Awesome Video Diffusion

A curated list of recent diffusion models for video generation, editing, restoration, understanding, nerf, etc.

(Source: Make-A-Video, Tune-A-Video, and Fate/Zero.)

Table of Contents

• Open-source Toolboxes and Foundation Models
• Video Generation
• Video Editing
• Long-form Video Generation and Completion
• Human or Subject Motion
• Video Enhancement and Restoration
• 3D / NeRF
• Video Understanding
• Healthcare and Biology

Open-source Toolboxes and Foundation Models

• Hotshot-XL (text-to-GIF)
  

• zeroscope_v2
  

• I2VGen-XL (image-to-video / video-to-video)
  

• text-to-video-synthesis-colab
  

• VideoCrafter: A Toolkit for Text-to-Video Generation and Editing
  

• ModelScope (Text-to-video synthesis)
  

• Diffusers (Text-to-video synthesis)
  

Video Generation

• Emu Video: Factorizing Text-to-Video Generation by Explicit Image Conditioning (Nov., 2023)
  

• Optimal Noise pursuit for Augmenting Text-to-Video Generation (Nov., 2023)
  

• VideoDreamer: Customized Multi-Subject Text-to-Video Generation with Disen-Mix Finetuning (Nov., 2023)
  

• SEINE: Short-to-Long Video Diffusion Model for Generative Transition and Prediction (Oct., 2023)
  

• FreeNoise: Tuning-Free Longer Video Diffusion Via Noise Rescheduling (Oct., 2023)
  

• DynamiCrafter: Animating Open-domain Images with Video Diffusion Priors (Oct., 2023)
  

• LAMP: Learn A Motion Pattern for Few-Shot-Based Video Generation (Oct., 2023)
  

• Show-1: Marrying Pixel and Latent Diffusion Models for Text-to-Video Generation (Sep., 2023)
  

• MotionDirector: Motion Customization of Text-to-Video Diffusion Models (Sep., 2023)
  

• LAVIE: High-Quality Video Generation with Cascaded Latent Diffusion Models (Sep., 2023)
  

• Diverse and Aligned Audio-to-Video Generation via Text-to-Video Model Adaptation (Sep., 2023)
  

• Free-Bloom: Zero-Shot Text-to-Video Generator with LLM Director and LDM Animator (Sep., 2023)
  

• Hierarchical Masked 3D Diffusion Model for Video Outpainting (Sep., 2023)
  

• Reuse and Diffuse: Iterative Denoising for Text-to-Video Generation (Sep., 2023)
  

• VideoGen: A Reference-Guided Latent Diffusion Approach for High Definition Text-to-Video Generation (Sep., 2023)
  

• MagicAvatar: Multimodal Avatar Generation and Animation (Aug., 2023)
  

• Empowering Dynamics-aware Text-to-Video Diffusion with Large Language Models (Aug., 2023)
  

• SimDA: Simple Diffusion Adapter for Efficient Video Generation (Aug., 2023)
  

• ModelScope Text-to-Video Technical Report (Aug., 2023)
  

• Dual-Stream Diffusion Net for Text-to-Video Generation (Aug., 2023)
  

• DragNUWA: Fine-grained Control in Video Generation by Integrating Text, Image, and Trajectory (Aug., 2023)
  

• InternVid: A Large-scale Video-Text Dataset for Multimodal Understanding and Generation (Jul., 2023)
  

• Animate-A-Story: Storytelling with Retrieval-Augmented Video Generation (Jul., 2023)
  

• AnimateDiff: Animate Your Personalized Text-to-Image Diffusion Models without Specific Tuning (Jul., 2023)
  

• DisCo: Disentangled Control for Referring Human Dance Generation in Real World (Jul., 2023)
  

• VideoComposer: Compositional Video Synthesis with Motion Controllability (Jun., 2023)
  

• Probabilistic Adaptation of Text-to-Video Models (Jun., 2023)
  

• Make-Your-Video: Customized Video Generation Using Textual and Structural Guidance (Jun., 2023)
  

• Gen-L-Video: Multi-Text to Long Video Generation via Temporal Co-Denoising (May, 2023)
  

• Control-A-Video: Controllable Text-to-Video Generation with Diffusion Models (May, 2023)
  

• ControlVideo: Training-free Controllable Text-to-Video Generation (May, 2023)
  

• Cinematic Mindscapes: High-quality Video Reconstruction from Brain Activity (May, 2023)
  

• Any-to-Any Generation via Composable Diffusion (May, 2023)
  

• VideoFactory: Swap Attention in Spatiotemporal Diffusions for Text-to-Video Generation (May, 2023)
  

• Preserve Your Own Correlation: A Noise Prior for Video Diffusion Models (May, 2023)
  

• Motion-Conditioned Diffusion Model for Controllable Video Synthesis (Apr., 2023)
  

• LaMD: Latent Motion Diffusion for Video Generation (Apr., 2023)
  

• Align your Latents: High-Resolution Video Synthesis with Latent Diffusion Models (CVPR 2023)
  

• Text2Performer: Text-Driven Human Video Generation (Apr., 2023)
  

• Generative Disco: Text-to-Video Generation for Music Visualization (Apr., 2023)
  

• Latent-Shift: Latent Diffusion with Temporal Shift (Apr., 2023)
  

• DreamPose: Fashion Image-to-Video Synthesis via Stable Diffusion (Apr., 2023)
  

• Follow Your Pose: Pose-Guided Text-to-Video Generation using Pose-Free Videos (Apr., 2023)
  

• Physics-Driven Diffusion Models for Impact Sound Synthesis from Videos (CVPR 2023)
  

• Seer: Language Instructed Video Prediction with Latent Diffusion Models (Mar., 2023)
  

• Text2video-Zero: Text-to-Image Diffusion Models Are Zero-Shot Video Generators (Mar., 2023)
  

• Conditional Image-to-Video Generation with Latent Flow Diffusion Models (CVPR 2023)
  

• Decomposed Diffusion Models for High-Quality Video Generation (CVPR 2023)
  

• Video Probabilistic Diffusion Models in Projected Latent Space (CVPR 2023)
  

• Learning 3D Photography Videos via Self-supervised Diffusion on Single Images (Feb., 2023)
  

• Structure and Content-Guided Video Synthesis With Diffusion Models (Feb., 2023)
  

• Tune-A-Video: One-Shot Tuning of Image Diffusion Models for Text-to-Video Generation (Dec., 2022)
  

• Mm-Diffusion: Learning Multi-Modal Diffusion Models for Joint Audio and Video Generation (CVPR 2023)
  

• Magvit: Masked Generative Video Transformer (Dec., 2022)
  

• VIDM: Video Implicit Diffusion Models (AAAI 2023)
  

• Latent Video Diffusion Models for High-Fidelity Video Generation With Arbitrary Lengths (Nov., 2022)
  

• SinFusion: Training Diffusion Models on a Single Image or Video (Nov., 2022)
  

• MagicVideo: Efficient Video Generation With Latent Diffusion Models (Nov., 2022)
  

• Imagen Video: High Definition Video Generation With Diffusion Models (Oct., 2022)
  

• Make-A-Video: Text-to-Video Generation without Text-Video Data (ICLR 2023)
  

• Diffusion Models for Video Prediction and Infilling (TMLR 2022)
  

• McVd: Masked Conditional Video Diffusion for Prediction, Generation, and Interpolation (NeurIPS 2022)
  

• Video Diffusion Models (Apr., 2022)
  

• Diffusion Probabilistic Modeling for Video Generation (Mar., 2022)
  

Video Editing

• Fuse Your Latents: Video Editing with Multi-source Latent Diffusion Models (Oct., 2023)
  

• DynVideo-E: Harnessing Dynamic NeRF for Large-Scale Motion- and View-Change Human-Centric Video Editing (Oct., 2023)
  

• Ground-A-Video: Zero-shot Grounded Video Editing using Text-to-image Diffusion Models (Oct., 2023)
  

• CCEdit: Creative and Controllable Video Editing via Diffusion Models (Sep., 2023)
  

• MagicProp: Diffusion-based Video Editing via Motion-aware Appearance Propagation (Sep., 2023)
  

• MagicEdit: High-Fidelity and Temporally Coherent Video Editing (Aug., 2023)
  

• StableVideo: Text-driven Consistency-aware Diffusion Video Editing (ICCV 2023)
  

• CoDeF: Content Deformation Fields for Temporally Consistent Video Processing (Aug., 2023)
  

• TokenFlow: Consistent Diffusion Features for Consistent Video Editing (Jul., 2023)
  

• INVE: Interactive Neural Video Editing (Jul., 2023)
  

• VidEdit: Zero-Shot and Spatially Aware Text-Driven Video Editing (Jun., 2023)
  

• Rerender A Video: Zero-Shot Text-Guided Video-to-Video Translation (SIGGRAPH Asia 2023)
  

• ControlVideo: Adding Conditional Control for One Shot Text-to-Video Editing (May, 2023)
  

• Make-A-Protagonist: Generic Video Editing with An Ensemble of Experts (May, 2023)
  

• Soundini: Sound-Guided Diffusion for Natural Video Editing (Apr., 2023)
  

• Zero-Shot Video Editing Using Off-the-Shelf Image Diffusion Models (Mar., 2023)
  

• Edit-A-Video: Single Video Editing with Object-Aware Consistency (Mar., 2023)
  

• FateZero: Fusing Attentions for Zero-shot Text-based Video Editing (Mar., 2023)
  

• Pix2video: Video Editing Using Image Diffusion (Mar., 2023)
  

• Video-P2P: Video Editing with Cross-attention Control (Mar., 2023)
  

• Dreamix: Video Diffusion Models Are General Video Editors (Feb., 2023)
  

• Shape-Aware Text-Driven Layered Video Editing (Jan., 2023)
  

• Speech Driven Video Editing via an Audio-Conditioned Diffusion Model (Jan., 2023)
  

• Diffusion Video Autoencoders: Toward Temporally Consistent Face Video Editing via Disentangled Video Encoding (CVPR 2023)
  

Long-form Video Generation and Completion

• MCVD: Masked Conditional Video Diffusion for Prediction, Generation, and Interpolation (NeurIPS 2022)
  

• NUWA-XL: Diffusion over Diffusion for eXtremely Long Video Generation (Mar., 2023)
  

• Flexible Diffusion Modeling of Long Videos (May, 2022)
  

Human or Subject Motion

• Avatars Grow Legs: Generating Smooth Human Motion from Sparse Tracking Inputs with Diffusion Model (CVPR 2023)
  

• InterGen: Diffusion-based Multi-human Motion Generation under Complex Interactions (Apr., 2023)
  

• ReMoDiffuse: Retrieval-Augmented Motion Diffusion Model (Apr., 2023)
  

• Human Motion Diffusion as a Generative Prior (Mar., 2023)
  

• Can We Use Diffusion Probabilistic Models for 3d Motion Prediction? (Feb., 2023)
  

• Single Motion Diffusion (Feb., 2023)
  

• HumanMAC: Masked Motion Completion for Human Motion Prediction (Feb., 2023)
  

• DiffMotion: Speech-Driven Gesture Synthesis Using Denoising Diffusion Model (Jan., 2023)
  

• Modiff: Action-Conditioned 3d Motion Generation With Denoising Diffusion Probabilistic Models (Jan., 2023)
  

• Unifying Human Motion Synthesis and Style Transfer With Denoising Diffusion Probabilistic Models (GRAPP 2023)
  

• Executing Your Commands via Motion Diffusion in Latent Space (CVPR 2023)
  

• Pretrained Diffusion Models for Unified Human Motion Synthesis (Dec., 2022)
  

• PhysDiff: Physics-Guided Human Motion Diffusion Model (Dec., 2022)
  

• BeLFusion: Latent Diffusion for Behavior-Driven Human Motion Prediction (Dec., 2022)
  

• Listen, Denoise, Action! Audio-Driven Motion Synthesis With Diffusion Models (Nov. 2022)
  

• Diffusion Motion: Generate Text-Guided 3d Human Motion by Diffusion Model (ICASSP 2023)
  

• Human Joint Kinematics Diffusion-Refinement for Stochastic Motion Prediction (Oct., 2022)
  

• Human Motion Diffusion Model (ICLR 2023)
  

• FLAME: Free-form Language-based Motion Synthesis & Editing (AAAI 2023)
  

• MotionDiffuse: Text-Driven Human Motion Generation with Diffusion Model (Aug., 2022)
  

• Stochastic Trajectory Prediction via Motion Indeterminacy Diffusion (CVPR 2022)
  

Video Enhancement and Restoration

• LDMVFI: Video Frame Interpolation with Latent Diffusion Models (Mar., 2023)
  

• CaDM: Codec-aware Diffusion Modeling for Neural-enhanced Video Streaming (Nov., 2022)
  

3D / NeRF

• Text2NeRF: Text-Driven 3D Scene Generation with Neural Radiance Fields (May, 2023)
  

• RoomDreamer: Text-Driven 3D Indoor Scene Synthesis with Coherent Geometry and Texture (May, 2023)
  

• NeuralField-LDM: Scene Generation with Hierarchical Latent Diffusion Models (CVPR 2023)
  

• Single-Stage Diffusion NeRF: A Unified Approach to 3D Generation and Reconstruction (Apr., 2023)
  

• Instruct-NeRF2NeRF: Editing 3D Scenes with Instructions (Mar., 2023)
  

• DiffusioNeRF: Regularizing Neural Radiance Fields with Denoising Diffusion Models (Feb., 2023)
  

• NerfDiff: Single-image View Synthesis with NeRF-guided Distillation from 3D-aware Diffusion (Feb., 2023)
  

• DiffRF: Rendering-guided 3D Radiance Field Diffusion (CVPR 2023)
  

Video Understanding

• Exploring Diffusion Models for Unsupervised Video Anomaly Detection (Apr., 2023)
  

• PDPP:Projected Diffusion for Procedure Planning in Instructional Videos (CVPR 2023)
  

• DiffTAD: Temporal Action Detection with Proposal Denoising Diffusion (Mar., 2023)
  

• DiffusionRet: Generative Text-Video Retrieval with Diffusion Model (Mar., 2023)
  

• Refined Semantic Enhancement Towards Frequency Diffusion for Video Captioning (Nov., 2022)
  

• A Generalist Framework for Panoptic Segmentation of Images and Videos (Oct., 2022)
  

Healthcare and Biology

• Annealed Score-Based Diffusion Model for Mr Motion Artifact Reduction (Jan., 2023)
  

• Feature-Conditioned Cascaded Video Diffusion Models for Precise Echocardiogram Synthesis (Mar., 2023)
  

• Neural Cell Video Synthesis via Optical-Flow Diffusion (Dec., 2022)