UniAdapter: All-in-One Control for Flexible Video Generation

C Wang, P Hu, H Zhao, Y Guo, J Gu… - … on Circuits and …, 2025 - ieeexplore.ieee.org
Condition-based video generation aims to create video content based on given information
that describes specific subjects. However, most existing works can only utilize a single …

RepVideo: Rethinking Cross-Layer Representation for Video Generation

C Si, W Fan, Z Lv, Z Huang, Y Qiao, Z Liu - arxiv preprint arxiv …, 2025 - arxiv.org
Video generation has achieved remarkable progress with the introduction of diffusion
models, which have significantly improved the quality of generated videos. However, recent …

Diffusion as Shader: 3D-aware Video Diffusion for Versatile Video Generation Control

Z Gu, R Yan, J Lu, P Li, Z Dou, C Si, Z Dong… - arxiv preprint arxiv …, 2025 - arxiv.org
Diffusion models have demonstrated impressive performance in generating high-quality
videos from text prompts or images. However, precise control over the video generation …

FFA Sora, video generation as fundus fluorescein angiography simulator

X Wu, L Wang, R Chen, B Liu, W Zhang, X Yang… - arxiv preprint arxiv …, 2024 - arxiv.org
Fundus fluorescein angiography (FFA) is critical for diagnosing retinal vascular diseases,
but beginners often struggle with image interpretation. This study develops FFA Sora, a text …

LayerAnimate: Layer-specific Control for Animation

Y Yang, L Fan, Z Lin, F Wang, Z Zhang - arxiv preprint arxiv:2501.08295, 2025 - arxiv.org
Animated video separates foreground and background elements into layers, with distinct
processes for sketching, refining, coloring, and in-betweening. Existing video generation …

EchoVideo: Identity-Preserving Human Video Generation by Multimodal Feature Fusion

J Wei, S Yan, W Lin, B Liu, R Chen, M Guo - arxiv preprint arxiv …, 2025 - arxiv.org
Recent advancements in video generation have significantly impacted various downstream
applications, particularly in identity-preserving video generation (IPT2V). However, existing …

MSC: Multi-Scale Spatio-Temporal Causal Attention for Autoregressive Video Diffusion

X Xu, M Cao - arxiv preprint arxiv:2412.09828, 2024 - arxiv.org
Diffusion transformers enable flexible generative modeling for video. However, it is still
technically challenging and computationally expensive to generate high-resolution videos …