Docs
Alibaba CloudVideo generation

HappyHorse 1.1 on FluxoKit | AI Video by the Clip

Run HappyHorse 1.1 on FluxoKit to create AI video from text, a still image, or up to nine character references, in 1080p inside one plan with 80+ models.

Updated July 2026

Create AI video from text, a starting image, or several character references with Alibaba Cloud's HappyHorse 1.1. Inside one canvas with Sora 2, Seedance, and 80+ other models. In 1080p. By the clip.

Why Run HappyHorse on FluxoKit

Going direct asks for an Alibaba Cloud developer account, USD billing, English prompts, and the DashScope endpoint. On FluxoKit you open the canvas, describe the scene in plain language, and the Prompt Enhancer tunes the prompt for HappyHorse automatically.

Three HappyHorse 1.1 routes sit beside Seedance, Sora 2, and 80+ other models in one plan. One card, no separate billing.

How to Use

  1. Open the studio at /workflow.
  2. Pick the route. T2V to create from scratch, I2V to animate a still, R2V to follow up to nine character references.
  3. Describe the scene, then adjust duration (3 to 15s), resolution (720P or 1080P), and aspect ratio.
  4. Generate. In seconds you get a clip ready for a paid ad, an organic reel, or a channel intro.

What Changed in 1.1

  • Cheaper 1080p. 1.1 lowers the 1080p per-second rate versus 1.0, so the same 5-second clip costs fewer credits.
  • More aspect ratios. Text to Video and Reference to Video add 4:5, 5:4, 9:21, and 21:9 on top of 16:9, 9:16, 1:1, 4:3, and 3:4.
  • Same routes. Text, image, and reference — no new workflow to learn.

Where HappyHorse Wins

  • Ecommerce. UGC product ads without a human creator or studio.
  • Info products. VSLs with a digital character or cinematic b-roll.
  • Organic social. Vertical 9:16 reels and TikToks from a single brief.
  • Cast consistency. R2V keeps the same character across clips with up to nine references.

Quick Decision

Use HappyHorse 1.1 Text to Video when the starting point is text, Image to Video to animate a photo, and Reference to Video when the clip must follow specific characters or products. Every route runs in one plan, by the clip, with a 30-day satisfaction guarantee on your first paid subscription, subject to the Refund Policy.

Examples

Real generations with HappyHorse 1.1 Text to Video

HappyHorse 1.1 Text to Video generated example 1

Capabilities

Output type

Video

Audio support

Yes

Limits

Generation credits

Depends on the configured run. Review the estimate before generating and the settled charge in history.

Parameters and inputs

Each field below shows what the model accepts and the limits to apply.

11 parameters

Parameters

Duration

duration

Select
Required
No
Default
5

Options

  • 3 (3)
  • 4 (4)
  • 5 (5)
  • 6 (6)
  • 7 (7)
  • 8 (8)
  • 9 (9)
  • 10 (10)
  • 11 (11)
  • 12 (12)
  • 13 (13)
  • 14 (14)
  • 15 (15)

Resolution

resolution

Select
Required
No
Default
1080P

Options

  • 720 P (720P)
  • 1080 P (1080P)

Ratio

ratio

Select
Required
No
Default
16:9

Options

  • 16:9 (16:9)
  • 9:16 (9:16)
  • 1:1 (1:1)
  • 4:3 (4:3)
  • 3:4 (3:4)
  • 4:5 (4:5)
  • 5:4 (5:4)
  • 9:21 (9:21)
  • 21:9 (21:9)

Watermark

watermark

checkbox
Required
No
Default
false

Seed Enabled

seed_enabled

checkbox
Required
No
Default
true

Seed

seed

Number
Required
No
Default
—

Prompt

prompt

Long text
Required
Yes
Default
—

PT BR Speech

Speech Enhancement Mode

speech_enhancement_mode

Select
Required
No
Default
off

Options

  • Auto (auto)
  • Audio Lipsync (audio-lipsync)
  • Audio Pt BR (audio-pt-br)
  • Off (off)

Speech Enhancement Voice ID

speech_enhancement_voice_id

Select
Required
No
Default
—

Speech Enhancement Duration Policy

speech_enhancement_duration_policy

Select
Required
No
Default
auto_fit_or_reject

Options

  • Auto Fit Or Reject (auto_fit_or_reject)
  • Locked Duration Reject (locked_duration_reject)

Speech Enhancement Lipsync Model

speech_enhancement_lipsync_model

Select
Required
No
Default
fal-ai/sync-lipsync/v3

Options

  • Fal Ai/sync Lipsync/v3 (fal-ai/sync-lipsync/v3)
  • Fal Ai/sync Lipsync/v2 (fal-ai/sync-lipsync/v2)
  • Fal Ai/sync Lipsync (fal-ai/sync-lipsync)

Frequently asked questions

What is HappyHorse?

HappyHorse is Alibaba Cloud's (DashScope) family of video models on FluxoKit. Version 1.1 generates video from text, animates a starting image, or follows several reference images, with 720P or 1080P output from 3 to 15 seconds.

Which HappyHorse 1.1 variants run on FluxoKit?

Three active routes: HappyHorse 1.1 Text to Video, Image to Video, and Reference to Video with up to nine images mapped by character1, character2, and so on. You pick the right route in the canvas.

What changed between HappyHorse 1.1 and 1.0?

1.1 keeps the same routes and lowers the 1080p rate versus 1.0, so a 5-second 1080p clip costs less in credits. Text to Video and Reference to Video also open extra aspect ratios such as 4:5, 5:4, 9:21, and 21:9.

How much does HappyHorse cost on FluxoKit?

By the clip inside your FluxoKit plan, with a 15% margin over provider cost already baked into the credit price. No per-model subscription and no separate Alibaba Cloud billing.

Next step

Use HappyHorse 1.1 Text to Video without signing up for Alibaba Cloud.

90+ AIs in one studio. Live USD checkout is processed through Stripe, with no API key to manage.

Related content