Wan 2.2 Vace Outpainting overview
Wan 2.2 Vace Outpainting by Alibaba Cloud
Wan 2.2 VACE Fun A14B Outpainting API extends scenes with consistent motion, spatial detail, and advanced AI-powered video editing.
Wan 2.2 Vace Outpainting specs
- Model ID
wan-22-vace-fun-a14b/outpainting- Developer
- Alibaba Cloud
- Input
- Text, Video
- Output
- Video
- Endpoint
POST https://api.aimlapi.com/v2/video/generations
Wan 2.2 Vace Outpainting is a video-to-video outpainting model designed for extending video frames beyond their original borders, effectively generating additional scene content that blends seamlessly with the input video. It excels in providing creative video outpainting capabilities with flexible control over content style, motion continuity, and resolution quality. This model is part of the Wan VACE series known for versatility in video synthesis and editing tasks.
Technical Specifications
- Model Architecture: Wan 2.2 VACE Fun A14B built on advanced video generation and diffusion networks with VACE architecture.
- Input Types: Video files or URLs with various encoding options.
- Output Resolution: Options for 480p, 580p, 720p, and up to 4K.
- Video Frame Rate: 16 FPS standard; supports higher frame rates.
- Memory & Performance: Optimized for GPU execution with model variants suitable for 8 GB VRAM GPUs.
- Max Video Length: Effectively unlimited length capability while preserving temporal consistency.
- Training Data: Trained on large-scale video datasets with multi-condition controls for robustness.
Performance Benchmarks
- State-of-the-Art Quality: Consistently ranked among leading open-source video generation models.
- Temporal Coherence: Maintains smooth motion and visual consistency across extended frames.
- Resolution Fidelity: High retention of detail in spatial and temporal dimensions even beyond initial frame borders.
- Efficiency: Real-time or near real-time generation speeds for standard HD video processing.
- Compatibility: Runs efficiently on consumer-grade GPUs with standard 8GB VRAM.
Key Features
- Video Outpainting: Extends video frames with new content, preserving visual coherence and temporal structure.
- High-Resolution Output: Supports up to 4K resolution output with smooth frame transitions.
- Flexible Input: Accepts multiple video formats such as MP4, MOV, WEBM, M4V, and GIF.
- Frame Rate: Processes videos at 16 or more frames per second ensuring fluid motion.
- Control Conditions: Supports detailed control inputs including pose, depth, edge (Canny), MLSD, and trajectory control for precise content generation.
- Multilingual Support: Suitable for diverse language inputs, facilitating global use.
Comparison with Other Models
vs Qwen Video: Wan 2.2 focuses on photorealistic video outpainting with detailed multi-condition controls such as pose, depth, and trajectory, enabling precise scene expansion. In contrast, Qwen video models lean towards artistic and stylized generation, often excelling in anime or creative styles but with less emphasis on photorealism and temporal smoothness. Wan 2.2 thus provides more consistent realism and fluidity in extended video sequences.
vs KLING 2.0: While KLING 2.0 offers competitive video generation quality with open-source availability, Wan 2.2 surpasses it by integrating MoE architecture that reduces compute by about 50% while enhancing video detail and motion coherence. Wan 2.2 also provides more versatile control parameters for nuanced scene and motion manipulation, making it preferable for professional and commercial video synthesis tasks.
vs Haiulo 02: Haiulo 02 is known for smooth basic video synthesis but lacks advanced conditioning controls and high-resolution outpainting capabilities that Wan 2.2 robustly supports. Wan 2.2's ability to manage complex group movements and detailed CGI effects offers an edge for movie-quality video extension use cases over Haiulo 02’s simpler workflow.
vs Veo 3: Veo 3 focuses on rapid video generation with less emphasis on outpainting quality and fine control, geared more towards fast content creation. Wan 2.2, on the other hand, balances speed with fidelity, providing high-resolution, temporally consistent outpainting with flexible control inputs that Veo3 currently lacks.
API Integration
Accessible via AI/ML API. Documentation: available here.
Use cases
- Creative video outpainting for extended cinematic scenes.
- Visual effects augmentation in post-production workflows.
- Generating expanded video environments for VR/AR experiences.
- Enhancing video storytelling with additional visual context.
- Video content generation for advertising and social media.
Wan 2.2 Vace Outpainting API pricing
| Usage | Price | Unit |
|---|---|---|
| Video generation | $0.05 | per generation |
| Additional | $0.013 | per generation |
Prices from the AI/ML API price list, checked on Nov 4, 2026.
Wan 2.2 Vace Outpainting vs other video models: prices
AI/ML API rates for 5 models, per generation.
| Model | Per generation |
|---|---|
 Wan 2.2 Vace Outpainting | $0.05 |
| Wan 2.2 Vace Depth | $0.05 |
| Wan 2.2 Vace Inpainting | $0.05 |
| Wan 2.2 Vace Pose | $0.05 |
| Wan 2.2 Vace Reframe | $0.05 |
How to use the Wan 2.2 Vace Outpainting 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": "wan-22-vace-fun-a14b/outpainting",
"prompt": "A slow dolly shot through a sunlit greenhouse full of ferns, light dust in the air, natural camera motion",
"video_url": "https://example.com/input.mp3"
}'import os
import requests
headers = {
"Authorization": f"Bearer {os.environ['AIMLAPI_KEY']}",
"Content-Type": "application/json",
}
payload = {
"model": "wan-22-vace-fun-a14b/outpainting",
"prompt": "A slow dolly shot through a sunlit greenhouse full of ferns, light dust in the air, natural camera motion",
"video_url": "https://example.com/input.mp3"
}
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": "wan-22-vace-fun-a14b/outpainting",
"prompt": "A slow dolly shot through a sunlit greenhouse full of ferns, light dust in the air, natural camera motion",
"video_url": "https://example.com/input.mp3"
}),
});
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 Vace Outpainting
Related articles
Wan 2.2 Vace Outpainting FAQ
What inputs and outputs does Wan 2.2 Vace Outpainting support?
Wan 2.2 Vace Outpainting takes text, video as input and returns video.
How much does Wan 2.2 Vace Outpainting cost?
Wan 2.2 Vace Outpainting costs $0.05 per generation on AI/ML API, billed as you go with no subscription.
How is Wan 2.2 Vace Outpainting billed?
Wan 2.2 Vace Outpainting is billed per generation, a fixed charge per output rather than by prompt length.
Who created Wan 2.2 Vace Outpainting?
Wan 2.2 Vace Outpainting was built by Alibaba Cloud.
How do I call Wan 2.2 Vace Outpainting on AI/ML API?
Send a request to v2/video/generations with wan-22-vace-fun-a14b/outpainting as the model id.
Is Wan 2.2 Vace Outpainting available through a single API key?
Yes. Wan 2.2 Vace Outpainting is served through AI/ML API, so the same key and endpoint format used for other models applies.
What kind of editing capability does this model offer?
It offers video editing through outpainting, extending existing video content.
What is the Wan 2.2 Vace Outpainting model ID?
Use wan-22-vace-fun-a14b/outpainting as the model parameter. Requests go to https://api.aimlapi.com/v2/video/generations with your AI/ML API key.