happyhorse-1-1 / reference-to-video

HappyHorse-1.1 是一款 AI 视频生成模型。相比 HappyHorse-1.0,它在 T2V、I2V 和 R2V 工作流中提供了更好的提示词理解、更流畅的运动、更强的一致性以及更高质量的输出。

Model Type:
Pricing: 22.5 credits/s ($0.1125) for 720 p or 29 credits/s ($0.145) for 1080 p High-tier top-ups include +10% bonus credits. Effective pricing is approximately 10% lower than the above rates.
Input

A description of the desired elements and visual style for the generated video. Input in any language is supported. The length is limited to 5,000 non-Chinese characters or 2,500 Chinese characters. Content exceeding this limit is automatically truncated. Image referencing: In the prompt, use "[Image 1]" and "[Image 2]" to refer to the corresponding reference image in the media array. The order must be consistent with the order in the media array. When using a reference, specify the object in the image, such as "the woman in a red qipao in [Image 1]".

0/5000

Click to upload or drag and drop

Supported formats: JPEG, PNG, WEBP, JPG Maximum file size: 20MB; Maximum files: 9

The URL of a reference image. Image requirements: 1. Formats: JPEG, JPG, PNG, WEBP. 2. Resolution: The shortest side must be at least 400 pixels. A clear image with a resolution of 720P or higher is recommended. Avoid using images that are too small, blurry, or overly compressed, as this can degrade the output quality. 3. Maximum file size: 20 MB.

The resolution tier of the generated video.

The aspect ratio of the generated video.

The duration of the generated video, in seconds. Value range: An integer from 3 to 15.

Output
output typevideo

README

Complete guide to using happyhorse-1-1/reference-to-video

Happy Horse 1.1 API – 在 Kie.ai 接入 Alibaba HappyHorse-1.1

Original image
HappyHorse-1.1 相比 HappyHorse-1.0 的改进之处