HappyHorse 1.0 — text-to-video generation on RunComfy. HappyHorse 1.0 is currently #1 on Artificial Analysis Video Arena and produces native 1080p video with in-pass synchronized audio (dialogue, ambient, Foley) and multi-shot character consistency. This skill calls HappyHorse 1.0 through the RunComfy CLI: `runcomfy run happyhorse/happyhorse-1-0/text-to-video`. Triggers on "happyhorse", "happy horse", "happyhorse 1.0", "happyhorse video", "happyhorse t2v", or any explicit ask to generate video with HappyHorse.
Design & media
HiAPI HappyHorse 1.0 Video
Try itUse when a user asks to create text-to-video with HappyHorse 1.0, HiAPI HappyHorse 1.0, or this specific skill.
What it does
Use when a user asks to create text-to-video with HappyHorse 1.0, HiAPI HappyHorse 1.0, or this specific skill.
The skill document
HiAPI HappyHorse 1.0 Video
Use this skill when the user wants text-to-video generation through HiAPI's happyhorse-1-0 model.
Requirements
- Node.js 18 or newer.
HIAPI_API_KEYmust be set in the environment.HIAPI_BASE_URLis optional and defaults tohttps://api.hiapi.ai.
Important links:
- Get API key: https://www.hiapi.ai/en/register
- Pricing: https://www.hiapi.ai/en/pricing
- Docs: https://docs.hiapi.ai
Never invent a video result. If the API call fails, report the status code, compact error message, and the next action from the Error Guidance section.
Generate A Video
Run:
node scripts/hiapi-happyhorse-1-video.mjs \
--prompt "A wuxia swordswoman leaps across temple rooftops at dusk, silk robes flowing in the wind" \
--seconds 5 \
--resolution 1080p \
--ratio 16:9
Supported durations:
- any integer from
3to15
Supported resolutions:
720p1080p
Supported aspect ratios (--ratio, legacy alias --size):
16:99:161:14:33:4
Optional seed:
- integer from
0to2147483647 - omit it when the user does not request reproducibility
The script creates a video task, polls until it finishes, downloads the video to outputs/ when possible, and prints JSON with the saved file path or remote URL.
API Contract
This skill calls:
POST /v1/tasks
GET /v1/tasks/{taskId}
with:
{
"model": "happyhorse-1-0",
"input": {
"prompt": "...",
"duration": 5,
"resolution": "1080p",
"aspect_ratio": "16:9",
"seed": 12345
}
}
HappyHorse 1.0 is text-to-video. Do not send image inputs to this model. The CLI maps --seconds to input.duration and --ratio (legacy alias --size) to input.aspect_ratio. Use --seed only when the user requests reproducibility.
For details, read references/api.md and references/output.md.
Check Configuration
Run:
node scripts/check-config.mjs
Use --live only when you want to verify that the configured key can reach the HiAPI pricing endpoint.
Error Guidance
- Missing
HIAPI_API_KEY: tell the user to create or copy a key from https://www.hiapi.ai/en/register and export it. - HTTP
401or403: tell the user to verify the HiAPI API key. - HTTP
402, HTTP403with quota text, insufficient balance, credits, quota, or payment errors: tell the user to add credits or check billing at https://www.hiapi.ai/en/dashboard and review pricing at https://www.hiapi.ai/en/pricing. - HTTP
400: tell the user to check duration, resolution, aspect_ratio, and seed. - HTTP
429: tell the user to wait and retry or reduce concurrent video generations. - Task failure: ask the user to try a clearer prompt.
- Timeout: explain that video generation may still be running and the user can retry later.
- Optional skill update notice: tell the user the printed update command can be run later.
- Required skill update notice: tell the user the printed update command must be run before using this skill again.
Related skills
Use APIDot for Happy Horse 1.1 API workflows, including Alibaba Happy Horse 1.1, audio-synced short video, text-to-video API, image-to-video API, reference-t...
Turn a brief, link, or research topic into a controlled, source-grounded video prompt that runs on HiAPI Seedance 2.0 or HappyHorse 1.0. Use when a user asks...
Turn rough Happy Horse use cases into structured video workflow plans, prompt packs, and revision loops. Use when the user wants better text-to-video, image-...
Use APIDot for Happy Horse API workflows, including Alibaba Happy Horse video generation, text-to-video API, image-to-video API, reference-to-video API, vide...
Happy Horse 1.0 video model — one model covers text-to-video (t2v), first-frame-to-video (i2v), reference-to-video (r2v), and video editing (edit). The selected mode is automatically routed to the matching sub-model. Happy Horse 1.0 视频模型,一站式覆盖文生视频(t2v)、首帧生视频(i2v)、参考图生视频(r2v)与视频编辑(edit):根据所选模式自动路由到对应子模型。