Does HappyHorse 1.1 support reference-to-video?

Yes. HappyHorse 1.1 accepts up to 9 reference images for reference-to-video generation.

Does HappyHorse 1.1 support text-to-video?

Yes. HappyHorse 1.1 generates video directly from a text prompt.

Does HappyHorse 1.1 support image-to-video?

Yes. Supply a single start frame for image-to-video generation.

What durations and resolutions are available?

HappyHorse 1.1 supports 3 to 15 second clips in 720p and 1080p.

How much does HappyHorse 1.1 cost?

Pricing is 19 gold per second at 720p. A 5-second 720p clip costs 95 gold. 1080p costs 26 gold per second.

CharGen

HappyHorse 1.1 Video Generator

Text-to-video, image-to-video, and reference-to-video generation with up to 9 reference images. 3 to 15 second clips at 720p or 1080p.

Key Features

Reference-to-video with up to 9 reference images for multi-image guided generation

Supports Text-to-Video, Image-to-Video, and Reference-to-Video in one model

Flexible 3s to 15s durations for quick tests, social clips, and longer scene beats

720p and 1080p output for cost-efficient iteration and high-quality finals

Five aspect ratios support landscape, portrait, square, and classic frame formats

HappyHorse 1.1 Specifications

Model NameHappyHorse 1.1

Input ModesText-to-Video, Image-to-Video, Reference-to-Video

Image Inputs1 start frame (i2v) or up to 9 reference images (ref2v)

Resolutions720p, 1080p

Durations3s to 15s

Aspect Ratios16:9, 9:16, 1:1, 3:4, 4:3

Pricing95 gold per 5s at 720p (19 gold/s); 1080p at 26 gold/s

Best Use Cases for HappyHorse 1.1

Multi-Reference Scene Building

Supply several reference images to guide a scene with consistent characters, props, and environments.

Character Reveals

Animate a single character image into a short introduction or hero moment.

Text-to-Video Previews

Generate quick cinematic previews from a text prompt before committing to a final high-resolution clip.

About HappyHorse 1.1

HappyHorse 1.1 adds reference-to-video support to the HappyHorse line, allowing up to 9 reference images for guided multi-image generation. It retains the full text-to-video and image-to-video modes from 1.0 and adds per-second gold pricing for transparent cost scaling across any duration from 3 to 15 seconds.