HappyHorse
HappyHorse モデルは統一された非同期ジョブ API で呼び出します。POST /api/generate でタスクを開始し、完了するまで GET /api/generate/{taskId} をポーリングします。このファミリーは 7 個のエンドポイントを提供します。
概要
すべてのエンドポイントは同じ外枠を共有し、変わるのは model と input フィールドだけです。モデルマーケットの playground から任意に実行できます。
認証
/api-keys で API キーを作成し、Bearer トークンとして送信します。ログイン中のブラウザからのリクエストはセッション cookie 経由でも動作します。
Authorization: Bearer <YOUR_API_KEY>タスクの作成
POST https://api.lithovas.com/api/generateボディ:{ "model": "<slug>", "input": { … } }
レスポンス:{ "taskId": "<id>", "state": "waiting" }
結果の照会
GET https://api.lithovas.com/api/generate/<taskId>レスポンス:{ "taskId", "state": "waiting" | "success" | "fail", "resultUrls": [ … ], "creditsConsumed", "failMsg", "balance" }
state が success または fail になるまでこのエンドポイントをポーリングしてください。失敗したタスクは課金されません。エンドポイント
| モデル | タスク | model slug |
|---|---|---|
| HappyHorse | Text to Video | happyhorse/text-to-video |
| HappyHorse | Image to Video | happyhorse/image-to-video |
| HappyHorse | Video to Video | happyhorse/reference-to-video |
| HappyHorse | Video Editing | happyhorse/video-edit |
| HappyHorse 1.1 | Image to Video | happyhorse-1-1/image-to-video |
| HappyHorse 1.1 | Text to Video | happyhorse-1-1/text-to-video |
| HappyHorse 1.1 | Video to Video | happyhorse-1-1/reference-to-video |
HappyHorse · Text to Video
happyhorse/text-to-videopromptstring必須Text description of video to generate; max 5000 chars (2500 Chinese)
resolutionenum<string>任意Output video resolution setting
aspect_ratioenum<string>任意Output aspect ratio format
durationinteger任意Video length in seconds (3-15 range)
seedinteger任意Random seed for reproducible generation (0-2147483647)
curl -X POST https://api.lithovas.com/api/generate \
-H "Authorization: Bearer $API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "happyhorse/text-to-video",
"input": {
"prompt": "A cinematic red panda surfing through neon rain at dusk.",
"resolution": "1080p",
"aspect_ratio": "16:9",
"duration": 5,
"seed": 0
}
}'HappyHorse · Image to Video
happyhorse/image-to-videopromptstring任意Text description for video generation (max 5000 chars)
image_urlsarray<string>必須Exactly one first-frame image URL (JPEG/PNG/WEBP, 300+ px)
resolutionenum<string>任意Output video resolution
durationinteger任意Video length in seconds (3-15 range)
seedinteger任意Random seed for reproducibility (0-2147483647)
curl -X POST https://api.lithovas.com/api/generate \
-H "Authorization: Bearer $API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "happyhorse/image-to-video",
"input": {
"prompt": "Animate the image with natural motion, subtle camera movement, and cinematic lighting.",
"image_urls": [
"https://example.com/input.jpg"
],
"resolution": "1080p",
"duration": 5,
"seed": 0
}
}'HappyHorse · Video to Video
happyhorse/reference-to-videopromptstring必須Text prompt describing the video to generate (any language)
reference_imagearray<string>必須Reference image URL list. Provide 1-9 images
resolutionenum<string>任意Output video resolution
aspect_ratioenum<string>任意Output aspect ratio
durationinteger任意Output duration in seconds (integer, 3-15)
seedinteger任意Random seed for reproducibility (if supported)
curl -X POST https://api.lithovas.com/api/generate \
-H "Authorization: Bearer $API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "happyhorse/reference-to-video",
"input": {
"prompt": "Restyle the source footage with richer lighting, cleaner motion, and a cinematic grade.",
"reference_image": [
"https://example.com/input.jpg"
],
"resolution": "1080p",
"aspect_ratio": "16:9",
"duration": 5,
"seed": 0
}
}'HappyHorse · Video Editing
happyhorse/video-editpromptstring必須Edit instruction for intended change; max 5000 chars (2500 Chinese)
video_urlstring必須Input video URL (MP4/MOV, 3-60s, max 2160px longer side)
reference_imagearray<string>任意Optional reference images (0-5 URLs, JPEG/PNG/WEBP, >=300px)
resolutionenum<string>任意Output video resolution
audio_settingenum<string>任意Audio handling strategy
seedinteger任意Random seed for reproducibility (0-2147483647)
curl -X POST https://api.lithovas.com/api/generate \
-H "Authorization: Bearer $API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "happyhorse/video-edit",
"input": {
"prompt": "A cinematic red panda surfing through neon rain at dusk.",
"video_url": "https://example.com/reference.mp4",
"reference_image": [
"https://example.com/input.jpg"
],
"resolution": "1080p",
"audio_setting": "auto",
"seed": 0
}
}'HappyHorse 1.1 · Image to Video
happyhorse-1-1/image-to-videopromptstring任意Describes video content to generate; max 5000 chars
image_urlsarray<string>必須URL of first frame image (JPEG/PNG/WEBP, 300px+ min)
resolutionenum<string>任意Output video resolution
durationnumber任意Video length in seconds; range [3, 15]
curl -X POST https://api.lithovas.com/api/generate \
-H "Authorization: Bearer $API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "happyhorse-1-1/image-to-video",
"input": {
"prompt": "Animate the image with natural motion, subtle camera movement, and cinematic lighting.",
"image_urls": [
"https://example.com/input.jpg"
],
"resolution": "1080p",
"duration": 5
}
}'HappyHorse 1.1 · Text to Video
happyhorse-1-1/text-to-videopromptstring必須Text description of the video; max 5000 chars (2500 Chinese)
resolutionenum<string>任意Output video resolution
aspect_ratioenum<string>任意Output video aspect ratio
durationnumber任意Output video duration in seconds (3-15, whole numbers)
curl -X POST https://api.lithovas.com/api/generate \
-H "Authorization: Bearer $API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "happyhorse-1-1/text-to-video",
"input": {
"prompt": "A cinematic red panda surfing through neon rain at dusk.",
"resolution": "1080p",
"aspect_ratio": "16:9",
"duration": 5
}
}'HappyHorse 1.1 · Video to Video
happyhorse-1-1/reference-to-videopromptstring必須Description of desired elements and visual style for the video
reference_imagearray<string>必須URLs of reference images (JPEG/PNG/WEBP, min 400px, max 20MB)
resolutionenum<string>任意Output video resolution tier
aspect_ratioenum<string>任意Video aspect ratio format
durationnumber任意Video length in seconds (integer, 3-15 range)
curl -X POST https://api.lithovas.com/api/generate \
-H "Authorization: Bearer $API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "happyhorse-1-1/reference-to-video",
"input": {
"prompt": "Restyle the source footage with richer lighting, cleaner motion, and a cinematic grade.",
"reference_image": [
"https://example.com/input.jpg"
],
"resolution": "1080p",
"aspect_ratio": "16:9",
"duration": 5
}
}'