Showing 6 of 6 posts with this tag
Researchers introduced MemFlow, a dynamic memory mechanism for AI video generation that achieves 96.60 subject consistency and real-time inference to solve long-video narrative coherence issues.
AI startup HeyGen announced on January 8 that it has integrated its avatar model with OpenAI's Sora model, creating a groundbreaking talking avatar technology driven entirely by AI.
VIDU, a text-to-image video multimodal model developed by ShengShu Technology, has introduced a new feature called Subject Consistency.
ByteDance's video editing product CapCut's new brand Dreamina announced that its AI drawing and AI video creation functions have been fully launched.
The domestic entity behind the AI video generation tool HeyGen, Surreal AI, is currently planning to deregister its domestic company.
On February 10, ByteDance’s Doubao large AI model team, in collaboration with Beijing Jiaotong University and the University of Science and Technology of China, unveiled VideoWorld, a video generation model that has now been open-sourced.