SuperAPI AI Directory

Qingying - Zhipu launches upgraded Qingying 2.0, AI video generation capabilities comprehensively improved

Author: AI小集 · Original source: AI工具集

What is Qingying 2.0

Qingying 2.0 is an upgraded version launched by Zhipu AIAI video generationtool, based onthe CogVideoX modeldeveloped. It supports generating ultra-high-definition videos of 10 seconds, 4K resolution, and 60 frames, with the following features: model capabilities comprehensively improved, able to better understand complex text prompts and generate more realistic videos. Supports video output in any aspect ratio, adapting to different playback needs, adds built-in sound effects, throughthe CogSound modelgenerating matching sound effects for videos, providing multi-channel generation capability, the same instruction or image can generate multiple videos at once.

Qingying 2.0

Main features of Qingying 2.0

  • 4K ultra-high-definition video generation: Supports generating ultra-high-definition videos of 10 seconds duration, 4K resolution, and 60 frames, for a smoother visual experience.
  • Any aspect ratio output: Can generate videos in different aspect ratios, adapting to various playback needs.
  • Built-in sound effects: Through the CogSound model, it can generate matching sound effects based on video content, such as natural environment sounds, vehicle sounds, etc.
  • Multi-channel generation capability: The same instruction or image can generate multiple videos at once, improving creative efficiency.
  • Powerful text understanding capability: Able to better understand complex text prompts and generate videos that better meet user needs.
  • High-quality image-to-video: Supports generating videos by uploading images, further optimizing the accuracy of character actions and physical world simulation.
  • Efficient compression and coherence: Uses a 3D variational autoencoder (3D VAE) to compress video data to 2%, significantly reducing computing resource requirements while maintaining coherence between video frames.
  • 3D Rotary Position Embedding (3D RoPE): Improves the model's ability to capture inter-frame relationships in the temporal dimension, establishing long-range dependencies and generating smoother videos.

Upgrade highlights of Qingying 2.0

  • Model capabilities greatly improved: Model structure, training methods, and data engineering are comprehensively updated, and the image-to-video foundation model capability is improved by 38%. Supports large-scale movement of the main subject in the frame while maintaining image stability, with greatly improved motion coherence and camera movement richness.
  • Industry-leading instruction-following capability: Able to understand and implement complex prompts, generating content that better meets user needs.
  • Supports multiple artistic styles: Qingying 2.0 can handle realistic styles, 3D animation, 2D animation, and special artistic styles, generating exquisite visuals.
  • Improved visual aesthetics and stability: Performs better in image stability and motion coherence, and the generated videos are more delicate and natural.
  • Official examples
    • Prompt: The puppy puts the pot down on the gas stove, picks up the spoon on the table and stirs it in the pot

    • Prompt: Realistic style, family portrait comes to life

    • Prompt: Viral gold coin effect

How to use Qingying 2.0

Use through the Zhipu Qingyan web version or APP: Qingying 2.0 is open for free use, with unlimited generation times.

  • Web version: Visitthe Zhipu Qingyan official website, select the AI video generation page, enter a text description or upload an image to generate a video.
  • App: Download the "Zhipu Qingyan App" from major app stores and experience the Qingying feature within the app.
  • Usage Suggestions:
    • Free Experience: All users can use Zhipu Qingying 2.0 for free, but may encounter queuing.
    • Acceleration Service: If you need faster generation speed, you can purchase the acceleration service.
    • Parameter Settings: With the following parameter modes, the generation results are better.

Application Scenarios of Qingying 2.0

  • Education: Qingying 2.0 can help teachers and educational content creators quickly generate instructional videos. Teachers can input a description of a scientific principle to generate intuitive animated videos, helping students better understand complex concepts.
  • Marketing: Enterprises can use Qingying 2.0 to generate customized advertising videos. By inputting product descriptions and marketing copy, Qingying 2.0 can generate attractive advertising videos and improve promotional effectiveness.
  • Entertainment: Content creators can use Qingying 2.0 to easily produce short videos and movie trailers. Qingying 2.0 provides rich customization options and efficient video generation capabilities, allowing creators to quickly generate high-quality video works according to their own ideas and needs.
  • News Media: News media organizations can use Qingying 2.0 to quickly generate news video reports. When urgent news events occur, reporters can input news scripts and related descriptions to quickly generate accompanying video content, improving the efficiency and reach of news dissemination.
  • Tourism Industry: Travel companies can combine Qingying 2.0 to generate detailed virtual tour guide videos. By inputting descriptions of tourist attractions, Qingying 2.0 can generate virtual guide videos, allowing tourists to experience tourist attractions panoramically online.
  • E-commerce: E-commerce sellers can use Qingying 2.0 to generate product display videos. By inputting detailed descriptions and features of products, Qingying 2.0 can generate videos displaying products, improving product appeal and sales.