Model reference · Updated July 2026

HappyHorse-1.0 Specs & Architecture

Everything published about how the model works, split into what is verified (observable via the hosted API) and what is reported (team disclosures awaiting the official repo).

Architecture (reported)

From team disclosures and technical press — unaudited until the official repo ships.

Parameters~15 billion
BackboneSingle-stream transformer, 40 layers, unified self-attention (no dedicated cross-attention)
Layer layoutFirst 4 + last 4 layers use modality-specific projections; middle 32 share parameters across modalities
ModalitiesText, image, video, and audio tokens processed in one sequence — audio and video generated jointly in a single forward pass
Sampling8 steps via DMD-2 distillation; no classifier-free guidance required
CompilerMagiCompiler full-graph optimization
ExtrasSeparate super-resolution module for upscaling to 1080p

Performance (reported)

1080p generation~38 seconds for a 5-second clip on one H100 80GB
Draft speed~2 seconds for a 5-second clip at 256p
Native resolutionUp to 1080p, no upscaler required

Capabilities (verified via hosted API)

ModesText-to-video, image-to-video, video editing, reference-to-video
Clip length3–15 seconds
Aspect ratios16:9, 9:16, 1:1, 4:3, 3:4
AudioJoint audio-video generation with native lip-sync in 7 languages: Mandarin, Cantonese, English, Japanese, Korean, German, French
Styles50+ (cinematic, anime, documentary, fashion, …)

Benchmarks

Artificial Analysis Video Arena#1 in both text-to-video and image-to-video (no-audio) at April 2026 debut — the only model to top both simultaneously
vs Seedance 2.0~60 Elo ahead without audio; behind or tied with audio enabled

Team & provenance

DeveloperAlibaba — Taotian Group's model lab
LeadZhang Di — 15-year AI veteran, ex-VP at Kuaishou, technical architect of Kling AI; rejoined Alibaba in late 2025
Public debutApril 7, 2026 (anonymous arena entry)
Attribution confirmedApril 10, 2026
Planning to run it yourself? See the self-hosting guide for hardware requirements, or check what is verifiably released today.