Loading...
Loading...
在RunComfy上使用HappyHorse 1.0生成文本转视频。本文档介绍了HappyHorse 1.0的优势(在Artificial Analysis Video Arena排名第一、原生1080p分辨率并支持生成过程同步音频、多镜头角色一致性、支持6种语言提示词)、时长/宽高比/分辨率配置规则,以及何时转而使用Wan 2.7/Seedance 2/LTX 2。通过本地RunComfy CLI调用`runcomfy run happyhorse/happyhorse-1-0/text-to-video`。当触发词为“happyhorse”、“happy horse”、“happyhorse 1.0”、“happyhorse video”或任何明确要求使用该模型生成视频的请求时执行。
npx skill4agent add prime-skills/runcomfy-agent-skills happyhorse-1-0npx skills add agentspace-so/runcomfy-skills --skill happyhorse-1-0 -g| 你的需求 | 推荐模型 |
|---|---|
| 具备角色/服装一致性的多镜头故事 | HappyHorse 1.0 |
| 生成过程中同步输出原生音频 | HappyHorse 1.0 |
| 当前盲选排名第一的视频生成模型 | HappyHorse 1.0 |
| 带精准唇形同步的对话+参考视频 | Seedance 2.0 Pro |
| 精细运动控制+多参考条件输入 | Wan 2.7 |
| 超快速迭代(每帧耗时不到1秒) | LTX 2 |
| 现有素材的电影级运动编辑 | Kling Video O1 |
npm i -g @runcomfy/cliruncomfy loginRUNCOMFY_TOKEN=<token>runcomfy loginhappyhorse/happyhorse-1-0/text-to-video| 字段 | 类型 | 是否必填 | 默认值 | 说明 |
|---|---|---|---|---|
| 字符串 | 是 | — | 最多2500字符,支持6种语言(中/英/日/韩/德/法) |
| 枚举 | 否 | | 仅支持 |
| 枚举 | 否 | | 可选 |
| 整数 | 否 | 5 | 取值范围3-15秒 |
| 整数 | 否 | 0 | 取值范围0到2^31-1,重复使用可对比不同变体 |
| 布尔值 | 否 | true | 是否添加服务商水印 |
runcomfy run happyhorse/happyhorse-1-0/text-to-video \
--input '{"prompt": "<用户提示词>"}' \
--output-dir <绝对路径>runcomfy run happyhorse/happyhorse-1-0/text-to-video \
--input '{
"prompt": "<用户提示词>",
"aspect_ratio": "9:16",
"duration": 8,
"watermark": false
}' \
--output-dir <绝对路径>runcomfy run happyhorse/happyhorse-1-0/text-to-video \
--input '{"prompt": "<用户提示词>", "resolution": "720P", "duration": 3}' \
--output-dir <绝对路径>*.runcomfy.net*.runcomfy.com--output-dir"Wide shot. ...""Tracking shot. ...""Locked tripod, low angle. ...""35mm anamorphic""shallow DOF""crushed shadows""Shot 1: 穿红色羊毛外套、蓝色围巾的高个女士在雨中小巷。Shot 2: 同一位穿红外套/蓝围巾的女士,现在躲在遮阳篷下。""远处的寺庙钟声,湿路面上的脚步声,无对话""温暖友好的语气,英语"| 使用场景 | 选择HappyHorse 1.0的原因 |
|---|---|
| 具备一致角色的多镜头品牌故事 | 原生跨镜头身份保留能力 |
| 需要片段内旁白+环境音的讲解类视频 | 生成过程中同步输出音频 |
| 多语言短视频广告 | 支持6种语言提示词,脚本质量无下降 |
| 电影级1080p交付 | 原生1080p输出,达到广播级标准 |
| 综合视频质量盲选排名第一 | 在Artificial Analysis Video Arena排名第一 |
Wide shot. A lone astronaut in dusty orange suit with blue-gray harness
skis across lunar plain, leaving parallel tracks in gray regolith.
Mid-stride, poles planted, pushing in 1/6th gravity with subtle upward
drift. Fine dust haze along ski tracks. Crescent Earth above lunar
horizon, blue-white glow against black sky. Raw sunlight, crushed
shadows, no fill. 8K photorealistic.Shot 1: Medium close-up. A woman in a navy trench coat enters a
rain-slick neon-lit Tokyo alley, looks left, holds up an umbrella.
Shot 2: Same woman in same navy trench, now under the awning of a
ramen shop, shaking water off the umbrella. Warm interior glow, soft
chatter, gentle rain on metal roof in the audio.9:16 vertical short. A barista in a black apron pulls a single
espresso shot, steam rising into the morning sun, rich crema slowly
forming. Close-up handheld, shallow DOF, warm cafe ambience and the
hiss of the steam wand.audio_urlruncomfy| 代码 | 含义 |
|---|---|
| 0 | 成功 |
| 64 | CLI参数错误 |
| 65 | 输入JSON错误/规则不匹配(例如 |
| 69 | 上游服务5xx错误 |
| 75 | 可重试:超时/429限流 |
| 77 | 未登录或令牌被拒绝 |
runcomfy run happyhorse/happyhorse-1-0/text-to-videohttps://model-api.runcomfy.net/v1/models/happyhorse/happyhorse-1-0/text-to-videorequest_idGET .../requests/<id>/statusGET .../requests/<id>/result.runcomfy.net.runcomfy.com--output-dirCtrl-CPOST .../requests/<id>/cancelruncomfy login~/.config/runcomfy/token.jsonRUNCOMFY_TOKEN--inputmodel-api.runcomfy.net*.runcomfy.net*.runcomfy.com