Reference to Video: AI Image-to-Video Generator

Happy Horse 1.1 Reference to Video (1080p) — generate 1080p 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 (1080p) is an advanced video generation tool that conditions output on 1–9 reference images plus a text prompt, creating highly controlled 1080p video with consistent visual elements across frames. By providing multiple reference images, you guide the model's composition, style, and character consistency—resulting in cohesive, professional-quality video. The seed parameter allows deterministic generation for reproducible results, making it ideal for iterative creative work and controlled visual production.

Happy Horse 1.1 Reference-to-Video is perfect for visual directors, production designers, game developers, and teams requiring pixel-perfect consistency across video sequences. Access it through muapi's unified API with straightforward per-generation pricing and full creative control.

1Game cinematic sequences: generate 1080p cutscenes with consistent character and environment styling across multiple reference images
2Animated storyboarding: use keyframe images as references to generate smooth video transitions and scene continuity
3Brand narrative videos: maintain consistent visual identity, color palette, and design language across multi-scene video sequences
4Product evolution visuals: show product transformations or feature progressions using reference images to guide consistency
5Character animation consistency: generate character performances with poses, expressions, and styling guided by reference images
💰

Pricing & Value

Cost analysis

muapiapp$0.90 per generation

Transparent per-generation pricing with no per-image surcharges for reference images. Cost-effective, controlled video generation with full visual consistency guidance.

* 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. Prepare 1–9 reference images (keyframes, mood boards, character designs, environment refs) that establish the visual direction and consistency you want.
  2. Upload or provide URLs for all reference images.
  3. Write a detailed text prompt describing the video narrative, motion, or action (e.g., 'character walks through the door and looks around the room').
  4. Select your aspect ratio.
  5. Specify your desired video duration (in seconds).
  6. Optionally provide a seed value for deterministic/reproducible generation (useful for A/B testing variations).
  7. Submit your request to muapi—Happy Horse 1.1 will generate 1080p video that respects your reference images' visual language while animating according to your prompt.
  8. Download the video.

Common Questions

Frequently asked

What is the cost of Happy Horse 1.1 Reference to Video (1080p)?

Happy Horse 1.1 Reference to Video (1080p) costs $0.90 per generation on muapi. Whether you provide 1 or 9 reference images, the cost remains flat at $0.90 per video. No subscriptions or per-image surcharges.

How do reference images influence the generated video?

Reference images guide the model's understanding of visual style, character appearance, color palette, composition, and design language. The model uses them as constraints while animating according to your text prompt, ensuring consistency across the video.

What does the seed parameter do?

The seed ensures deterministic generation—submitting the same prompt, references, and seed value will produce identical (or nearly identical) videos. This is useful for reproducing results, testing variations, or ensuring consistency across projects.