Skip to main content

Happy Horse 1.0 Text-to-Video

AI Generated

Generated on PixelDojo with Happy Horse 1.0 Text-to-Video. Produced by PixelDojo's generation pipeline.

Cancel anytimeCommercial-use license50+ AI models

Happy Horse 1.0 Text-to-Video costs 12 credits for the cheapest clip we could run, 3 seconds at 720p, and it took about 4 minutes from request to finished file on August 26, 2026. The mode starts from nothing but a text prompt, no reference image required. This page covers the real charge, the measured turnaround, a real duration limit the documentation does not fully explain, and what the output actually looks like frame by frame.

The 12 credit clip, second attempt, first result kept

Every example below was produced on PixelDojo. Hover to see the prompt.

A paper-craft fox walks through a folded-paper forest, handmade stop-motion style, gentle camera push

Happy Horse 1.0 Text-to-Video

What text-to-video mode gets you

No reference image needed

We sent only a prompt, a paper-craft fox walking through a folded-paper forest, stop-motion style. The mode is meant for scenes you can fully describe in words rather than ones anchored to a photo.

The documented duration floor is wrong in practice

The tool's own schema allows a duration of 2 seconds. We tried 2 first and the request failed instantly: 'duration must be between 3 and 15 seconds, got 2.' The real floor, enforced by the provider, is 3.

720p or 1080p, priced per second

720p runs 4 credits per second, 1080p runs 6. At the 3 second floor that is 12 credits or 18 credits, before you touch duration.

Two engine versions

Version 1.0 is the default for this mode and what this run used. Version 1.1 is available at a lower per-second rate by passing version explicitly.

Five aspect ratios on the base schema

16:9, 9:16, 1:1, 4:3, and 3:4 are all documented options, though this specific text-to-video variant fixes mode server-side rather than letting you toggle it.

What came back

A 1280 by 720, 24 frames per second H.264 clip, about 3 seconds of playable video, 2.2 megabytes. Measured directly with ffprobe against the downloaded file.

One text prompt, no image, one run on August 26, 2026: 12 credits, about 4 minutes, a 1280 by 720 clip.

Why Choose Pixel Dojo for Happy Horse 1.0 Text-to-Video

Professional-quality results with cutting-edge AI technology

12 credits, no source image

Nothing to prepare beyond a text prompt. The 3 second minimum at 720p is 12 credits flat.

About 4 minutes, measured

240 seconds from submission to a finished file on August 26, 2026, after correcting our duration to the real 3 second floor.

A real duration correction, saved for you

We hit the 2 second rejection so this page can tell you the true minimum before you spend a credit finding out.

How It Works

How we ran it, so you can repeat it:

1

Write a scene you do not need a photo for

Our prompt described a paper-craft fox and a folded-paper forest, nothing that required a reference image.

2

Use 3 seconds as your real floor

We first tried duration 2 and it failed instantly against the provider, not our schema. 3 is the number that actually runs.

3

Run it in the app or over the API

Generate from the Happy Horse page's text-to-video mode, or POST to /api/v1/models/happyhorse-1.0-t2v/run. Ours took about 4 minutes and charged 12 credits.

Write your own scene

Loved by creators on PixelDojo

Real feedback from people using PixelDojo, pulled from our in-product surveys.

Creative freedom, range of tools and options.
Verified PixelDojo creator
I love the training feature
Verified PixelDojo creator
the quality is the best
Verified PixelDojo creator
All the tools needed in one dashboard
Verified PixelDojo creator
Very fair and very broad in tools.
Verified PixelDojo creator
Accurate results
Verified PixelDojo creator

Common Questions

Everything you need to know about Happy Horse 1.0 Text-to-Video

What does Happy Horse Text-to-Video cost?

4 credits per second at 720p, 6 at 1080p, with a real 3 second minimum. The cheapest clip is 12 credits.

How fast is Happy Horse Text-to-Video?

About 4 minutes in our August 26, 2026 run, measured from submission to the finished file. Turnaround depends on Alibaba's queue at request time.

Can I really request a 2 second clip?

The schema accepts a duration of 2 in the request body, but the provider rejects it with a clear error. Use 3 as the real floor and you will not lose the request.

How do I call it from the API?

POST to /api/v1/models/happyhorse-1.0-t2v/run with your API key and a prompt. Add resolution, duration, and version to control price and quality.

How is this different from the Image-to-Video mode?

Image-to-Video needs a first frame image and animates from it. Text-to-Video needs no image at all, only a prompt describing the whole scene.

How is this different from Reference?

Reference takes one or more subject images and drives them through a scene the prompt describes. Text-to-Video has no image input at all.

Compare it against every other video model

Ready to Create Amazing Happy Horse 1.0 Text-to-Video Images?

Join thousands of creators using AI to bring their ideas to life