Alibaba WAN 2.5

alibaba/wan-2.5/text-to-video

alibaba/wan-2.5/text-to-video. 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 *Prompttextarea—≤ 5000 chars
negative_promptNegative Prompttextarea—≤ 5000 chars
audioAudio urlaudio_upload——
sizeSizeselect1920*10801920*1080 | 1080*1920 | 1440*1440 | 1632*1248 | 1248*1632 | 1280*720 | 720*1280 | 960*960 | …
durationDurationselect55 | 10 | 15
prompt_extendEnable Prompt Expansionbooleanfalse—
seedSeednumber-1—

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。
videosarray<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-2.5/text-to-video" \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "input": {
    "prompt": "A serene sunset over a calm ocean with gentle waves and a silhouetted sailboat on the horizon.",
    "negative_prompt": "crowded beach, noisy environment, stormy weather",
    "size": "1920*1080",
    "duration": 10,
    "prompt_extend": true,
    "seed": 42
  }
}'

# 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-2.5/text-to-video",
    headers=HEADERS,
    json={
        "input": {
            "prompt": "A serene sunset over a calm ocean with gentle waves and a silhouetted sailboat on the horizon.",
            "negative_prompt": "crowded beach, noisy environment, stormy weather",
            "size": "1920*1080",
            "duration": 10,
            "prompt_extend": True,
            "seed": 42
        }
    },
)
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-2.5/text-to-video", {
  method: "POST",
  headers: { ...HEADERS, "Content-Type": "application/json" },
  body: JSON.stringify({
    "input": {
      "prompt": "A serene sunset over a calm ocean with gentle waves and a silhouetted sailboat on the horizon.",
      "negative_prompt": "crowded beach, noisy environment, stormy weather",
      "size": "1920*1080",
      "duration": 10,
      "prompt_extend": true,
      "seed": 42
    }
  }),
});
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

WAN 2.5 Text-to-Video

Generate cinematic videos directly from text prompts.

WAN 2.5 Text-to-Video is a next-generation AI video generation model designed to transform natural language prompts into dynamic video clips. Compared with earlier WAN models, it delivers improved motion realism, stronger scene understanding, and higher temporal consistency across frames. The model enables creators and developers to generate cinematic short videos from text descriptions through a scalable, production-ready REST inference API.


🚀 Key Features

  • Text-to-Video Generation: Convert natural language prompts into dynamic video clips with coherent scenes and motion.
  • Enhanced Motion Quality: WAN 2.5 produces smoother and more realistic motion between frames.
  • Improved Scene Understanding: The model better interprets complex prompts and generates visually consistent environments.
  • Multi-Resolution Output: Generate videos in different resolutions depending on production needs.
  • Production-Ready API: Easily integrate video generation into creative pipelines, applications, and automated workflows.

🛠️ How It Works

ParameterDetails
InputText Prompt
OutputGenerated Video (MP4)
Resolution Options480p, 720p, 1080p
Clip DurationTypically 5 seconds per generation
SeedDefault: -1 (random)

Generation Capabilities:

  • Scene Creation: "A futuristic city skyline with flying cars at sunset."
  • Character Motion: "A young woman walking slowly through a neon-lit street."
  • Product Visualization: "A luxury watch rotating on a reflective black surface."
  • Cinematic Effects: "Slow-motion waves crashing against dramatic cliffs."

💰 Pricing

ResolutionPrice (USD/sec)
480p$0.05
720p$0.10
1080p$0.15

💡 Best Use Cases

  • Social Media Content: Create engaging short videos for TikTok, Instagram, or YouTube Shorts.
  • Marketing & Advertising: Generate promotional video concepts quickly from simple prompts.
  • Creative Storyboarding: Visualize scenes and ideas before full production.
  • AI Content Pipelines: Integrate automated video generation into large-scale media production workflows.

🔗 Related Models

  • Need to generate videos from images? Try WAN 2.5 Image-to-Video.
  • Need simpler video generation? Try WAN 2.2 Text-to-Video Plus.
  • Need to extend existing video clips? Try WAN Spicy Video Extend.

Note: Generation quality depends on prompt clarity and scene complexity. Detailed prompts describing motion, subjects, and environments typically produce better results.

相關模型

xAI Grok Imagine Video v1.5 Text to Video
文字轉影片X Ai

xAI Grok Imagine Video v1.5 Text to Video

x-ai/grok-imagine-video-v1.5/text-to-video. 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。

起價 $0.840 / 每次執行
MiniMax H3 Text to Video
文字轉影片Minimax

MiniMax H3 Text to Video

minimax/h3/text-to-video. 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。

起價 $0.650 / 每次執行
ltx-2.5/text-to-video
文字轉影片Ltx 2.5

ltx-2.5/text-to-video

ltx-2.5/text-to-video. 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。

起價 $0.500 / 每次執行
Kling Omni Video O3 Standard Text-To-Video
文字轉影片Kling

Kling Omni Video O3 Standard Text-To-Video

kwaivgi/kling-video-o3/text-to-video. 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。

起價 $0.420 / 每次執行
Kling 3.0
文字轉影片Kling

Kling 3.0

kwaivgi/kling-v3.0/text-to-video. 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。

起價 $0.420 / 每次執行
Kling V2.6 Text to Video API
文字轉影片Kling

Kling V2.6 Text to Video API

kwaivgi/kling-v2.6/text-to-video. 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。

起價 $0.210 / 每次執行
Gemini Omni Flash Text to Video API
文字轉影片Google

Gemini Omni Flash Text to Video API

google/gemini-omni-flash/text-to-video. 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。

起價 $1.04 / 每次執行
Seedance 2.0 Mini Text to Video
文字轉影片Doubao

Seedance 2.0 Mini Text to Video

doubao/seedance-2.0-mini/text-to-video. 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。

起價 $0.378 / 每次執行