UniAll AI SEO/GEO · Happy Horse · 2026-05-30

Happy Horse API overview

Happy Horse is an AI video generation model available through UniAll AI. It supports multiple production workflows: text-to-video, image-to-video, and reference-image-to-video. The public model id for the 720p variant is `happy-horse-720p`.

The model is designed for short-form video generation, creative prototyping, product visuals, social assets, and automated content pipelines where teams need an API-first way to generate video clips from prompts and visual references.

What Happy Horse can generate

Happy Horse supports three main generation modes:

| Mode | Best for | Required input | |---|---|---| | Text to video | Creating a video from a written scene description | `prompt` | | Reference image to video | Animating or extending a single visual reference | `prompt`, `image_url` | | Reference media to video | Generating video with one or more reference images | `prompt` plus optional reference images |

Supported durations range from 3 to 15 seconds. Output aspect ratios include `16:9`, `9:16`, `1:1`, `4:3`, and `3:4`, making the model suitable for landscape, vertical, square, and feed-style video formats.

Happy Horse vs. a basic video generation API

Compared with a minimal text-only video API, Happy Horse is more flexible because it supports both prompt-based and reference-image-based generation. This matters when brand consistency, product appearance, character reference, or visual style continuity is important.

Key comparison points:

• **Input flexibility:** supports text prompts, a single reference image, or multiple reference images.
• **Resolution choice:** supports `720p` and `1080p` output.
• **Async workflow:** requests are handled asynchronously, which is better for video jobs that take longer than standard text or image generation.
• **API suitability:** works well for backend automation, creative tools, marketing systems, and batch content workflows.
• **Output count:** one video is generated per request.

If you only need quick draft clips, 720p is usually the more cost-efficient option. If you need sharper assets for presentations, ads, or post-production, 1080p may be the better fit.

API usage

Happy Horse is available through the UniAll AI video generation endpoint:

```http POST /v1/videos/generations ```

Example request:

```json { "model": "happy-horse-720p", "generation_mode": "text_to_video", "prompt": "A cinematic product reveal, soft studio lighting, smooth camera movement.", "duration": 5, "aspect_ratio": "16:9", "resolution": "720p", "video_count": 1 } ```

Example with a reference image:

```json { "model": "happy-horse-720p", "generation_mode": "reference_image_to_video", "prompt": "Animate the product with a slow camera push-in and premium studio lighting.", "image_url": "https://example.com/reference.png", "duration": 5, "aspect_ratio": "16:9", "resolution": "720p" } ```

Common parameters include:

• `prompt`: required text instruction for the video.
• `duration`: clip length from 3 to 15 seconds.
• `image_url`: optional single reference image for image-to-video.
• `reference_image_urls`: optional list of reference images, up to 9 images.
• `aspect_ratio`: `16:9`, `9:16`, `1:1`, `4:3`, or `3:4`.
• `resolution`: `720p` or `1080p`.

Pricing angle

Happy Horse is billed per second of generated video. On UniAll AI, the listed user pricing is:

| Resolution | Price | |---|---:| | 720p | $0.0952 per second | | 1080p | $0.1904 per second |

For example, a 5-second 720p generation is priced based on 5 seconds of output. A 1080p generation costs more per second because it produces a higher-resolution video.

Failed generations are eligible for refund handling according to the platform configuration, while automatic retry is not enabled for this model.

Who should use Happy Horse

Happy Horse is a strong fit for:

• Marketing teams producing short promotional videos.
• Developers building AI video generation into apps or workflows.
• E-commerce teams creating product motion assets from reference images.
• Agencies prototyping ad concepts and social videos.
• Creative platforms that need an async video API with predictable parameters.

It is less suitable if you need long-form video generation in a single request, multiple videos per request, source video input, or audio-driven generation, because those capabilities are not listed for this model.