Wan 2.2 Plus Image to Video overview
Wan 2.2 Plus Image to Video by Alibaba Cloud
Wan2.2 I2V API converts images into videos with efficient cloud inference, real-time streaming output, and responsive AI video generation.
Wan 2.2 Plus Image to Video specs
- Model ID
alibaba/wan2.2-i2v-plus- Developer
- Alibaba Cloud
- Input
- Text, Image
- Output
- Image, Video
- Endpoint
POST https://api.aimlapi.com/v2/video/generations
Wan2.2 Image-to-Video supports multi-turn conversational sessions facilitating dynamic user interactions with visual and textual data and enables function calling to orchestrate complex pipelines involving video synthesis, image captioning, and reasoning over visual content, suitable for automation and enterprise-level workflows.
Performance Benchmarks
Wan2.2 excels in multi-modal tasks involving images and text, optimized for vision-language integration and cross-modal reasoning, achieves state-of-the-art accuracy on VQA benchmarks and image captioning tasks.
Key Capabilities
- Vision Understanding: Superior in interpreting complex visual scenes and generating descriptive, coherent text
- Multi-modal Reasoning: Excels at cross-modal inference combining image and text inputs for detailed analytic tasks
- Content Generation: Supports high-quality image-conditioned text generation for reports, summaries, and creative tasks
Optimal Use Cases
- Visual Question Answering and Interactive Image Analysis
- Automated Image Captioning and Content Summarization
- Multi-modal Business Intelligence and Analytics
- Creative Visual Storytelling and Report Generation
Comparison with Other Models
- vs. Popular Vision-Language Models: Wan2.2 Image-to-Video delivers superior VQA and image captioning accuracy, excelling in complex motion continuity and multi-modal reasoning, whereas popular models provide broader but less specialized multi-modal capabilities primarily for general image captioning and classification tasks.
- vs. Text-only LLMs: Wan2.2 supports robust vision-language integration with direct image-to-video generation, while text-only LLMs are limited to text-based reasoning with no native vision understanding.
- vs. Wan2.1: Wan2.2 Image to Video outperforms with a Mixture-of-Experts architecture, trained on substantially more images and videos (+65.6% images, +83.2% videos), resulting in richer cinematic aesthetics, more stable video generation, and better motion coherence.
Limitations
Mainly optimized for image-to-video generation tasks, less suitable for pure text or non-visual applications.
API Integration
Accessible via AI/ML API. Documentation: available here.
Use cases
- Visual Question Answering and Interactive Image Analysis
- Automated Image Captioning and Content Summarization
- Multi-modal Business Intelligence and Analytics
- Creative Visual Storytelling and Report Generation
Wan 2.2 Plus Image to Video API pricing
| Usage | Price | Unit |
|---|---|---|
| Video generation | $0.1 | per generation |
Prices from the AI/ML API price list, checked on Nov 4, 2026.
Wan 2.2 Plus Image to Video vs other video models: prices
AI/ML API rates for 5 models, per generation.
| Model | Per generation |
|---|---|
 Wan 2.2 Plus Image to Video | $0.1 |
| Wan 2.2 Vace Depth | $0.05 |
| Wan 2.2 Plus Text to Video | $0.1 |
 Gemini Omni | $0.1014 |
 Kling V2.1 Pro Image-to-Video | $0.103 |
How to use the Wan 2.2 Plus Image to Video 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/wan2.2-i2v-plus",
"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/wan2.2-i2v-plus",
"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/wan2.2-i2v-plus",
"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 2.2 Plus Image to Video
Related articles
Wan 2.2 Plus Image to Video FAQ
What inputs and outputs does Wan 2.2 Plus Image to Video support?
Wan 2.2 Plus Image to Video takes image as input and returns video.
When was Wan 2.2 Plus Image to Video released?
Wan 2.2 Plus Image to Video became available on November 20, 2025.
How much does Wan 2.2 Plus Image to Video cost?
Wan 2.2 Plus Image to Video costs $0.1 per generation on AI/ML API, billed as you go with no subscription.
How is Wan 2.2 Plus Image to Video billed?
Wan 2.2 Plus Image to Video is billed per generation, a fixed charge per output rather than by prompt length.
Can Wan 2.2 Plus Image to Video take an existing image as input?
Yes, Wan 2.2 Plus Image to Video accepts image input as well as a text prompt.
Who created Wan 2.2 Plus Image to Video?
Wan 2.2 Plus Image to Video was built by Alibaba Cloud.
How do I call Wan 2.2 Plus Image to Video on AI/ML API?
Send a request to v2/generate/video/alibaba/generation with alibaba/wan2.2-i2v-plus as the model id.
Is Wan 2.2 Plus Image to Video available through a single API key?
Yes. Wan 2.2 Plus Image to Video is served through AI/ML API, so the same key and endpoint format used for other models applies.
What improvement does Wan 2.2 Plus Image to Video offer over earlier versions?
It generates high-quality videos from input images with improved stability.
What is the Wan 2.2 Plus Image to Video model ID?
Use alibaba/wan2.2-i2v-plus as the model parameter. Requests go to https://api.aimlapi.com/v2/video/generations with your AI/ML API key.