Enterprise Plans
AI Application Development
AI Translator API
AI SEO/GEO Service
Web Scraping Service
Log in
const main = async () => {
const response = await fetch('https://api.ai.cc/v2/video/generations', {
method: 'POST',
headers: {
Authorization: 'Bearer ',
'Content-Type': 'application/json',
},
body: JSON.stringify({
model: 'krea/krea-wan-14b/video-to-video',
prompt: 'A powerful, matte black jeep, its robust frame contrasting with the lush green surroundings, navigates a winding jungle road, kicking up small clouds of dust and loose earth from its tires.',
video_url: 'https://storage.googleapis.com/falserverless/example_inputs/krea_wan_14b_v2v_input.mp4'
}),
}).then((res) => res.json());
console.log('Generation:', response);
};
main()
import requests
def main():
url = "https://api.ai.cc/v2/video/generations"
payload = {
"model": "krea/krea-wan-14b/video-to-video",
"prompt": "A powerful, matte black jeep, its robust frame contrasting with the lush green surroundings, navigates a winding jungle road, kicking up small clouds of dust and loose earth from its tires.",
"video_url": "https://storage.googleapis.com/falserverless/example_inputs/krea_wan_14b_v2v_input.mp4"
}
headers = {"Authorization": "Bearer ", "Content-Type": "application/json"}
response = requests.post(url, json=payload, headers=headers)
print("Generation:", response.json())
if __name__ == "__main__":
main()
-
AI Playground
Test all API models in the sandbox environment before you integrate.
We provide more than 300 models to integrate into your app.
Product Detail
Krea WAN 14B API: Unleashing Advanced Video Generative AI
Krea WAN 14B represents a significant leap in video generative AI, built upon the robust WAN architecture. This cutting-edge model is engineered for high-detail video generation and seamless video-to-video transformation. It excels in maintaining stable motion and offering precise style control, making it an indispensable tool for creative professionals.
Targeting applications in creative video production, synthetic content creation, and dynamic advertising visualizations, Krea WAN 14B empowers users with real-time editing and style transfer capabilities on their uploaded video content.
⚙️ Technical Specifications
- • Model Type: Video generative diffusion model
- • Architecture: Based on WAN, distilled to 14 billion parameters
- • Inference Speed: Approximately 11 frames per second (fps)
- • Generation Modes: Supports Video-to-Video transformations
- • Input Formats: mp4, mov, webm, m4v, gif
🚀 Performance Benchmarks
- • Achieves 11 fps inference speed on a single high-end GPU
- • Scales 10 times larger than previous real-time video models
- • Latency as low as 1 second to the first frame for streamed video generation
- • Outperforms smaller models in generating complex motion and detailed textures in videos
💰 Krea WAN 14B API Pricing
Experience powerful video generation at an affordable rate: $0.02625 per second (calculated at 16 fps).
✨ Key Features
- • Real-time video generation with a large-scale 14 billion parameter model
- • Video-to-Video capabilities: Upload existing videos for AI enhancement, style transfer, and advanced editing
- • Stable motion handling and high-frequency detail generation
- • Memory and compute optimizations enabling practical high-resolution video generation in real time
- • Comprehensive support for long-form video content generation
💡 Powerful Use Cases
- • Creative video content generation for social media and dynamic marketing campaigns
- • AI-driven video editing and style transfer for synthetic content creation
- • Real-time video enhancement and restyling for webinars, presentations, and live streams
- • Development of high-detail advertisement visuals with customizable artistic styles
- • Streamlined Video-to-Video editing workflows for improving or transforming existing footage
💻 Code Sample
Integrate Krea WAN 14B seamlessly into your applications with our straightforward API. Here's an example for video-to-video transformation:
// Python Example for Krea WAN 14B Video-to-Video API
import requests
API_URL = "https://api.yourplatform.com/v1/video/generate" # Replace with actual API endpoint
HEADERS = {
"Authorization": "Bearer YOUR_API_KEY", # Replace with your actual API key
"Content-Type": "application/json"
}
payload = {
"model": "krea/krea-wan-14b/video-to-video",
"input_video_url": "https://example.com/your-video.mp4", # URL to your input video
"style_prompt": "a vibrant cyberpunk city at night",
"strength": 0.7, # How much style to apply (0.0 to 1.0)
"output_format": "mp4",
"resolution": "1080p"
}
try:
response = requests.post(API_URL, headers=HEADERS, json=payload)
response.raise_for_status() # Raise an exception for HTTP errors
result = response.json()
print("Video transformation initiated successfully:")
print(result)
except requests.exceptions.RequestException as e:
print(f"API request failed: {e}")
Note: This is a conceptual code snippet. Replace placeholder URLs, API keys, and models with your actual implementation details.
Original reference: "Code Sample" in Krea WAN 14B API Overview
📊 Comparison with Leading Video AI Models
Understanding Krea WAN 14B's unique position in the market is crucial. Here's how it stands against other prominent video AI models:
Krea WAN 14B vs. Wan2.1 Turbo
Krea WAN 14B excels in real-time interactive video editing with autoregressive streaming, offering on-the-fly restyling and prompt modifications. In contrast, Wan2.1 Turbo focuses on accelerated batch video generation at 720P resolution using a diffusion transformer architecture, prioritizing speed and affordability over interactive capabilities.
Krea WAN 14B vs. StreamDiffusion
While StreamDiffusion is notable for its color balance and artistic detail, Krea WAN 14B shines with its more stable motion and coherent long-term video structure, coupled with real-time prompt updates. StreamDiffusion typically offers slower generation speed and less temporal stability.
Krea WAN 14B vs. Imagen Video
Krea WAN 14B emphasizes real-time, open-source, interactive video generation and editing with efficient inference on standard GPUs. Imagen Video, on the other hand, aims for ultra-high-quality video synthesis using proprietary models, but this comes at the cost of significantly higher computational resources, slower generation, and a lack of real-time interaction.
❓ Frequently Asked Questions (FAQs)
1. What is Krea WAN 14B API primarily used for?
Krea WAN 14B API is primarily used for advanced, real-time video generation and video-to-video transformations, enabling high-detail output, stable motion, and precise style control for creative and commercial applications.
2. How does Krea WAN 14B achieve real-time performance?
It utilizes a distilled WAN architecture with 14 billion parameters and significant memory and compute optimizations, allowing for an inference speed of approximately 11 frames per second (fps) and latency as low as 1 second to the first frame.
3. Can I apply custom artistic styles to my videos?
Yes, Krea WAN 14B excels in style transfer. You can upload your videos and apply a wide range of AI-driven enhancements and artistic styles, making it ideal for creative restyling and editing.
4. What are the pricing details for Krea WAN 14B API?
The API is priced at $0.02625 per second of video processing, calculated at 16 frames per second.
5. What video formats does the API support?
The Krea WAN 14B API supports common input video formats including MP4, MOV, WebM, M4V, and GIF.
Learn how you can transformyour company with AICC APIs
