Wan 2.5 Image-to-Video Preview overview
Wan 2.5 Image-to-Video Preview by Alibaba Cloud
Wan 2.5 Image-to-Video API converts images into dynamic videos with efficient performance across different hardware setups.
Wan 2.5 Image-to-Video Preview specs
- Model ID
alibaba/wan2.5-i2v-preview- Developer
- Alibaba Cloud
- Input
- Text, Image
- Output
- Video
- Endpoint
POST https://api.aimlapi.com/v2/video/generations
Wan 2.5 is an advanced AI-powered image-to-video generation model from Alibaba Cloud, designed to transform static images into dynamic, photorealistic videos with fully synchronized audio. It supports rich storytelling through cinematic motion control and extended video durations, making it ideal for content creators, advertisers, and filmmakers seeking high-quality, cost-effective video generation.
Technical Specifications
- Video duration: Up to 10 seconds (longer than many rivals capped at ~8 seconds)
- Frame rate: 24 frames per second (fps)
- Audio: Real-time synchronized voiceover, background music, and sound effects
- Model architecture: Multimodal AI framework integrating vision, audio, and language understanding
- Compatibility: Runs efficiently on a broad range of GPUs with optimized resource requirements
Performance Benchmarks
- Generation speed: 25% faster than Wan 2.2 baseline
- Video quality: 30% improvement in visual fidelity and smoothness
- Semantic compliance: 40% more accurate at reflecting input prompts in video content
- Motion reconstruction: 35% smoother transitions and realistic movements
- Audio-visual sync: High precision lip-syncing and sound alignment
- Hardware efficiency: 20% better GPU resource utilization compared to previous versions
Key Features
- Image-to-video generation: Converts static images into dynamic videos up to 10 seconds.
- Audio-video synchronization: Native support for integrated voiceover, music, and sound effects with lip-sync.
- Advanced motion control: Cinematic camera moves including pan, tilt, zoom, dolly, and rack focus.
- Multilingual support: Robust handling of Chinese and other languages in prompts for consistent AV alignment.
- Efficient rendering: Optimized for faster generation and wider hardware compatibility.
Use Cases
- Social media content creation with dynamic visuals and sound
- Marketing videos and short advertisements
- Cinematic storytelling for short films or promos
- Educational animations with synchronized narration
- Video enhancement and style transfer on existing footage
Comparison with Other Models
vs Google Veo 3: Wan 2.5 offers native synchronized audio with lip-sync, supporting integrated voiceover and music, while Veo 3 focuses on realistic ambient sound and dialogue generation but can sometimes have audiovisual mismatches. Wan 2.5 is generally faster and more cost-effective for video generation.
vs Wan 2.2: Wan 2.5 delivers improved dynamic motion with smoother transitions and better visual fidelity compared to Wan 2.2’s moderate motion and detail sharpness. Hardware compatibility and rendering speed are also enhanced in 2.5, with optimized GPU utilization and broader device support.
vs Kling 2.5 Turbo: Wan 2.5 has richer audio-video synchronization capabilities, including lip-sync and sound effects, while Kling 2.5 Turbo emphasizes physics-consistent motion and natural object behavior in videos but with less advanced audio integration.
API Integration
Accessible via AI/ML API. Documentation: available here.
Use cases
- Social media content creation with dynamic visuals and sound
- Marketing videos and short advertisements
- Cinematic storytelling for short films or promos
- Educational animations with synchronized narration
- Video enhancement and style transfer on existing footage
Wan 2.5 Image-to-Video Preview API pricing
| Usage | Price | Unit |
|---|---|---|
| Video generation | $0.05 | per second |
The final price depends on request parameters such as resolution or duration.
Prices from the AI/ML API price list, checked on Nov 4, 2026.
Wan 2.5 Image-to-Video Preview vs other video models: prices
AI/ML API rates for 5 models, per second.
| Model | Per second |
|---|---|
 Wan 2.5 Image-to-Video Preview | $0.05 |
| Wan 3.0 Video | $0.05 |
| Wan 2.7 Image to Video | $0.1 |
| Wan 2.7 Reference to Video | $0.1 |
| Happy Horse 1.1 | $0.14 |
How to use the Wan 2.5 Image-to-Video Preview API
View docs
Build with your agent
Give your agent the model details, code and documentation.
1Get your API key
Create API keyexport AIMLAPI_KEY="8f2b4c7d9a1e6b3f…"2Make your first request
curl 'https://api.aimlapi.com/v2/video/generations' \
-H "Authorization: Bearer $AIMLAPI_KEY" \
-H 'Content-Type: application/json' \
-d '{
"model": "alibaba/wan2.5-i2v-preview",
"prompt": "A slow dolly shot through a sunlit greenhouse full of ferns, light dust in the air, natural camera motion",
"image_url": "https://example.com/input.jpg"
}'import os
import requests
headers = {
"Authorization": f"Bearer {os.environ['AIMLAPI_KEY']}",
"Content-Type": "application/json",
}
payload = {
"model": "alibaba/wan2.5-i2v-preview",
"prompt": "A slow dolly shot through a sunlit greenhouse full of ferns, light dust in the air, natural camera motion",
"image_url": "https://example.com/input.jpg"
}
response = requests.post("https://api.aimlapi.com/v2/video/generations", headers=headers, json=payload, timeout=120)
response.raise_for_status()
print(response.json())const response = await fetch("https://api.aimlapi.com/v2/video/generations", {
method: "POST",
headers: {
Authorization: `Bearer ${process.env.AIMLAPI_KEY}`,
"Content-Type": "application/json",
},
body: JSON.stringify({
"model": "alibaba/wan2.5-i2v-preview",
"prompt": "A slow dolly shot through a sunlit greenhouse full of ferns, light dust in the air, natural camera motion",
"image_url": "https://example.com/input.jpg"
}),
});
if (!response.ok) throw new Error(`HTTP ${response.status}`);
console.log(await response.json());The request returns a generation id. Poll GET https://api.aimlapi.com/v2/video/generations?generation_id=<id> until the status is completed.
Models similar to Wan 2.5 Image-to-Video Preview
Related articles
Wan 2.5 Image-to-Video Preview FAQ
What inputs and outputs does Wan 2.5 Image-to-Video Preview support?
Wan 2.5 Image-to-Video Preview takes image as input and returns video.
When was Wan 2.5 Image-to-Video Preview released?
Wan 2.5 Image-to-Video Preview became available on November 20, 2025.
How much does Wan 2.5 Image-to-Video Preview cost?
Wan 2.5 Image-to-Video Preview costs $0.05 per second on AI/ML API, billed as you go with no subscription.
How is Wan 2.5 Image-to-Video Preview billed?
Wan 2.5 Image-to-Video Preview costs $0.05 per second on AI/ML API, billed as you go with no subscription.
Can Wan 2.5 Image-to-Video Preview take an existing image as input?
Yes, Wan 2.5 Image-to-Video Preview accepts image input as well as a text prompt.
Who created Wan 2.5 Image-to-Video Preview?
Wan 2.5 Image-to-Video Preview was built by Alibaba Cloud.
How do I call Wan 2.5 Image-to-Video Preview on AI/ML API?
Send a request to v2/video/generations with alibaba/wan2.5-i2v-preview as the model id.
Is Wan 2.5 Image-to-Video Preview available through a single API key?
Yes. Wan 2.5 Image-to-Video Preview is served through AI/ML API, so the same key and endpoint format used for other models applies.
What video resolutions can Wan 2.5 Image-to-Video Preview output?
It supports 480p, 720p, and 1080p resolutions.
Which API endpoint is used to generate videos with this model?
Video generations are created via the v2/video/generations endpoint.