Reference to Video: AI Image-to-Video Generator

Happy Horse 1.1 Reference to Video (720p) — generate 720p video conditioned on 1-9 reference images plus a text prompt.

📝

Overview

About this model

Updated Jul 16, 2026

Happy Horse 1.1 Reference to Video (720p) is a cost-optimized version that conditions video generation on 1–9 reference images plus a text prompt, producing 720p video with consistent visual elements. Provide reference images to guide style, character, and composition, and Happy Horse generates smooth video that honors those visual constraints. The seed parameter enables reproducible generation, making it perfect for iterative workflows and high-volume content production where 720p delivers excellent visual quality.

Happy Horse 1.1 Reference-to-Video (720p) is ideal for teams scaling video production, game developers on budget, and content creators who need reference-guided consistency without premium resolution overhead. Available through muapi with transparent per-generation pricing and no subscriptions.

1Animated storyboarding on budget: use keyframe references to generate 720p smooth video transitions and scene flow across multiple shots
2Character performance capture: guide character animations with pose and expression references to ensure consistent performance across video sequences
3Marketing campaign consistency: produce multiple video variations guided by brand style references while maintaining visual cohesion
4Game asset variation: generate multiple animation variants of game scenes guided by visual style references
5Rapid prototyping: quickly iterate on video concepts using reference images to establish visual direction before committing to high-resolution production
💰

Pricing & Value

Cost analysis

muapiapp$0.70 per generation

Cost-effective, transparent per-generation pricing with no per-image surcharges. Scale reference-guided video production affordably without subscriptions.

* Competitor pricing is estimated based on similar model architectures and usage tiers.

⚙️

Technical Details

Configuration schema

Promptstring

Text description of the desired video. Up to 5,000 characters.

Default ValuePlace @image1 inside @image2 running across countertops while giant cooking disasters happen everywhere. Exploding soup pots, flying vegetables, and fire bursts create chaos.
Reference Imagesarray

1-9 reference image URLs. JPEG/PNG/WEBP, >=400px shortest side, <=10 MB each.

Default Valuehttps://d3adwkbyhxyrtq.cloudfront.net/webassets/videomodels/happy-horse-1-reference-to-video-1080p-1.jpg
Aspect RatioEnum (5 options)

Output video aspect ratio.

Default Value16:9
Duration (seconds)int

Video duration in seconds.

Default Value5
Seedint

Optional random seed for reproducibility (0-2147483647).

Default Value0
📖

Implementation Guide

Developer documentation

  1. Gather 1–9 reference images that establish the visual style, color palette, character design, or scene composition you want.
  2. Upload or link all reference images.
  3. Write a detailed text prompt describing the video action or narrative (e.g., 'character running toward camera with determined expression').
  4. Select your desired aspect ratio.
  5. Specify the video duration in seconds.
  6. Optionally provide a seed value for deterministic reproduction of results.
  7. Submit your request to muapi—Happy Horse 1.1 will generate 720p video aligned with your visual references.
  8. Download the video file.

Common Questions

Frequently asked

How much does Happy Horse 1.1 Reference to Video (720p) cost?

Happy Horse 1.1 Reference to Video (720p) costs $0.70 per generation on muapi. This flat rate applies regardless of how many reference images you provide (1–9) or video duration. No subscriptions or additional charges.

How many reference images should I provide?

You can provide 1–9 reference images. More references give the model stronger guidance on visual consistency, but even a single reference image can meaningfully constrain the output. Experiment to find the right balance for your use case.

Can I reuse the same reference images for multiple video generations?

Yes, absolutely. Using consistent reference images across multiple requests ensures visual cohesion across your video library. Each new prompt/generation incurs a separate $0.70 charge.