CatPortrait: Taming Video Generative Models for Portrait Animation via In-context Conditioning

arXiv:2610.14957 · cs.CV · Submitted 2026-10-10 · Read on arXiv

cs.CV

Submitted: 2026-10-10

Updated: 2026-10-10

Comments: Accepted to PRCV 2026

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Terminology

• Generative Model — 1× in this paper · explained in 2 episodes
• Generative Models — 1× in this paper · explained in 3 episodes

Sources

• VideoCanvas: Unified Video Completion from Arbitrary Spatiotemporal Patches via In-Context Conditioning
• CatVTON: Concatenation Is All You Need for Virtual Try-On with Diffusion Models
• Hallo2: Long-Duration and High-Resolution Audio-Driven Portrait Image Animation
• Video Diffusion Transformers are In-Context Learners
• Dual Audio-Centric Modality Coupling for Talking Head Generation
• EditVerse: Unifying Image and Video Editing and Generation with In-Context Learning
• FullDiT: Multi-Task Video Generative Foundation Model with Full Attention
• HunyuanVideo: A Systematic Framework For Large Video Generative Models
• Learning to Credit the Right Steps: Objective-aware Process Optimization for Visual Generation
• Reward-Aware Trajectory Shaping for Few-step Visual Generation
• Rethinking Reward Signals in Video GRPO: When Scores Become Targets
• AMMKD: Adaptive Multimodal Multi-teacher Distillation for Lightweight Vision-Language Models
• TeleBoost: A Systematic Alignment Framework for High-Fidelity, Controllable, and Robust Video Generation
• Flow Matching for Generative Modeling
• DiffTalker: Co-driven audio-image diffusion for talking faces via intermediate landmarks
• SMIRK: 3D Facial Expressions through Analysis-by-Neural-Synthesis
• DiffTalk: Crafting Diffusion Models for Generalized Audio-Driven Portraits Animation
• Human Motion Diffusion Model
• Wan: Open and Advanced Large-Scale Video Generative Models
• AniPortrait: Audio-Driven Synthesis of Photorealistic Portrait Animation

Related papers

• Loss Knows Best: Detecting Annotation Errors in Videos via Loss Trajectories
• AnchorWeave: World-Consistent Video Generation with Retrieved Local Spatial Memories
• Benchmarking the Robustness of Foundation Models for Mammography under Domain Shift
• MambaX-Net: Dual-Input Mamba-Enhanced Cross-Attention Network for Longitudinal MRI Segmentation
• TeleOCR: Navigating Document Parsing Across Digital and Camera-Captured Documents
• A Survey on Efficient Vision-Language-Action Models