6 papers · 1 filter
MotionStone: Decoupled Motion Intensity Modulation with Diffusion Transformer for Image-to-Video Generation
Shuwei Shi, Biao Gong, Xi Chen +9
The image-to-video (I2V) generation is conditioned on the static image, which has been enhanced recently by the motion intensity as an additional control signal. These motion-aware…
Mimir: Improving Video Diffusion Models for Precise Text Understanding
Shuai Tan, Biao Gong, Yutong Feng +6
Text serves as the key control signal in video generation due to its narrative nature. To render text descriptions into video clips, current video diffusion models borrow features…
Panther: Illuminate the Sight of Multimodal LLMs with Instruction-Guided Visual Prompts
Honglin Li, Yuting Gao, Chenglu Zhu +3
Multimodal large language models (MLLMs) are closing the gap to human visual perception capability rapidly, while, still lag behind on attending to subtle images details or locatin…
LumiSculpt: Enabling Consistent Portrait Lighting in Video Generation
Yuxin Zhang, Dandan Zheng, Biao Gong +5
Lighting plays a pivotal role in ensuring the naturalness and aesthetic quality of video generation. However, the impact of lighting is deeply coupled with other factors of videos,…
Animate-X: Universal Character Image Animation with Enhanced Motion Representation
Shuai Tan, Biao Gong, Xiang Wang +6
Character image animation, which generates high-quality videos from a reference image and target pose sequence, has seen significant progress in recent years. However, most existin…
Accelerating Pre-training of Multimodal LLMs via Chain-of-Sight
Ziyuan Huang, Kaixiang Ji, Biao Gong +6
This paper introduces Chain-of-Sight, a vision-language bridge module that accelerates the pre-training of Multimodal Large Language Models (MLLMs). Our approach employs a sequence…