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/text-to-video',
prompt: 'A DJ on the stand is playing, around a World War II battlefield, lots of explosions, thousands of dancing soldiers, between tanks shooting, barbed wire fences, lots of smoke and fire, black and white old video: hyper realistic, photorealistic, photography, super detailed, very sharp, on a very white background',
}),
}).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/text-to-video",
"prompt": "A DJ on the stand is playing, around a World War II battlefield, lots of explosions, thousands of dancing soldiers, between tanks shooting, barbed wire fences, lots of smoke and fire, black and white old video: hyper realistic, photorealistic, photography, super detailed, very sharp, on a very white background"
}
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: Revolutionizing Real-Time Text-to-Video AI
Discover Krea WAN 14B, a cutting-edge artificial intelligence model specifically engineered for advanced real-time text-to-video generation and editing. Boasting an impressive 14 billion parameters, it establishes a new performance benchmark in creating and transforming high-quality videos on demand. Users can easily input textual prompts or storyboards to generate dynamic video clips, which can then be restyled or edited in real time with exceptionally low latency, making creative workflows more fluid and efficient.
✨ Technical Specifications
- ✓ Model Type: Autoregressive video diffusion model, expertly distilled from Wan 2.1 14B utilizing the Self-Forcing technique.
- ✓ Parameters: A massive 14 billion, ensuring high fidelity and complexity in video generation.
- ✓ Inference Speed: Achieves 11 frames per second (fps), enabling rapid processing.
- ✓ Output Frame Rate: Delivers smooth videos at 16 fps.
🚀 Performance Highlights
- ✓ Real-time Generation: Experience first frames in approximately 1 second latency for immediate visual feedback.
- ✓ Creative Interaction: Optimized for rapid, interactive video generation, providing unparalleled creative control during the process.
- ✓ Unmatched Scale: Achieves over 10x larger scale compared to currently available open-source video models.
💡 Key Features & API Pricing
- ✓ Autoregressive Video: Generate videos seamlessly from diverse text inputs.
- ✓ Dynamic Restyling: Perform on-the-fly video restyling and comprehensive editing.
- ✓ Long-Form Support: Facilitates extended video generation through its innovative streaming architecture.
- ✓ Enhanced Quality: Multiple attention backends work to significantly boost both generation speed and video quality.
API Pricing for Krea WAN 14B:
$0.02625 / sec (16 fps)
🎯 Diverse Use Cases
- ✓ Media & Marketing: Ideal for rapid video prototyping in advertising and media content creation.
- ✓ Educational Content: Generate scalable and easily adaptable video content for various educational platforms.
- ✓ Social Media & News: Quickly produce platform-generated video snippets for engaging social media feeds and breaking news.
- ✓ Interactive Presentations: Empower interactive video-based storytelling and dynamic presentation tools.
💻 Code Sample Integration
<snippet data-name="video.text-to-video" data-model="krea/krea-wan-14b/text-to-video"></snippet>📣 Krea WAN 14B: A Competitive Edge
vs. Wan 2.1:
Krea WAN 14B features a significantly larger 14-billion parameter model, vastly outperforming Wan 2.1's 1.3 billion parameters. This substantial increase directly translates to far superior modeling of complex movements and high-frequency video details, delivering richer and more realistic outputs.
vs. Wan 2.1 Turbo:
While Wan 2.1 Turbo is optimized for throughput and higher-resolution batch generation, Krea WAN 14B distinguishes itself with a focus on live, prompt-interactive video generation, offering streaming edits. This makes Krea WAN 14B ideal for creative workflows that demand immediate iteration and on-the-fly control.
vs. Veo 3.1:
Veo 3.1 is known for producing high-quality long-form videos but currently lacks real-time streaming or interactive generation capabilities. Krea WAN 14B is thus more advantageous for creative processes requiring instant feedback. Furthermore, Krea's model is open-source, providing greater transparency and modification potential compared to Google's proprietary Veo system.
❓ Frequently Asked Questions (FAQ)
1. What is Krea WAN 14B Text-to-Video AI model?
Krea WAN 14B is an advanced text-to-video generation model with 14 billion parameters, designed to create high-quality videos from text descriptions, generating coherent motion and realistic scenes based on textual prompts.
2. What makes Krea WAN 14B stand out from other models?
Krea WAN 14B's 14B parameter architecture is optimized for real-time, interactive video generation with low latency, superior motion coherence, high visual quality, and diverse style support, unlike many models focused solely on batch processing.
3. How much does Krea WAN 14B Text-to-Video API cost?
The API pricing for Krea WAN 14B is $0.02625 per second of generated video content, calculated at an output frame rate of 16 fps.
4. Does Krea WAN 14B support long-form video generation?
Yes, Krea WAN 14B is designed with a streaming architecture that effectively supports the generation of long-form videos, making it versatile for various content needs beyond short clips.
5. What are the primary use cases for Krea WAN 14B?
Key use cases include content creation for media, advertising, and marketing with rapid video prototyping; scalable educational video content; platform-generated snippets for social media and news; and interactive video-based storytelling tools.
Learn how you can transformyour company with AICC APIs
