TokenStream: Multi-Subject Personalized Video Generation with Token-wise LoRA and Guided Attention
cs.CV
Submitted: 2026-11-12
Updated: 2026-11-12
Terminology
Sources
- World Simulation with Video Foundation Models for Physical AI
- Stable Video Diffusion: Scaling Latent Video Diffusion Models to Large Datasets
- OmniVCus: Feedforward Subject-driven Video Customization with Multimodal Control Conditions
- VideoDreamer: Customized Multi-Subject Text-to-Video Generation with Disen-Mix Finetuning on Language-Video Foundation Models
- UniMax: Fairer and more Effective Language Sampling for Large-Scale Multilingual Pretraining
- CINEMA: Coherent Multi-Subject Video Generation via MLLM-Based Guidance
- MAGREF: Masked Guidance for Any-Reference Video Generation with Subject Disentanglement
- SkyReels-A2: Compose Anything in Video Diffusion Transformers
- An Image is Worth One Word: Personalizing Text-to-Image Generation using Textual Inversion
- Encoder-based Domain Tuning for Fast Personalization of Text-to-Image Models
- AnimateDiff: Animate Your Personalized Text-to-Image Diffusion Models without Specific Tuning
- LTX-Video: Realtime Video Latent Diffusion
- HunyuanCustom: A Multimodal-Driven Architecture for Customized Video Generation
- PolyVivid: Vivid Multi-Subject Video Generation with Cross-Modal Interaction and Enhancement
- VACE: All-in-One Video Creation and Editing
- HunyuanVideo: A Systematic Framework For Large Video Generative Models
- BLIP-Diffusion: Pre-trained Subject Representation for Controllable Text-to-Image Generation and Editing
- BindWeave: Subject-Consistent Video Generation via Cross-Modal Integration
- JarvisArt: Liberating Human Artistic Creativity via an Intelligent Photo Retouching Agent
- Phantom: Subject-consistent video generation via cross-modal alignment
Related papers
- TEA: Text Encoder Alignment for Robust Concept Erasure in Text-to-Image Models
- Do Egocentric Video-Language Models Capture Both Hand- and Object-Centric Cues?
- Aura: Consistent Multi-Subject Video Generation via VLM-Grounded Semantic Alignment
- PVRF: All-in-one Adverse Weather Removal via Prior-modulated and Velocity-constrained Rectified Flow
- DLWM: Diverse Latent World Models for Efficient Multimodal Reasoning
- Out of Sight, Still in Mind: Token Compression for Omni-LLMs