Skip to main content
AI video model
HappyHorse
HappyHorse

HappyHorse 1.1

HappyHorse 1.1 routes by image count: no image selects text mode, 1 image selects first-frame image-to-video, and 2–9 images select reference mode. All three modes share the same resolutions, durations, and per-second rates.

Workflow
Text / single image / multiple images
Output
720p / 1080p
Duration
3–15 seconds
Credits
68–435
Selects among three workflows from 0 / 1 / 2–9 images
Applies strict prompt limits to Chinese and other text
Prices 720p / 1080p by output second
Validates true image format and dimensions before reserving credits
30-second overview
HappyHorse
68–435 credits
What it does best
A short-video entry point whose three branches are selected by image count.
Best for
A good fit for animating one key frame or using multiple character, wardrobe, and setting images as references.
Popular searches
How do I use HappyHorse 1.1?How much does HappyHorse 1.1 cost?How many reference images does HappyHorse 1.1 support?

At a glance

What is this model like?

Single-image mode requires both sides of the image to be at least 300 pixels, with an aspect ratio from 0.4–2.5. Reference mode requires a minimum short edge of 400 pixels. Signed upload metadata binds the true format and dimensions, and prompts or media outside the contract are rejected before credits are reserved.

What it does best
A short-video entry point whose three branches are selected by image count.
Best for
A good fit for animating one key frame or using multiple character, wardrobe, and setting images as references.
Why use it on Kyeo AI
Kyeo never silently truncates the prompt and validates image geometry, mode, and dynamic pricing before task creation.

Key facts

Quickly assess whether this model fits your use case.

Single-image mode
Exactly 1 image
Reference mode
2–9 images
Image formats
JPEG / PNG / WebP
Prompt
Chinese and other text use different limits

Also known as

The same model may appear under different names across documentation and community discussions; this list keeps them easy to search and compare.

HappyHorse V1.1
HappyHorse 1.1 image to video
HappyHorse 1.1 multi-image video

Common questions

These practical questions focus on the task, input conditions, and result requirements you should confirm before choosing.

How do I use HappyHorse 1.1?
How much does HappyHorse 1.1 cost?
How many reference images does HappyHorse 1.1 support?
Does HappyHorse 1.1 support Chinese prompts?
How do HappyHorse 1.1 720p and 1080p prices differ?

Selection guide

Use these decision points when choosing a model.

1
Use one image for first-frame guidance

With only one primary visual, the system selects single-image mode and does not send the reference-mode aspect-ratio field.

2
Use two or more images as element references

In reference mode, identify the roles of people, clothing, and settings by image order in the prompt.

3
Switch models for video or audio references

HappyHorse 1.1 does not currently accept reference video or audio. Compare MiniMax H3 or Seedance when those media types are required.

Popular comparisons

Compare common alternatives on the same task to clarify differences in inputs, controls, and cost.

How do the reference-media types of HappyHorse 1.1 and MiniMax H3 differ?
How do the image-to-video limits of HappyHorse 1.1 and Kling 3.0 Turbo compare?

Model comparison

Compare the current model with alternatives at a glance.

Input options
HappyHorse 1.1
Text, 1 first-frame image, or 2–9 reference images
Kling 3.0 Turbo
Text or 1 image
MiniMax H3
Text, first/last frames, or multimodal references

Practical usage insights

Practical guidance based on public sources, current on-site limits, and representative tasks.

No silent truncation produces a controlled failure

Prompts over the language-specific limit are rejected before task creation, so users are not led to believe that the entire input was sent.

Reference-image count does not change the current rate

The three branches share a per-second rate, though additional media can still increase conflicts and iteration cost.

Capabilities

Text-to-video

Create a video from text using nine aspect ratios, a resolution, and a duration.

Single-image-to-video

Use one valid image as the first-frame visual input.

Multi-image reference

Use 2–9 images to define characters, objects, and settings.

Use cases

Character showcase clip

Generate motion and camera changes from one character image.

Wardrobe and setting combination

Use separate images for the person, clothing, and environment.

Multi-format ad draft

Compare landscape, portrait, and square composition in text or reference mode.

Prompt tips

Refer to images by order

Use labels such as “image 1” and “image 2” to give every reference a distinct role.

Keep Chinese prompts within 2,500 characters

Do not rely on public source truncation; manually shorten overlong content before submission.

Name what must stay fixed in single-image mode

List the appearance, product branding, and compositional elements that should not change.

Why choose it

Image count makes the three input modes intuitive.
Supports up to 9 reference images.
Offers nine common output aspect ratios.
Kyeo does not silently truncate prompts.

What to know first

No reference video or reference audio.
Single-image mode does not expose a separate aspect-ratio field.
Chinese prompts have a lower limit than other text.
More reference images do not guarantee better consistency.

Adjustable parameters

Quickly assess whether this model fits your use case.

Resolution
resolution
Optional
Parameter type: Select
Default: 1080p
720p
1080p
Video duration
duration
Optional
Parameter type: Integer
Default: 5 seconds
3–15 seconds
Text / reference-mode aspect ratio
aspect_ratio
Optional
Parameter type: Select
Default: 16:9
16:9
9:16
1:1
4:3
3:4
4:5
5:4
9:21
21:9

Credit usage

68–435 credits

Text, single-image, and multi-image-reference modes share the same rates: 720p costs 22.5 credits per output second, while 1080p costs 29. Kyeo rounds the request total up and settles against actual consumption after completion.

Budget tip

Before batch generation, run an A/B test with the same assets across the current model and alternatives to validate quality and avoid wasting credits.

FAQ

Related models

Compare these similar candidates before deciding.

Kling 3.0 Turbo

Kling 3.0 Turbo targets 3–15-second video generation. It uses text mode when no image is uploaded and switches to image-to-video when one valid image is supplied. Resolution and duration directly determine the preauthorization amount.

AI video model
54–338 credits

MiniMax H3

MiniMax H3 offers 768P and 2K output with text, first/last-frame, and image/video/audio reference scenes. Reference-video duration and every input image from image 6 onward affect pre-task authorization.

AI video model
64–812 credits

Seedance 2.0 Mini

Seedance 2.0 Mini combines text, first/last-frame, and multimodal-reference generation in one entry point. Reference video enters the pre-task pricing formula, so both media duration and output duration must be verified before task creation.

AI video model
16–150 credits

Sources

Content is based on model documentation, feature references, and the settings available on Kyeo AI.

Source note

Explore HappyHorse 1.1: 720p or 1080p, 3–15 seconds, text, single-image, or 2–9-image reference generation, 68–435 credits, and image limits. Text, single-image, and multi-image-reference modes share the same rates: 720p costs 22.5 credits per output second, while 1080p costs 29. Kyeo rounds the request total up and settles against actual consumption after completion.

Last updated: 2026-08-28
HappyHorse V1.1 current interface notes
Platform

Used to check the input modes, visible controls, media limits, and availability of the version currently connected to this site. The page and workbench show the actual options.