Research on emotion animation generation based on AIGC tools: Personalized expression and multi-level encoding strategy
Yitian Liu, Zhou Zhao, Kun Qi · 2026
Read Research on emotion animation generation based on AIGC tools: Personalized expression and multi-level encoding strategy by Yitian Liu, Zhou Zhao, Kun Qi (2026) in the Tower of Babel, a free online library of public-domain works preserved in clean, searchable text. No sign-up. The full text is served as a plain-text file at a predictable URL, where text is present: https://antarctic-labs.com/tower-of-babel/plos-pone-0356895.txt.
Description
Yitian Liu, Zhou Zhao, and Kun Qi built a way to generate cartoon animations with strong, controllable feelings. They used generative AI tools. Two chronic weaknesses drove the work. Feelings often drift off-script, and characters feel generic. Their 2026 study layered prompts in a hierarchy. Each request was encoded along three lines: the feeling, the behavior, and the style. A language model read the request, and a video tool made the images.
Test runs held face, movement rhythm, and color mood in close agreement with the requested feeling. Different user profiles produced visibly different expression sizes, tempos, and styles. That showed the personal touch worked. The layered prompting also improved movement logic and fine gesture detail. The authors offer the scheme as a template for controllable creative AI.
Catalog record
| CREATOR | Yitian Liu, Zhou Zhao, Kun Qi |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 86913 |
| LICENSE | CC_BY |
| RIGHTS | CC BY |
| SOURCE | PLOS |