Skip to content
Log in

HappyHorse Ranked #1 in T2V and I2V

By Alibaba ATH, inside Renoise. 15-second multi-shot narratives with native audio, outperforming the field.

Try HappyHorse

What HappyHorse does, at a glance

Ranked #1

#1 T2V (Elo 1333) and #1 I2V (Elo 1392) on Artificial Analysis, April 2026.

15s

Up to 15 seconds of multi-shot narrative — enough to tell a complete story.

Native Audio

Dialogue and sound effects generated with the video — native lip-sync across 7 languages.

1080p

Native 1080p at 30 FPS — professional-grade output without extra upscaling.

How to generate videos with HappyHorse

  1. Drag a reference image into the Renoise upload card
    Step 1

    Enter a prompt or image

    Describe the scene in text, or upload an image as the starting frame.

  2. Type a video prompt in Renoise
    Step 2

    Add character references

    Optionally upload up to 9 reference images, addressed in your prompt as character1, character2, etc.

  3. Renoise model selector with HappyHorse 1.0 chosen
    Step 3

    Generate and download

    Pick HappyHorse, hit Generate, and receive a 1080p clip with native audio.

Industry-leading video generation

T2V and I2V in one model

Pure text runs T2V; upload a first-frame image and it switches to I2V automatically. Same interface, same workflow — both modes without switching models.

Native audio, no dubbing

Dialogue, sound effects, and ambience are generated alongside the video in one pass — with native lip-sync across 7 languages including Cantonese, English, French, and Korean.

Multi-reference character fusion

Upload up to 9 reference images and use character1 / character2 in your prompt — the model fuses each character’s appearance and keeps it consistent across the scene.

15-second multi-shot narratives

Generate up to 15 seconds of coherent video with multiple shot cuts in a single pass — natural motion, fluid camera work, and stable temporal consistency.

Choose your plan

Unlock HappyHorse 1.0 and every other model on one Renoise plan.

Starter
$20/mo
Upgrade Plan
1,200©/mo
$1.67 / 100©Generate up to 3,000 images or 150 videos every month.
✓Watermark-free exports
✓20 FacePass Assets
✓Image Models
✓Video Models
Standard
$60/mo
Upgrade Plan
3,600©/mo
$1.67 / 100©Generate up to 9,000 images or 450 videos every month.
✓Watermark-free exports
✓50 FacePass Assets
✓Latest Image Models
GPT Image 2 Nano Banana 2 Nano Banana Pro Midjourney V7
✓Latest Video Models
Seedance 2.0 HappyHorse 1.0
◈ Best Value
Advance
$200/mo
Upgrade Plan
14,000©/mo
$1.43 / 100©Generate up to 35,000 images or 1,750 videos every month.
✓Watermark-free exports
✓Unlimited FacePass Assets
✓Latest SOTA Image Models
GPT Image 2 Nano Banana 2 Nano Banana Pro Midjourney V7
✓Latest SOTA Video Models
Seedance 2.0 HappyHorse 1.0

FAQ

1.Who makes HappyHorse 1.0?

HappyHorse 1.0 is developed by Alibaba’s ATH team. Renoise integrates it alongside Seedance 2.0, Kling 3.0 Omni, Nano Banana 2 / Pro, GPT Image 2, and Midjourney V7 — Renoise does not train video models itself.

2.How is HappyHorse ranked?

HappyHorse ranks #1 in text-to-video (Elo 1333) and #1 in image-to-video (Elo 1392) on Artificial Analysis as of April 2026.

3.Does HappyHorse do both text-to-video and image-to-video?

Yes. Pure text runs T2V; upload a first-frame image and it switches to I2V automatically — one interface, no model-switching.

4.Does HappyHorse generate audio?

Yes. Dialogue, sound effects, and ambience are generated with the video in one pass, with native lip-sync across 7 languages including Cantonese, English, French, and Korean — no separate dubbing.

5.How long can a HappyHorse clip be, and at what quality?

Up to 15 seconds of multi-shot narrative at native 1080p and 30 FPS, with support for up to 9 character reference images.

Make your next video with HappyHorse.

Open Renoise, enter a prompt or upload a reference, and hit Generate.

Try HappyHorse
By Renoise AILast reviewed Models verified: HappyHorse 1.0