under the Alibaba Token Hub division, is the first video model to reach the top of the Artificial Analysis leaderboard rankings based on blind human preference votes: users compare two unlabeled clips and pick the better one, with no knowledge of which model produced either. The model earned an Elo of 1333 in Text-to-Video and 1392 in Image-to-Video (no audio), placing it above every other video generation model currently benchmarked.
HappyHorse-1.0 was led by Zhang Di, a 15-year AI industry veteran who previously served as VP at Kuaishou and technical architect of Kling AI, before rejoining Alibaba in late 2025. A fal spokesperson noted that "HappyHorse is known for producing 1080p video with synced audio, strong lighting, and realistic, emotional, and consistent detail."
The model's core architecture is a unified 40-layer self-attention Transformer that generates video and audio jointly in a single forward pass, with no cross-attention modules and no separate audio post-processing step. The result is synchronized audiovisual output with native lip-sync support across seven languages: English, Mandarin, Cantonese, Japanese, Korean, German, and French. The team claims approximately 38-second generation time for 1080p output on a single NVIDIA H100 GPU.
Happy Horse Use Cases
The model supports use cases ranging from product promos and social content to multi-shot sequences with consistent character identity across frames. Camera direction fidelity, including cues like "slow dolly push-in," "overhead crane shot," and "breeze versus strong wind," are some examples of key differentiators for developers building video production workflows. To get started with using Happy Horse, visit fal.
About fal: fal is a generative media platform for developers and enterprises, specializing in high-performance inference and fine-tuning across image, video, audio, and 3D models. It provides low-latency APIs for state-of-the-art models like HappyHorse-1.0, Seedance 2.0, Nano Banana, and Flux, serving industries such as gaming, e-commerce, and creative production. fal has been among the first official API providers for major model releases across the generative media landscape. The platform supports both self-serve and enterprise customers with immediate model access, high-throughput infrastructure, and dedicated ML engineering support.
SOURCE fal
Share this article