Latest Search
Quote
| Back Zoom + Zoom - | ||||
|
Meituan Open-Sources SOTA-Level Virtual Human Video Generation Model LongCat-Video-Avatar
Recommend 19 Positive 24 Negative 6 |
||||
|
||||
|
MEITUAN-W (03690.HK)'s Meituan LongCat team has officially released and open-sourced the SOTA-level virtual human video generation model, LongCat-Video-Avatar, according to Chinese media reports. Built on the LongCat-Video base model, LongCat-Video-Avatar continues the core design of "one model for multiple tasks". It natively supports Audio-Text-to-Video (AT2V), Audio-Text-Image-to-Video (ATI2V), and video continuation functions. With the underlying architecture having been upgraded, it has achieved breakthroughs in motion realism, long video stability, and identity consistency across three dimensions. AAStocks Financial News |
||||
Copied to Clipboard
 |
||||
