Custom Forcing: Training-Free Subject Customization for Autoregressive Video Generation
cs.CV
Submitted: 2026-10-02
Updated: 2026-10-05
Comments: 31 pages. Project page: https://gustn9609.github.io/custom-forcing/
Project page: https://gustn9609.github.io/custom-forcing
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Sources
- Qwen3-VL Technical Report
- SkyReels-V2: Infinite-length Film Generative Model
- Context Forcing: Consistent Autoregressive Video Generation with Long Context
- AdaState: Self-Evolving Anchors for Streaming Video Generation
- SkyReels-A2: Compose Anything in Video Diffusion Transformers
- An Image is Worth One Word: Personalizing Text-to-Image Generation using Textual Inversion
- ID-Animator: Zero-Shot Identity-Preserving Human Video Generation
- Prompt-to-Prompt Image Editing with Cross Attention Control
- Classifier-Free Diffusion Guidance
- HunyuanCustom: A Multimodal-Driven Architecture for Customized Video Generation
- Memory Forcing: Spatio-Temporal Memory for Consistent Scene Generation on Minecraft
- ConceptMaster: Multi-Concept Video Customization on Diffusion Transformer Models Without Test-Time Tuning
- Forcing-KV: Hybrid KV Cache Compression for Efficient Autoregressive Video Diffusion Models
- V-Warper: Appearance-Consistent Video Diffusion Personalization via Value Warping
- SkyReels-V3 Technique Report
- Rolling Sink: Bridging Limited-Horizon Training and Open-Ended Testing in Autoregressive Video Diffusion
- Advancing Narrative Long Video Generation via Training-Free Identity-Aware Memory
- Light Forcing: Accelerating Autoregressive Video Diffusion via Sparse Attention
- MAGI-1: Autoregressive Video Generation at Scale
- Training-Free Consistent Text-to-Image Generation
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