Text-to-video or image-to-video model. Generates short video clips with configurable duration and resolution.
Key strengths
- Text + image input
- Multiple resolutions
- Duration control
- Motion coherence
Text-to-video or image-to-video model. Generates short video clips with configurable duration and resolution.
Alibaba's alibaba/video-style-transform is a high-fidelity video generation model. It supports text-to-video and image-to-video workflows with configurable duration, aspect ratio, and resolution, plus first-frame and last-frame control for guided scene composition.
Generates cinematic clips with consistent motion, camera control, and optional native audio. Billed per second of generated content.
alibaba/video-style-transform is fully OpenAI-compatible — drop in your existing OpenAI Python or Node SDK and switch `baseURL` to `https://api.tokenlx.ai`. TokenLX transparently routes your requests to the optimal provider endpoint while preserving streaming, function-calling, and structured-output semantics.
Compare different providers across TokenLX · All locations.
Pricing is shown by the model billing method, using per-call or per-second prices and resolution tiers.
Total usage per day on TokenLX (last 30 days).
TokenLX normalizes requests and responses across providers. Use any OpenAI SDK or our native SDK.
import requests, time
resp = requests.post(
"https://api.tokenlx.ai/v1/aigc/video/tasks",
headers={"Authorization": "Bearer sk-tokenlx-...", "Content-Type": "application/json"},
json={
"model": "video-style-transform",
"prompt": "",
"referenceVideoUrls": ["https://example.com/source.mp4"],
"seed": 7,
"resolution": "720p",
},
)
task = resp.json()
task_id = task.get("taskId") or task.get("task_id") or task.get("id")
while True:
result = requests.get(
f"https://api.tokenlx.ai/v1/aigc/video/tasks/{'{'}task_id{'}'}?model=video-style-transform",
headers={"Authorization": "Bearer sk-tokenlx-..."},
).json()
print("status:", result.get("status"))
if result.get("status") in ("completed", "succeeded", "done"):
print(result)
break
time.sleep(10)Replace sk-aihubrouter-… with your key from the dashboard.
POST /v1/aigc/video/tasksGET /v1/aigc/video/tasks/{taskId}?model=video-style-transformResponse is raw upstream JSON passthrough — fields vary by channel.
Style is specified via the seed parameter (0~7). Each value maps to a different art style.
| Parameter | Type | Required | Description |
|---|---|---|---|
| model | string | Yes | Must be video-style-transform |
| prompt | string | No | Optional, can be empty |
| referenceVideoUrls | array | Yes | Source video URL (1 video, ≤30s, ≤100MB) |
| seed | int | No | Style number (0~7) 0: 日漫1: 美漫2: 清新漫画3: 3D 卡通 |
modelstringYespromptstringNoreferenceVideoUrlsarrayYesseedintNo0: 日漫1: 美漫2: 清新漫画3: 3D 卡通4: 中国风卡通5: 剪纸艺术6: 简约插画7: 中国水墨画| resolution | string | No | Output resolution (default 720p) 720p540p |
4: 中国风卡通5: 剪纸艺术6: 简约插画7: 中国水墨画resolutionstringNo720p540p