AnimateAnyone generates character action videos from character images and action templates. It consists of three independent models: "AnimateAnyone-detect" for detecting character image compliance, "AnimateAnyone-template" for generating action templates, and "AnimateAnyone" for generating character videos.
This document applies only to the China (Beijing) region. To use these models, you must use an API key from the China (Beijing) region.
Model overview
Model introduction
AnimateAnyone-detect is an image detection model that checks whether an input image meets the character image specifications for the AnimateAnyone model.
AnimateAnyone-template is an action template generation model that extracts character actions from a motion video to generate an action template compatible with the AnimateAnyone model.
AnimateAnyone is a character video generation model that generates character action videos from character images and action templates.
Performance showcase
Input: Character image | Input: Action video | Output (image background) | Output (video background) |
| |||
|
The preceding examples were generated by the Tongyi App, which integrates AnimateAnyone.
The videos generated by the AnimateAnyone model do not include audio.
Billing and rate limiting
Mode | Model | Unit price | QPS limit for task submission API | Number of concurrent tasks |
Model call | animate-anyone-detect-gen2 | Model call, pay-as-you-go: $0.000574/image | 5 | No limit for sync APIs |
animate-anyone-template-gen2 | Model call, pay-as-you-go: $0.011469/second | 1 (At any given time, only one job is running. Other jobs in the queue are waiting.) | ||
animate-anyone-gen2 |
Prerequisites
You must activate the service and obtain an API key: Get an API key.
Model calling
The AnimateAnyone series of models supports pay-as-you-go calls.
When you call a model, you must specify its name. Call the models in the following order:
a. Call the "AnimateAnyone-detect" model to confirm that the input character image meets the required specifications. For more information, see AnimateAnyone image detection.
b. Call the "AnimateAnyone-template" model and provide a motion video to generate an action template. For more information, see AnimateAnyone action template generation.
c. Call the "AnimateAnyone" model. Provide the character image that passed detection and the action template ID to generate a video. For more information, see AnimateAnyone video generation.