Skip to main content
$1 on usClaim your $1 + trialTerms apply
ai
by HappyHorse

HappyHorse Video Edit — AI Video Generator

HappyHorse Video Edit is available on Artifio.ai as part of our unified AI workspace. Powered by HappyHorse. Starting at about $0.140 per second.

From $0.140 / secEstimated ~360s; not a measured benchmark

Start with HappyHorse Video Edit

Review settings and cost in the editor before generating. Up to 240 characters here; you can edit your brief there. Your brief stays in this browser tab during the handoff. You may be asked to sign in first.

Open the full editor instead
Open full editorBrowse all models
HappyHorse Video Edit logo

HappyHorse Video Edit pricing

These prices are calculated from the current model settings. Each row describes the configuration used for that price.

Current configuration prices for HappyHorse Video Edit
SettingsPer generation
Resolution: 720p · 5 seconds$0.700
Resolution: 1080p · 5 seconds$1.200

Review the estimate for your selected settings before submitting. Compare model pricing

About HappyHorse Video Edit

HappyHorse 1.0 is a video generation and editing model from the innovation unit of Alibaba Token Hub (ATH), the AI business group Alibaba formed in March 2026 under Zhang Di, who rejoined the company in November 2025. The model debuted anonymously on the Artificial Analysis video arena in early April 2026, topped the blind text-to-video and image-to-video rankings ahead of ByteDance's Seedance 2.0, and was confirmed as Alibaba's on April 10. A limited beta opened in late April through the HappyHorse website, the Qwen app, and an API on Alibaba Cloud Model Studio.

This is the editing variant, covering the two edit functions in Alibaba's launch announcement: video-to-video (V2V), which modifies an existing clip while preserving its original structure and motion, and subject-and-video-to-video (SV2V), which replaces or inserts a subject from a reference image while keeping the source video's motion, composition, and unaffected regions intact. On Artifio it runs beside 100+ other models in one workspace, paid per generation from a single wallet.

Features

  • Video-to-video editing rewrites the look of an existing clip while preserving its original structure and motion.
  • Alibaba's published V2V example restyles live footage into a blocky voxel game world based on a reference image, with movements, character actions, and the camera track kept unchanged.
  • Subject-and-video-to-video replaces or inserts a specific subject from a reference image while preserving the original video's motion, composition, and untouched regions.
  • Edits are driven by a text instruction, optionally combined with a style or subject reference image.
  • Part of the HappyHorse 1.0 family, which generates synchronized audio and up to 15 seconds of 1080p multi-shot video.

What people use it for

  • Restyling existing footage into a new visual treatment without reshooting or manual rotoscoping.
  • Swapping a product or character into already-shot video for advertising variants.
  • Adapting one master clip into several brand or market versions while keeping the camera work identical.
  • Stylized versions of user-generated or archival clips for social campaigns.

Reported strengths

  • Structure and motion preservation is the documented core of the edit modes, so the timing and choreography of the source clip survive the transformation.
  • Combines subject replacement and full restyling in one model instead of separate tools.
  • Comes from the model family that ranked first in both generation categories on the Artificial Analysis arena at its April 2026 debut.

Reported limitations

  • The editing functions are documented in a single launch announcement with one published example per mode; Alibaba gives no length or resolution specifics for edited output.
  • The Artificial Analysis rankings behind the model's reputation measure generation, and no public benchmark covers its editing quality.
  • Access is a limited beta as of mid-2026, and Alibaba describes the model as still under development.
  • Guidance on failure cases, such as heavy occlusion of the replaced subject or long continuous takes, has not been published.

Sources

  1. Alibaba Rolls Out HappyHorse 1.0 in Limited Beta (Alibaba Cloud)
  2. Alibaba's HappyHorse tops Seedance, offering glimpse into China's race for AI talent (South China Morning Post)
  3. Alibaba revealed as creator of AI video generation model 'HappyHorse-1.0' (CNBC)

HappyHorse Video Edit FAQ

  • What is HappyHorse Video Edit?

    HappyHorse Video Edit is an AI model (video to video) available on Artifio.ai through HappyHorse. You can run it in our workspace from a single shared wallet and download your outputs.

  • How much does HappyHorse Video Edit cost on Artifio?

    HappyHorse Video Edit has a starting estimate of $0.140 per second on Artifio.ai. Review the estimate for your settings in the workspace before confirming. Usage-billed models reconcile the final charge after generation.

  • How do I use HappyHorse Video Edit on Artifio?

    Click Generate Now to open the workspace at /create/happyhorse-video-edit. Fill in the form fields, review the live cost estimate, and run your generation.

  • What kind of outputs does HappyHorse Video Edit produce?

    HappyHorse Video Edit is configured for video to video workflows in the AI content category. See the technical parameters below for supported inputs and options.

  • Can I try HappyHorse Video Edit for free?

    Sign up free, top up your wallet from $1, and you can run HappyHorse Video Edit pay-as-you-go without a separate subscription for this model.

Try HappyHorse Video Edit on Artifio

Open the workspace with this model pre-selected. Review your prompt, settings, and cost before you generate.

Generate Now