Emoji creates expressive videos from a portrait or half-body image and a preset dynamic template.
ImportantThis document applies only to the China (Beijing) region. An API key for the China (Beijing) region is required to use the model.
Performance showcase
| Input: Portrait image | Output: Dynamic portrait video |
|---|---|
 | driven_id: jingdian_xianqi |
 | driven_id: mengwa_kaixin |
Video generation flow
Emoji video generation requires two API calls: check portrait compliance and then generate the video.
-
Step 1: Image detection
Call the Emoji image detection API to verify portrait compliance and retrieve face and dynamic area coordinates.
-
Step 2: Video generation
Call the Emoji video generation API with the portrait image, coordinates from step 1, and a template ID from the list of template IDs.
Billing and rate limits
- For the free quota and unit price for the model, see Recommended models.
- For rate limits, see Rate limiting.