Model VersionCapabilitiesDurationResolutionPrice
viduq1-imageImage-to-Video Generation5s1080p$0.5 / video
viduq1-start-endStart and End Frame5s1080p$0.5 / video
viduq1-textText-to-Video Generation5s1080p$0.6 / video

​
Capability Description

  • ​Image-to-Video Generation​: Generate a video by providing a starting frame or both starting and ending frames along with corresponding text descriptions.
  • ​Start and End Frame​: Supports input of two images: the first uploaded image is treated as the starting frame, and the second as the ending frame. The model uses these images as input parameters to generate the video.
  • ​Text-to-Video Generation​: Generate a video from a text prompt; currently supports both a general style and an anime style optimized for animation.
Note: The URL link for the video generated by the model is valid for one day. Please save it as soon as possible if needed.
Scenario TypeDescription
Film Generation- By inputting script excerpts, concept art, and other materials, users can generate promotional videos, visual effects shots, and auxiliary film assets
- Delivers theatrical-level clarity and visual quality with complete frame details
- Provides professional-grade video transitions with natural scene flow
Anime Production- Input character designs and storyboard scripts to quickly generate 2D animated sequences and stylized anime shorts
- Supports styles such as Chinese animation and Japanese anime
- Enables storyline extension and creative regeneration of classic IPs
Short Drama Production- Automatically generate short videos or micro-dramas from novel chapters or scripted scenes
- Covers diverse genres such as romance, mystery, and historical drama
- Optimized for multi-platform distribution needs
Advertising & Marketing- Quickly generate highly engaging brand ads, e-commerce product videos, and interactive ads (e.g., virtual try-on) based on product images and feature descriptions
- Supports adaptation to various platform dimensions and creative formats
Cultural and Tourism Promotion- Generate immersive cultural and tourism promo videos or travel MVs in one click using scenic photos and promotional copy
- Integrates cultural IPs (e.g., historical artifacts, city icons) to create interactive digital experiences

​
Resources

API Documentation: Learn how to call the API.

​
Detailed Description

  1. ​
    Cinematic-Level Visual Clarity

The model delivers a comprehensive upgrade in visual detail restoration.

  1. ​
    Precise Resolution of Visual Artifacts

Movements are smooth and natural—hand gestures during product demonstrations in e-commerce livestreams are accurately rendered and compliant. Visual jitter is minimized through dynamic frame interpolation technology, ensuring fluid and stable footage even in motion-heavy scenes such as running shots or vehicle perspectives.

  1. ​
    Multi-Style Artistic Expression

The realistic style aims for lifelike visuals—urban landscapes and character portraits in city promos are rendered with striking realism. The animated style focuses on authenticity, accurately capturing everything from the hand-drawn lines of Japanese anime to the saturated colors of Western cartoons. By inputting anime character designs, the model generates dynamic story segments that closely match the original IP’s visual style, boosting the efficiency of derivative content creation. Realistic Style: Animated Style:

  1. ​
    Industry-Leading Transition Smoothness

The start-to-end frame transition technology reaches a new level, using dynamic frame prediction and style fusion algorithms to overcome the limitations of “mechanical stitching” in video transitions.

​
Example

Text-to-Video Generation
curl --location --request POST 'https://api.z.ai/api/paas/v4/videos/generations' \
--header 'Authorization: Bearer {your apikey}' \
--header 'Content-Type: application/json' \
--data-raw '{
    "model": "viduq1-text",
    "style": "anime",
    "prompt": "Peter Rabbit drives a small car along the road, his face filled with joy and happiness.",
    "duration": 5,
    "aspect_ratio": "16:9",
    "size": "1920x1080",
    "movement_amplitude": "auto"
}'
Image-to-Video Generation
curl --location --request POST 'https://api.z.ai/api/paas/v4/videos/generations' \
--header 'Authorization: Bearer {your apikey}' \
--header 'Content-Type: application/json' \
--data-raw '{
    "model":"viduq1-image",
    "image_url":"https://example.com/path/to/your/image.jpg",
    "prompt":"Peter Rabbit drives a small car along the road, his face filled with joy and happiness.",
    "duration":5,
    "size":"1920x1080",
    "movement_amplitude":"auto"
}'
Start and End Frame
curl --location --request POST 'https://api.z.ai/api/paas/v4/videos/generations' \
--header 'Authorization: Bearer {your apikey}' \
--header 'Content-Type: application/json' \
--data-raw '{
    "model":"viduq1-start-end",
    "image_url":["https://example.com/path/to/your/image.jpg","https://example.com/path/to/your/image1.jpg"],
    "prompt":"Peter Rabbit drives a small car along the road, his face filled with joy and happiness.",
    "duration":5,
    "size":"1920x1080",
    "movement_amplitude":"auto"
}'