Video Generation

MuseV: An Open Source AI Video Generation Tool

by
MuseV: An Open Source AI Video Generation Tool

Introduction MuseV is a virtual human video generation framework based on diffusion models, featuring the following characteristics: Supports infinite length generation using a novel visual condition parallel denoising scheme, eliminating cumulative error issues, especially suitable for fixed camera position scenarios. Provides a pre-trained model for virtual human video generation trained on a character-type dataset. Supports … Read more

MultiTalk: KJ Achieves Over 6x Acceleration with Ultra-Realistic Digital Singing Avatars! Supports Realistic Cartoon and Animal Generalization for 15-Second Long Videos

by
MultiTalk: KJ Achieves Over 6x Acceleration with Ultra-Realistic Digital Singing Avatars! Supports Realistic Cartoon and Animal Generalization for 15-Second Long Videos

❝ 🌹Hello everyone! Welcome to PoLang‘s homepage. Thank you for your support and encouragement. On the road of AIGC exploration, I will be with you all the way. If you like it, please star and follow PoLang or scan the code at the end of the article to join the discussion group! 1: Introduction to … Read more

Asia’s First! Wuwen Xinqiong Wins Best Paper Award at FPGA’25 for Proposing the First Video Generation Large Model Inference IP, Significantly Enhancing Hardware Computing Power through Software-Hardware Collaboration

by
Asia's First! Wuwen Xinqiong Wins Best Paper Award at FPGA'25 for Proposing the First Video Generation Large Model Inference IP, Significantly Enhancing Hardware Computing Power through Software-Hardware Collaboration

Follow our public account to discover the beauty of CV technology The top international conference in the field of reconfigurable computing, FPGA 2025, has announced that this year’s Best Paper Award goes to Wuwen Xinqiong and the collaborative work on video generation large model inference IP, FlightVGM, from Shanghai Jiao Tong University and Tsinghua University. … Read more

Understanding ARM64 Inline Hooking Techniques

by
Understanding ARM64 Inline Hooking Techniques

/ Today’s Tech News / Recently, before Sora ignited the text-to-video track, domestic ByteDance also launched a revolutionary video model – Boximator. Unlike models like Gen-2 and Pink1.0, Boximator can precisely control the actions of characters or objects in the generated video through text. It was revealed that according to experimental data, Boximator maintains the … Read more