Video ExtendAlibaba
ai/wan-2.2-spicy/video-extend-lora
alibaba/wan-2.2-spicy/video-extend-lora
alibaba/wan-2.2-spicy/video-extend-lora. 瀏覽圖像、影片與換臉模型 API。先試用任一模型,再透過統一 REST API 整合。
相關模型
完整參數參考、輸出結構與即時價格
| AI 模型 API 市集 | 一個平台,全部完成 | 最受歡迎 | 服務條款 | 瀏覽圖像、影片與換臉模型 API。先試用任一模型,再透過統一 REST API 整合。 |
|---|---|---|---|---|
| prompt *Prompt | textarea | — | ≤ 5000 chars | |
| video *Video | video_upload | — | video/* | |
| resolutionResolution | select | 480p | 480p | 720p | |
| durationDuration | select | 5 | 5 | 8 | |
| lorasLoras | array<object> | — | 0–3 items | |
| ↳path *Path | text | — | ≤ 500 chars | |
| ↳scaleScale | slider | 1 | 0 ~ 4 · step 0.1 | |
| high_noise_lorasHigh Noise Loras | array<object> | — | 0–3 items | |
| ↳path *Path | text | — | ≤ 500 chars | |
| ↳scaleScale | slider | 1 | 0 ~ 4 · step 0.1 | |
| low_noise_lorasLow Noise Loras | array<object> | — | 0–3 items | |
| ↳path *Path | text | — | ≤ 500 chars | |
| ↳scaleScale | slider | 1 | 0 ~ 4 · step 0.1 | |
| seedSeed | number | — | — |
完整參數參考、輸出結構與即時價格
| 深入了解 | 一個平台,全部完成 | 瀏覽圖像、影片與換臉模型 API。先試用任一模型,再透過統一 REST API 整合。 |
|---|---|---|
| videos | array<string> |
API
瀏覽圖像、影片與換臉模型 API。先試用任一模型,再透過統一 REST API 整合。
cURL
# 1) Submit — returns { "task_uuid": "..." }
curl -X POST "https://www.namifusion.com/api/v1/marketplace/run/alibaba/wan-2.2-spicy/video-extend-lora" \
-H "Authorization: Bearer YOUR_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"input": {
"prompt": "Continue the camera movement and subject action naturally while preserving the original visual style, lighting, and scene continuity.",
"video": "https://assets-public.namifusion.com/marketplace/videos/2026-04-14/88d6efad3763.mp4",
"resolution": "480p",
"duration": 5
}
}'
# 2) Poll until status is "completed", then read the output URLs
curl "https://www.namifusion.com/api/v1/marketplace/run/tasks/TASK_UUID" \
-H "Authorization: Bearer YOUR_API_KEY"Python
import time, requests
API_KEY = "YOUR_API_KEY"
HEADERS = {"Authorization": f"Bearer {API_KEY}"}
# 1) Submit
resp = requests.post(
"https://www.namifusion.com/api/v1/marketplace/run/alibaba/wan-2.2-spicy/video-extend-lora",
headers=HEADERS,
json={
"input": {
"prompt": "Continue the camera movement and subject action naturally while preserving the original visual style, lighting, and scene continuity.",
"video": "https://assets-public.namifusion.com/marketplace/videos/2026-04-14/88d6efad3763.mp4",
"resolution": "480p",
"duration": 5
}
},
)
resp.raise_for_status() # 401/402/429/5xx stop here instead of polling a bad task
task = resp.json()
# 2) Poll until a terminal state (completed / failed / cancelled).
# This model is allowed up to 300s server-side.
deadline = time.time() + 360
while task.get("status") not in ("completed", "failed", "cancelled"):
if time.time() > deadline:
raise TimeoutError(f"still {task.get('status')} — keep the task_uuid and poll later")
time.sleep(3)
poll = requests.get(f"https://www.namifusion.com/api/v1/marketplace/run/tasks/{task['task_uuid']}", headers=HEADERS)
poll.raise_for_status()
task = poll.json()
print(task["status"], task.get("output"))JavaScript
const API_KEY = "YOUR_API_KEY";
const HEADERS = { Authorization: `Bearer ${API_KEY}` };
// 1) Submit
const resp = await fetch("https://www.namifusion.com/api/v1/marketplace/run/alibaba/wan-2.2-spicy/video-extend-lora", {
method: "POST",
headers: { ...HEADERS, "Content-Type": "application/json" },
body: JSON.stringify({
"input": {
"prompt": "Continue the camera movement and subject action naturally while preserving the original visual style, lighting, and scene continuity.",
"video": "https://assets-public.namifusion.com/marketplace/videos/2026-04-14/88d6efad3763.mp4",
"resolution": "480p",
"duration": 5
}
}),
});
if (!resp.ok) throw new Error(`submit failed: ${resp.status} ${await resp.text()}`);
let task = await resp.json();
// 2) Poll until a terminal state (completed / failed / cancelled).
// This model is allowed up to 300s server-side.
const deadline = Date.now() + 360 * 1000;
while (!["completed", "failed", "cancelled"].includes(task.status)) {
if (Date.now() > deadline) throw new Error(`still ${task.status} — keep the task_uuid and poll later`);
await new Promise((r) => setTimeout(r, 3000));
const poll = await fetch(`https://www.namifusion.com/api/v1/marketplace/run/tasks/${task.task_uuid}`, { headers: HEADERS });
if (!poll.ok) throw new Error(`poll failed: ${poll.status}`);
task = await poll.json();
}
console.log(task.status, task.output);API 文件
ai/wan-2.2-spicy/video-extend-lora
Extend short clips into longer, smoother videos with flexible LoRA-based style control.
ai/wan-2.2-spicy/video-extend-lora is an image-to-video model designed for video continuation and clip extension workflows. It helps turn existing footage into longer sequences with smoother motion, while supporting custom LoRA weights for more precise control over style, character consistency, and visual details. With no cold starts and cost-efficient inference, it is well suited for production-oriented creative pipelines.
🚀 Key Features
- Video extension workflow: Continue from an input video to generate longer sequences that feel more complete and narrative-ready.
- Smooth animation: Optimized for temporal continuity and motion coherence to produce more natural-looking extended clips.
- Custom LoRA support: Apply up to 3 LoRAs, including separate high-noise and low-noise LoRA configurations, for flexible visual control.
- No cold start: Delivers more predictable responsiveness for real-time or high-throughput production use cases.
- Flexible output options: Supports 480p and 720p output, with 5-second and 8-second durations for balancing quality, speed, and cost.
- Reproducible generation: Seed control makes it easier to test variations, compare outputs, and maintain consistency across runs.
🛠️ Technical Specifications
| Item | Details |
|---|---|
| Model architecture | Video extension / continuation model with LoRA support |
| Task type | Image-to-video |
| Input | Prompt, input video, LoRA configurations |
| Output Format | Video |
| Resolution | 480p, 720p |
| Duration | 5s, 8s |
| Fps | Not publicly specified |
| LoRA support | Up to 3 LoRAs; up to 3 high-noise LoRAs; up to 3 low-noise LoRAs |
| Seed | Supported; -1 uses a random seed |
| Latency | Optimized for fast inference with no cold starts |
| Best suited for | Clip extension, stylized continuation, character-consistent video generation |
Sample prompts:
- Continue the scene with the character walking forward through a neon-lit city street, smooth camera motion, cinematic lighting
- Preserve the subject's appearance from the source video and extend with a natural turn, realistic cloth motion, and coherent body movement
- Extend the existing product clip into a polished commercial-style video, slow push-in camera motion, clean background, premium advertising look
💰 Pricing
| Item | Price |
|---|---|
| Base Price | $0.2 |
💡 Best Use Cases
- Short-form content extension: Expand existing clips into longer social videos, teasers, or narrative sequences.
- E-commerce and advertising: Turn product footage into richer promotional videos without reshooting new material.
- Style and character consistency: Use LoRAs to maintain a consistent visual identity across extended scenes.
- Previsualization and concept development: Quickly extend shots for storyboard animation, pacing tests, and creative validation.
🔗 Related Models
- WAN 2.2 Spicy series: A strong fit for users prioritizing motion quality, clip continuation, and customizable LoRA-driven control.
- video-extend-lora variants: Particularly useful for workflows centered on extending footage while preserving style and subject continuity.