Long Video Generation Survey 2025

Project Overview

Total Projects: 33 | Categories: Video Generation, Diffusion Models, AI Video Synthesis

1. Video Poet - Google Research

17. InstructVideo

2. Goku - Saiyan World

26. Make Pixel Dance

5. SlowFast-VGen

6. StreamingT2V

7. World Simulator Story Presenter

8. FreeLong

9. Hierarchical Patch Diffusion Models

10. Kubrick - Multimodal Agent Collaborations

11. Moonshot - Show Lab

12. AtomoVideo

13. ART•V - Auto-Regressive Text-to-Video

14. VideoCrafter2 - AI Lab CVC

15. EvalCrafter

16. FlowVid

18. Snap Video

19. Fairy - Fast Parallelized Video-to-Video Synthesis

20. FlowZero

21.Meta Movie Gen

22. CVRR Evaluation Suite

23. Dreamix - Video Diffusion Models

24. StoryDiffusion

25. Phenaki

3. Runway Gen-4

4. ARLON - Autoregressive Long Video Generation

27. LayoutGPT

28. MCVD - Mask-Conditioned Video Diffusion

29. TATS - Time-Agnostic VQGAN and Time-Sensitive Transformer

30. VersVideo

31. MicroCinema

32. MEVG - ECCV 2024

33. Gen-L-Video

GitHub Repository Links

Direct links to all GitHub repositories and codebases mentioned in the survey

Flash Video - Foundation Vision

github.com/FoundationVision/FlashVideo

Reducio-VAE - Microsoft

github.com/microsoft/Reducio-VAE

Mask2DiT - Multi-Scene Long Video Generation

github.com/Tianhao-Qi/Mask2DiT

HunyuanVideo - Tencent

github.com/Tencent-Hunyuan/HunyuanVideo

Video-Infinity

github.com/Yuanshi9815/Video-Infinity

RV GAN

github.com/GuptaSonam/RV-GAN

VideoTetris

github.com/YangLing0818/VideoTetris

Vidgen

github.com/Capstonelingam/vidgen

AtomoVideo (Duplicate)

github.com/atomo-video/atomo-video.github.io

ARLDM - Auto-Regressive Latent Diffusion Models

github.com/xichenpan/ARLDM

MM Diffusion

github.com/researchmm/MM-Diffusion

Upscale-A-Video

github.com/sczhou/Upscale-A-Video

Mochi - Genmo AI

github.com/genmoai/mochi

VideoBooth

github.com/Vchitect/VideoBooth

AVID - Any-Length Video Inpainting

github.com/zhang-zx/AVID

VGen - Ali VILab

github.com/ali-vilab/VGen

BIVDiff - Bridging Image and Video Diffusion

github.com/MCG-NJU/BIVDiff

Peekaboo - Microsoft

github.com/microsoft/Peekaboo

LongVideoGAN - NVlabs

github.com/NVlabs/long-video-gan

MVBench

github.com/OpenGVLab/Ask-Anything/blob/main/video_chat2/MVBENCH.md

3D-VLA

github.com/UMass-Embodied-AGI/3D-VLA

MeBt

github.com/Ugness/MeBT

DIGAN

github.com/sihyun-yu/digan

StyleGAN-V

github.com/universome/stylegan-v

NUWA-Infinity - Microsoft

github.com/microsoft/NUWA/blob/main/NUWAInfinity.md

CogVideoX - THUDM

github.com/THUDM/CogVideo

FlexiFilm

github.com/Y-ichen/FlexiFilm?tab=readme-ov-file

Make It 4D

github.com/leoShen917/Make-It-4D

SceneScape

github.com/RafailFridman/SceneScape

FreeNoise - Longer Video Diffusion

github.com/AILab-CVC/FreeNoise

Control Video

github.com/YBYBZhang/ControlVideo

LFDM - Latent Flow Diffusion Models

github.com/nihaomiao/CVPR23_LFDM

Glober

github.com/iva-mzsun/GLOBER

ControlNet

github.com/lllyasviel/ControlNet

Sora - Open AI

github.com/burmba/Open-Ai-Sora

Make A Story - UBC Vision

github.com/ubc-vision/Make-A-Story

MAVIN

github.com/18445864529/MAVIN

SEINE

github.com/Vchitect/SEINE

VideoCrafter

github.com/AILab-CVC/VideoCrafter

WorldGPT

github.com/DCDmllm/WorldGPT

Vlogger

github.com/Vchitect/Vlogger

LLM-grounded Video Diffusion Models

github.com/TonyLianLong/LLM-groundedVideoDiffusion

Mora

github.com/lichao-sun/Mora

Free Bloom

github.com/SooLab/Free-Bloom

VideoDirectorGPT

github.com/HL-hanlin/VideoDirectorGPT