Alibaba WAN 2.5

alibaba/wan-2.5/image-to-video

Alibaba WAN 2.5 redefines AI video generation by transforming text or images into high-quality videos (480p/720p/1080p) with natively synced audio. Engineered to be faster and more cost-effective than Google Veo 3, it offers a ready-to-use REST API with industry-leading performance and zero cold starts. It is the ultimate solution for creators seeking professional-grade output at a fraction of the cost.

Examples

Alibaba WAN 2.5 example 1

Parameters

NameTypeDefaultConstraintsDescription
image_url *Imageimage_upload0–1 itemsThe image for generating the output.
audio_urlAudioc URLaudio_uploadAudio URL to guide generation (optional).
promptPrompttextarea≤ 1500 charsThe positive prompt for the generation.
negative_promptNegative Prompttextarea≤ 1500 charsThe negative prompt for the generation.
resolutionResolutionselect1080P480P | 720P | 1080PThe resolution of the generated media.
durationDurationselect55 | 10 | 15The duration of the generated media in seconds.
prompt_extendEnable Prompt ExpansionbooleantrueIf set to true, the prompt optimizer will be enabled.
seedSeednumber≥ 0The random seed to use for the generation. -1 means a random seed will be used.

API

Call this model through one unified REST API. Get a key on the API Keys page.

cURL
# 1) Submit — returns { "task_uuid": "..." }
curl -X POST "https://www.namifusion.com/api/v1/marketplace/run/alibaba/wan-2.5/image-to-video" \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "input": {
    "image_url": [
      "https://assets-public.namifusion.com/uploads/images/2026-03-04/b44fa344efb2.png"
    ],
    "prompt": "Create a vibrant and dynamic video portraying the transition from dawn to daylight over a mountainous region.",
    "negative_prompt": "Avoid including any urban structures or human figures.",
    "resolution": "1080P",
    "duration": 10,
    "prompt_extend": true,
    "seed": 0
  }
}'

# 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/image-to-video",
    headers=HEADERS,
    json={
        "input": {
            "image_url": [
                "https://assets-public.namifusion.com/uploads/images/2026-03-04/b44fa344efb2.png"
            ],
            "prompt": "Create a vibrant and dynamic video portraying the transition from dawn to daylight over a mountainous region.",
            "negative_prompt": "Avoid including any urban structures or human figures.",
            "resolution": "1080P",
            "duration": 10,
            "prompt_extend": True,
            "seed": 0
        }
    },
)
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/image-to-video", {
  method: "POST",
  headers: { ...HEADERS, "Content-Type": "application/json" },
  body: JSON.stringify({
    "input": {
      "image_url": [
        "https://assets-public.namifusion.com/uploads/images/2026-03-04/b44fa344efb2.png"
      ],
      "prompt": "Create a vibrant and dynamic video portraying the transition from dawn to daylight over a mountainous region.",
      "negative_prompt": "Avoid including any urban structures or human figures.",
      "resolution": "1080P",
      "duration": 10,
      "prompt_extend": true,
      "seed": 0
    }
  }),
});
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);

Documentation

WAN 2.5 Image-to-Video

Transform static images into dynamic, cinematic video clips.

WAN 2.5 Image-to-Video is a next-generation AI video generation model designed to animate a single image into a short, high-quality video. Compared with previous WAN models, it delivers smoother motion, stronger visual consistency, and improved scene understanding. The model preserves the original visual style while generating natural movement and cinematic transitions. With a production-ready REST inference API, developers and creators can easily integrate image-to-video generation into creative pipelines and automated content workflows.


🚀 Key Features

  • Image-to-Video Animation: Convert a single image into a dynamic video clip with natural motion and scene continuity.
  • Enhanced Motion Quality: WAN 2.5 improves motion realism and temporal consistency across frames.
  • High Visual Fidelity: Maintains the original structure, subject, and visual style of the source image.
  • Multi-Resolution Output: Generate videos in multiple resolutions suitable for different production needs.
  • Production-Ready API: Easily integrate into applications, creative tools, and automated video pipelines through REST APIs.

🛠️ How It Works

ParameterDetails
InputImage + optional text prompt
OutputGenerated Video (MP4)
Resolution Options480p, 720p, 1080p
Clip DurationTypically 5 seconds per generation
SeedDefault: -1 (random)

Generation Capabilities:

  • Scene Animation: “A sunset beach photo where waves gently move toward the shore.”
  • Character Motion: “A portrait photo where the subject slowly turns and smiles.”
  • Product Showcase: “A sneaker photo rotating slowly on a studio background.”
  • Cinematic Effects: “Clouds drifting slowly across a mountain landscape.”

💰 Pricing

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

💡 Best Use Cases

  • Social Media Content: Turn photos into short engaging videos for TikTok, Instagram, or YouTube Shorts.
  • Marketing & Advertising: Animate product images for promotional content and digital ads.
  • Creative Design: Quickly transform visual concepts or artwork into animated clips.
  • AI Content Pipelines: Integrate automated image-to-video generation into scalable media production workflows.

🔗 Related Models

  • Need to generate videos from text? Try WAN 2.5 Text-to-Video.
  • Need simpler image animation? Try WAN 2.2 Image-to-Video Plus.
  • Need to extend existing clips? Try WAN Spicy Video Extend.

Note: Generation quality depends on the clarity of the input image and prompt. High-resolution images with clear subjects typically produce better results.

Related models

xAI Grok Imagine Video v1.5 Image to Video
Image to VideoX Ai

xAI Grok Imagine Video v1.5 Image to Video

Animate one input image with a text prompt into a 1-15 second video at 480p or 720p.

from $0.840 / per run
Vidu Q3 Image To Video
Image to VideoVidu

Vidu Q3 Image To Video

Vidu Q3 Image-to-Video turns text prompts into high-quality videos with exceptional visual fidelity and diverse motion. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.

from $0.750 / per run
Nami Wan 2.7 I2V Spicy Prime
Image to Video

Nami Wan 2.7 I2V Spicy Prime

Create a 2–15 second video from a reference image and prompt, with 720p/1080p output and optional audio guidance.

from $1.00 / per run
MiniMax H3 Image to Video
Image to VideoMinimax

MiniMax H3 Image to Video

MiniMax H3 Image to Video animates a first-frame image into a coherent 2K video, with natural-language motion instructions and optional last-frame control for consistent motion, scene continuity, and cinematic video generation. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.

from $0.650 / per run
Kling Omni Video O3 Image-To-Video
Image to VideoKling

Kling Omni Video O3 Image-To-Video

Kling Omni Video O3 Image-to-Video transforms static images into dynamic cinematic videos using MVL (Multi-modal Visual Language) technology. Maintains subject consistency while adding natural motion, physics simulation, and seamless scene dynamics. Supports audio generation. Ready-to-use REST API, best performance, no coldstarts, affordable pricing.

from $0.420 / per run
Kling Omni Video O1 Image-to-Video
Image to VideoKling

Kling Omni Video O1 Image-to-Video

Kling Omni Video O1 Image-to-Video transforms static images into dynamic cinematic videos using MVL (Multi-modal Visual Language) technology. Maintains subject consistency while adding natural motion, physics simulation, and seamless scene dynamics. Ready-to-use REST API, best performance, no coldstarts, affordable pricing.

from $0.560 / per run
Kling 3.0 Standard
Image to VideoKling

Kling 3.0 Standard

Kling 3.0 Standard delivers high-quality image-to-video generation with smooth motion, cinematic visuals, accurate prompt adherence, and native audio for ready-to-share clips. Ready-to-use REST inference API, best performance, no cold starts, affordable pricing.

from $0.420 / per run
Kling V2.6 Image to Video API
Image to VideoKling

Kling V2.6 Image to Video API

Kling 2.6 delivers top-tier image-to-video generation with smooth motion, cinematic visuals, accurate prompt adherence, and native audio for ready-to-share clips. Ready-to-use REST inference API, best performance, no cold starts, affordable pricing.

from $0.210 / per run
Alibaba WAN 2.5 API — Pricing, Playground & Docs | NamiFusion