7 papers
Delving into Latent Spectral Biasing of Video VAEs for Superior Diffusability
Shizhan Liu, Xinran Deng, Zhuoyi Yang +3
Latent diffusion models pair VAEs with diffusion backbones, and the structure of VAE latents strongly influences the difficulty of diffusion training. However, existing video VAEs…
SCAIL: Towards Studio-Grade Character Animation via In-Context Learning of 3D-Consistent Pose Representations
Wenhao Yan, Sheng Ye, Zhuoyi Yang +6
Achieving controllable character animation that meets studio-grade standards remains challenging despite recent progress. Existing approaches can transfer motion from a driving vid…
Kaleido: Open-Sourced Multi-Subject Reference Video Generation Model
Zhenxing Zhang, Jiayan Teng, Zhuoyi Yang +6
We present Kaleido, a subject-to-video~(S2V) generation framework, which aims to synthesize subject-consistent videos conditioned on multiple reference images of target subjects. D…
VisionReward: Fine-Grained Multi-Dimensional Human Preference Learning for Image and Video Generation
Jiazheng Xu, Yu Huang, Jiale Cheng +19
Visual generative models have achieved remarkable progress in synthesizing photorealistic images and videos, yet aligning their outputs with human preferences across critical dimen…
VPO: Aligning Text-to-Video Generation Models with Prompt Optimization
Jiale Cheng, Ruiliang Lyu, Xiaotao Gu +9
Video generation models have achieved remarkable progress in text-to-video tasks. These models are typically trained on text-video pairs with highly detailed and carefully crafted…
Concat-ID: Towards Universal Identity-Preserving Video Synthesis
Yong Zhong, Zhuoyi Yang, Jiayan Teng +2
We present Concat-ID, a unified framework for identity-preserving video generation. Concat-ID employs variational autoencoders to extract image features, which are then concatenate…