Pixel-space video generation with U-JiT
cs.CV
Submitted: 2026-11-03
Updated: 2026-11-03
Code: https://github.com/LTH14/JiT
Terminology
Sources
- Stable Video Diffusion: Scaling Latent Video Diffusion Models to Large Datasets
- A Short Note about Kinetics-600
- Asymmetric Flow Models
- DC-VideoGen: Efficient Video Generation with Deep Compression Video Autoencoder
- On the Importance of Noise Scheduling for Diffusion Models
- Diffusion Autoencoders are Scalable Image Tokenizers
- L2P: Unlocking Latent Potential for Pixel Generation
- End-to-End Training for Unified Tokenization and Latent Denoising
- DeRA: Decoupled Representation Alignment for Video Tokenization
- LTX-Video: Realtime Video Latent Diffusion
- Unified Latents (UL): How to train your latents
- Imagen Video: High Definition Video Generation with Diffusion Models
- Auto-Encoding Variational Bayes
- HunyuanVideo: A Systematic Framework For Large Video Generative Models
- PiD: Fast and High-Resolution Latent Decoding with Pixel Diffusion
- Cosmos World Foundation Model Platform for Physical AI
- WaiT for the Signal: Simple Frequency-Aware Flow-Matching
- Movie Gen: A Cast of Media Foundation Models
- GLU Variants Improve Transformer
- Improved Baselines with Representation Autoencoders
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