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/generate/video/runway/generation', {
method: 'POST',
headers: {
Authorization: 'Bearer ',
'Content-Type': 'application/json',
},
body: JSON.stringify({
model: 'runway/act_two',
character: {
type: 'image',
url: 'https://fs.tonkosti.ru/33/ol/33olc2eyzj6s4w8ksg8kkc0gg.jpg',
},
reference: {
type: 'video',
url: 'https://videos.pexels.com/video-files/3044160/3044160-uhd_2560_1440_24fps.mp4',
}
}),
}).then((res) => res.json());
console.log('Generation:', response);
};
main()
import requests
def main():
url = "https://api.ai.cc/v2/generate/video/runway/generation"
payload = {
"model": "runway/act_two",
"character": {
"type": "image",
"url": "https://fs.tonkosti.ru/33/ol/33olc2eyzj6s4w8ksg8kkc0gg.jpg",
},
"reference": {
"type": "video",
"url": "https://videos.pexels.com/video-files/3044160/3044160-uhd_2560_1440_24fps.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
RunwayML Act Two is an advanced video generation API that revolutionizes character animation. It efficiently creates high-quality short videos by combining driving performance videos with character references. Featuring a transparent, credit-based pricing system, Act Two is highly accessible for developers and creators engaged in diverse creative and production workflows.
Technical Specifications
🚀 Performance Benchmarks
- • Optimized for rapid video generation.
- • Suitable for lightweight video synthesis tasks with efficient compute usage.
💡 Key Capabilities
- • Supports variable-length video outputs with strong cost efficiency.
- • Easy integration for developers aiming to add video synthesis functionality.
- • Resource-efficient, making it ideal for applications with limited hardware or budget constraints.
💰 API Pricing
- $0.0525 per second, utilizing a transparent, credit-based system.
Optimal Use Cases
- • Quick video content creation for social media and marketing campaigns.
- • Lightweight creative tools requiring efficient video synthesis capabilities.
- • Prototyping and small-scale video generation projects.
- • Cost-conscious deployments needing short video outputs with predictable pricing.
Code Sample
<snippet data-name="runway.create-video-character-performance-generation" data-model="runway/act_two"></snippet>
Comparison with Other Models
➡️ Vs. Pika Labs:
Act Two's minimal 3-second video unit and transparent credit pricing make it a compelling choice for rapid, budget-conscious prototyping. Pika Labs may offer more customization for advanced workflows but typically at a higher price and computational requirement.
➡️ Vs. Kaiber:
While Kaiber is known for its broader video transformation and style transfer capabilities, Act Two excels by offering high-quality animated short videos with minimal compute needs. This makes it ideal for developers seeking straightforward deployment and predictable costs.
➡️ Vs. Sora:
Sora delivers premium visual effects and extended scene generation. However, RunwayML Act Two stands out by providing immediate, cost-effective results for short-form animated videos, catering to developers and content creators who prioritize speed and affordability over advanced cinematic capabilities.
Limitations
- 🚫 Minimum Video Length: A minimum video length of 3 seconds may not suit applications requiring ultra-short clips or single-frame outputs.
- 🚫 Optimization for Short Videos: Primarily optimized for short video generation; longer or complex videos may require more specialized solutions.
Frequently Asked Questions
❓ What generative architecture innovations power Runway Act Two's cinematic video synthesis?
Runway Act Two employs a revolutionary temporal diffusion transformer architecture with multi-scale spacetime attention mechanisms. This system simultaneously models short-term motion dynamics and long-term narrative coherence, incorporating hierarchical latent representations that separate content, style, and motion factors for independent control. Advanced physics-informed neural networks ensure realistic motion patterns that adhere to physical laws.
❓ How does Act Two achieve unprecedented consistency in character and object persistence?
The model implements persistent identity embeddings that maintain character features, clothing details, and object properties across extended sequences. It utilizes cross-frame attention mechanisms with memory banks that store and retrieve entity information, combined with geometric consistency constraints that preserve spatial relationships and proportions. The system also includes automatic continuity detection to identify and correct potential inconsistencies.
❓ What professional cinematography capabilities does Act Two introduce to AI video generation?
Act Two incorporates comprehensive cinematography intelligence, including dynamic camera choreography with professional movement patterns (dolly, crane, steadicam), advanced lighting simulation with realistic light transport and global illumination, and depth-of-field effects with authentic bokeh rendering. It also features professional color grading with cinematic LUT applications, understanding scene composition principles, shot sequencing logic, and editorial pacing.
❓ What creative control and directorial interfaces does Act Two provide?
Act Two offers granular creative control through semantic editing interfaces that allow shot-by-shot direction, style transfer with cinematic references, emotional tone adjustment, character personality specification, and narrative pacing controls. The system includes interactive preview capabilities with real-time adjustments, collaborative workflow support for team production, and export options compatible with professional editing software. Advanced users can access low-level parameters for lighting, camera physics, and scene composition with precision control.
Learn how you can transformyour company with AICC APIs
