| W.A.L.T-XL (class-conditional) |
- FVD16
- 36±2
|
Photorealistic Video Generation with Diffusion Models
2023-12-11 |
연결 없음 |
| Video-GPT |
- FVD16
- 53
|
Video-GPT via Next Clip Diffusion
2025-05-18 |
코드 1 |
| LARP |
- FVD16
- 57
|
LARP: Tokenizing Videos with a Learned Autoregressive Generative Prior
2024-10-28 |
코드 1 |
| FAR |
- FVD16
- 57
|
Long-Context Autoregressive Video Modeling with Next-Frame Prediction
2025-03-25 |
코드 1 |
| MAGVIT-v2 |
- FVD16
- 58±3
|
Language Model Beats Diffusion -- Tokenizer is Key to Visual Generation
2023-10-09 |
코드 1 · 코드 2 · 코드 3 |
| HPDM-L |
- Inception Score
- 87.68
- FVD16
- 66.32
|
Hierarchical Patch Diffusion Models for High-Resolution Video Generation
2024-06-12 |
연결 없음 |
| MAGVIT (-L-CG, 128x128, class-conditional) |
- Inception Score
- 89.27±0.15
- FVD16
- 76±2
|
MAGVIT: Masked Generative Video Transformer
2022-12-10 |
코드 1 |
| Make-A-Video (Finetuning, 256x256, class-conditional) |
- Inception Score
- 82.55
- FVD16
- 81.25
|
Make-A-Video: Text-to-Video Generation without Text-Video Data
2022-09-29 |
코드 1 · 코드 2 |
| ACDiT |
- FVD16
- 90
|
ACDiT: Interpolating Autoregressive Conditional Modeling and Diffusion Transformer
2024-12-10 |
코드 1 |
| MAGVIT-v2 (AR) |
- FVD16
- 109
|
Language Model Beats Diffusion -- Tokenizer is Key to Visual Generation
2023-10-09 |
코드 1 · 코드 2 · 코드 3 |
| REGIS-Fuse (Finetuning, 128x128, text-conditional) |
- FVD16
- 141
|
REGIS: Refining Generated Videos via Iterative Stylistic Redesigning
2023-11-03 |
코드 1 |
| MAGVIT (-B-CG, 128x128, class-conditional) |
- Inception Score
- 83.55±0.14
- FVD16
- 159±2
|
MAGVIT: Masked Generative Video Transformer
2022-12-10 |
코드 1 |
| Latte + LeanVAE |
- FVD16
- 164.45
|
LeanVAE: An Ultra-Efficient Reconstruction VAE for Video Diffusion Models
2025-03-18 |
코드 1 |
| VideoFusion (128x128, class-conditional) |
- Inception Score
- 80.03
- FVD16
- 173
|
VideoFusion: Decomposed Diffusion Models for High-Quality Video Generation
2023-03-15 |
코드 1 · 코드 2 |
| OmniTokenizer-AR |
- FVD16
- 191
|
OmniTokenizer: A Joint Image-Video Tokenizer for Visual Generation
2024-06-13 |
코드 1 |
| VideoFusion (128x128, unconditional) |
- Inception Score
- 72.22
- FVD16
- 220
|
VideoFusion: Decomposed Diffusion Models for High-Quality Video Generation
2023-03-15 |
코드 1 · 코드 2 |
| PixelDance (256x256, text-conditional) |
- Inception Score
- 42.10
- FVD16
- 242.82
|
Make Pixels Dance: High-Dynamic Video Generation
2023-11-18 |
연결 없음 |
| W.A.L.T 3B (text-conditional) |
- Inception Score
- 35.1
- FVD16
- 258.1
|
Photorealistic Video Generation with Diffusion Models
2023-12-11 |
연결 없음 |
| MAGVIT (AR) |
- FVD16
- 265
|
MAGVIT: Masked Generative Video Transformer
2022-12-10 |
코드 1 |
| Video-LaVIT |
- Inception Score
- 44.26
- FVD16
- 280.57
|
Video-LaVIT: Unified Video-Language Pre-training with Decoupled Visual-Motional Tokenization
2024-02-05 |
코드 1 |
| VIDM (256x256, unconditional) |
- FVD16
- 294.7
- FVD128
- 1531.9
|
VIDM: Video Implicit Diffusion Models
2022-12-01 |
코드 1 |
| CogVideo (128x128, class-conditional) |
- Inception Score
- 51.11
- FVD16
- 305
|
CogVideo: Large-scale Pretraining for Text-to-Video Generation via Transformers
2022-05-29 |
코드 1 |
| PYoCo (Zero-shot, 64x64, unconditional) |
- Inception Score
- 60.01
- FVD16
- 310
|
Preserve Your Own Correlation: A Noise Prior for Video Diffusion Models
2023-05-17 |
연결 없음 |
| MMVG (128x128, class-conditional) |
- Inception Score
- 73.7
- FVD16
- 328
|
Tell Me What Happened: Unifying Text-guided Video Completion via Multimodal Masked Video Generation
2022-11-23 |
코드 1 |
| TATS (128x128, class-conditional) |
- Inception Score
- 79.28
- FVD16
- 332
|
Long Video Generation with Time-Agnostic VQGAN and Time-Sensitive Transformer
2022-04-07 |
코드 1 |
| Lumiere (Zero-shot. 1024x1024, text-conditional) |
- Inception Score
- 37.54
- FVD16
- 332.49
|
Lumiere: A Space-Time Diffusion Model for Video Generation
2024-01-23 |
코드 1 |
| GridDiff (Zero-shot) |
- Inception Score
- 62.88
- FVD16
- 340.0
|
Grid Diffusion Models for Text-to-Video Generation
2024-03-30 |
연결 없음 |
| VideoAssembler (Zero-shot, 256x256, class-conditional) |
- Inception Score
- 48.01
- FVD16
- 346.84
|
MagDiff: Multi-Alignment Diffusion for High-Fidelity Video Generation and Editing
2023-11-29 |
코드 1 |
| VideoPoet (text-conditional) |
- Inception Score
- 38.44
- FVD16
- 355
|
VideoPoet: A Large Language Model for Zero-Shot Video Generation
2023-12-21 |
연결 없음 |
| PYoCo (Zero-shot, 64x64, text-conditional) |
- Inception Score
- 47.76
- FVD16
- 355.19
|
Preserve Your Own Correlation: A Noise Prior for Video Diffusion Models
2023-05-17 |
연결 없음 |