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
Use cases
- Ads and trailers
- Concept videos
- Storyboards
- Social media content
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.
Performance
Compare different providers across TokenLX · All locations.
Effective Pricing
Pricing is shown by the model billing method, using per-call or per-second prices and resolution tiers.
Recent activity
Total usage per day on TokenLX (last 30 days).
Sample code & API
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-aihub-...", "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-aihub-..."},
).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.
Parameter Reference
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 |
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resolutionstringNo720p540p