OrbitQuant is a data-agnostic PTQ technique for DiTs that uses RPBH rotation in a normalized basis to enable a single codebook across all inputs, achieving SOTA low-bit performance on FLUX.1, CogVideoX and similar models.
super hub Canonical reference
Make-A-Video: Text-to-Video Generation without Text-Video Data
Canonical reference. 90% of citing Pith papers cite this work as background.
122
Pith papers citing it
314
external citations · Pith
Background
90% of classified citations
abstract
We propose Make-A-Video -- an approach for directly translating the tremendous recent progress in Text-to-Image (T2I) generation to Text-to-Video (T2V). Our intuition is simple: learn what the world looks like and how it is described from paired text-image data, and learn how the world moves from unsupervised video footage. Make-A-Video has three advantages: (1) it accelerates training of the T2V model (it does not need to learn visual and multimodal representations from scratch), (2) it does not require paired text-video data, and (3) the generated videos inherit the vastness (diversity in aesthetic, fantastical depictions, etc.) of today's image generation models. We design a simple yet effective way to build on T2I models with novel and effective spatial-temporal modules. First, we decompose the full temporal U-Net and attention tensors and approximate them in space and time. Second, we design a spatial temporal pipeline to generate high resolution and frame rate videos with a video decoder, interpolation model and two super resolution models that can enable various applications besides T2V. In all aspects, spatial and temporal resolution, faithfulness to text, and quality, Make-A-Video sets the new state-of-the-art in text-to-video generation, as determined by both qualitative and quantitative measures.
hub tools
citation-role summary
background 28
baseline 2
citation-polarity summary
claims ledger
- abstract We propose Make-A-Video -- an approach for directly translating the tremendous recent progress in Text-to-Image (T2I) generation to Text-to-Video (T2V). Our intuition is simple: learn what the world looks like and how it is described from paired text-image data, and learn how the world moves from unsupervised video footage. Make-A-Video has three advantages: (1) it accelerates training of the T2V model (it does not need to learn visual and multimodal representations from scratch), (2) it does not require paired text-video data, and (3) the generated videos inherit the vastness (diversity in ae
authors
co-cited works
representative citing papers
HCMS partitions multi-head attention into chunks and pipelines them across dual CUDA streams to overlap communication and computation, delivering 10-17.5% speedup over Ulysses for 31K-56K token sequences.
Goku provides a 2M-pair dataset for multi-task structural video editing, Goku-Edit model with MLLM and dual-branch design, and Goku-Bench yielding up to 8% gains in instruction following.
None of ten tested video-generation models reliably remembers objects after occlusion in dynamic scenes; static-camera videos inflate consistency scores.
Net-Ev² proposes a two-stage generative simulator with structure-guided masked pre-training and topology-aware diffusion using graph U-Net down/upsampling to model network event evolution from text inputs, plus a new 6.5M multimodal benchmark and JL-MMD metric.
Dream.exe evaluates 8 video generation models on 101 manipulation tasks by converting generated videos into executable robot trajectories in a simulator, finding measurable success rates that visual metrics do not predict.
SafeGen-Bench is a benchmark with 10 malicious categories that evaluates conditional T2V models on paired start frames and text prompts, finding unsafety scores up to 44.5 and 80% guardrail failure rate.
MBench is a new benchmark that quantifies long-term memory in video world models via three hierarchical consistency dimensions evaluated on curated real videos.
YoCausal benchmark shows video diffusion models detect the arrow of time but lack genuine causal understanding relative to humans.
CRONOS benchmark shows recent open-source video generators fail to preserve physical consistency under controlled changes to viewpoint, scene, object category, and appearance.
MSAVBench is the first comprehensive benchmark for multi-shot audio-video generation featuring four dimensions, challenging scenarios, and an adaptive hybrid evaluation framework that achieves 91.5% Spearman correlation with human judgments.
Aero-World adapts a pretrained latent diffusion transformer for action-conditioned aerial video generation by injecting inertial action tokens and using a frozen latent-space Physics Probe for inertial consistency supervision during LoRA finetuning, with a new AeroBench benchmark showing improved AA
StreamingEffect enables real-time 720p human-centric video effect generation on one GPU via teacher-student distillation, keyframe control, and a new 130K video dataset.
TeDiO regularizes temporal diagonals in diffusion transformer attention maps to produce smoother video motion while keeping per-frame quality intact.
GTA generates 3D worlds from single images via a two-stage video diffusion process that prioritizes geometry before appearance to improve structural consistency.
Proposes V2V-Zero, a training-free framework replacing text conditioning with VLM final-layer hidden states from visual pages, achieving 0.85 on GenEval and 32.7/100 on new Simple-V2V Bench across models including video extension.
DCR uses a counterfactual attractor and projection-based repulsion to suppress default completion bias in diffusion models, improving fidelity for rare compositional prompts while preserving quality.
TrajShield is a training-free defense that reduces jailbreak success rates by 52.44% on average in text-to-video models by localizing and neutralizing risks through trajectory simulation and causal intervention.
Cutscene Agent uses a multi-agent LLM system and a new toolkit for game engine control to automate end-to-end 3D cutscene generation, evaluated on the introduced CutsceneBench.
Z²-Sampling implicitly realizes zero-cost zigzag trajectories for curvature-aware semantic alignment in diffusion models by reducing multi-step paths via operator dualities and temporal caching while synthesizing a directional derivative penalty.
Sparse Forcing adds a native trainable sparsity mechanism and PBSA kernel to autoregressive diffusion video models, yielding higher VBench scores and 1.1-1.27x speedups on 5s to 1min generations.
Encoding cameras as pixel-aligned raxels lets one video diffusion model jointly denoise video and trajectories, supporting pose estimation, controlled generation, and joint synthesis.
ViVa turns a video generator into a value model for robot RL that jointly forecasts future states and task value, yielding better performance on real-world box assembly when integrated with RECAP.
HumANDiff improves motion consistency in human video generation by sampling diffusion noise on an articulated human body template and adding joint appearance-motion prediction plus a geometric consistency loss.
citing papers explorer
-
OrbitQuant: Data-Agnostic Quantization for Image and Video Diffusion Transformers
OrbitQuant is a data-agnostic PTQ technique for DiTs that uses RPBH rotation in a normalized basis to enable a single codebook across all inputs, achieving SOTA low-bit performance on FLUX.1, CogVideoX and similar models.
-
HCMS: Head-Chunked Multi-Stream Pipeline for Communication-Computation Overlap in Long-Sequence Parallel Attention
HCMS partitions multi-head attention into chunks and pipelines them across dual CUDA streams to overlap communication and computation, delivering 10-17.5% speedup over Ulysses for 31K-56K token sequences.
-
Goku: A Million-Scale Universal Dataset and Benchmark for Instruction-Based Video Editing
Goku provides a 2M-pair dataset for multi-task structural video editing, Goku-Edit model with MLLM and dual-branch design, and Goku-Bench yielding up to 8% gains in instruction following.
-
MemoBench: Benchmarking World Modeling in Dynamically Changing Environments
None of ten tested video-generation models reliably remembers objects after occlusion in dynamic scenes; static-camera videos inflate consistency scores.
-
Net-Ev$^2$: A Generative Simulator for Network Event Evolution
Net-Ev² proposes a two-stage generative simulator with structure-guided masked pre-training and topology-aware diffusion using graph U-Net down/upsampling to model network event evolution from text inputs, plus a new 6.5M multimodal benchmark and JL-MMD metric.
-
Dream.exe: Can Video Generation Models Dream Executable Robot Manipulation?
Dream.exe evaluates 8 video generation models on 101 manipulation tasks by converting generated videos into executable robot trajectories in a simulator, finding measurable success rates that visual metrics do not predict.
-
SafeGen-Bench: Benchmarking Safety in Image-Conditioned Text-to-Video Generation
SafeGen-Bench is a benchmark with 10 malicious categories that evaluates conditional T2V models on paired start frames and text prompts, finding unsafety scores up to 44.5 and 80% guardrail failure rate.
-
MBench: A Comprehensive Benchmark on Memory Capability for Video World Models
MBench is a new benchmark that quantifies long-term memory in video world models via three hierarchical consistency dimensions evaluated on curated real videos.
-
YoCausal: How Far is Video Generation from World Model? A Causality Perspective
YoCausal benchmark shows video diffusion models detect the arrow of time but lack genuine causal understanding relative to humans.
-
CRONOS: Benchmarking Counterfactual Physical Consistency in Video Models
CRONOS benchmark shows recent open-source video generators fail to preserve physical consistency under controlled changes to viewpoint, scene, object category, and appearance.
-
MSAVBench: Towards Comprehensive and Reliable Evaluation of Multi-Shot Audio-Video Generation
MSAVBench is the first comprehensive benchmark for multi-shot audio-video generation featuring four dimensions, challenging scenarios, and an adaptive hybrid evaluation framework that achieves 91.5% Spearman correlation with human judgments.
-
Aero-World: Action-Conditioned Aerial Video Generation from Inertial Controls
Aero-World adapts a pretrained latent diffusion transformer for action-conditioned aerial video generation by injecting inertial action tokens and using a frozen latent-space Physics Probe for inertial consistency supervision during LoRA finetuning, with a new AeroBench benchmark showing improved AA
-
StreamingEffect: Real-Time Human-Centric Video Effect Generation
StreamingEffect enables real-time 720p human-centric video effect generation on one GPU via teacher-student distillation, keyframe control, and a new 130K video dataset.
-
TeDiO: Temporal Diagonal Optimization for Training-Free Coherent Video Diffusion
TeDiO regularizes temporal diagonals in diffusion transformer attention maps to produce smoother video motion while keeping per-frame quality intact.
-
GTA: Advancing Image-to-3D World Generation via Geometry Then Appearance Video Diffusion
GTA generates 3D worlds from single images via a two-stage video diffusion process that prioritizes geometry before appearance to improve structural consistency.
-
Beyond Text Prompts: Visual-to-Visual Generation as A Unified Paradigm
Proposes V2V-Zero, a training-free framework replacing text conditioning with VLM final-layer hidden states from visual pages, achieving 0.85 on GenEval and 32.7/100 on new Simple-V2V Bench across models including video extension.
-
DCR: Counterfactual Attractor Guidance for Rare Compositional Generation
DCR uses a counterfactual attractor and projection-based repulsion to suppress default completion bias in diffusion models, improving fidelity for rare compositional prompts while preserving quality.
-
TrajShield: Trajectory-Level Safety Mediation for Defending Text-to-Video Models Against Jailbreak Attacks
TrajShield is a training-free defense that reduces jailbreak success rates by 52.44% on average in text-to-video models by localizing and neutralizing risks through trajectory simulation and causal intervention.
-
Cutscene Agent: An LLM Agent Framework for Automated 3D Cutscene Generation
Cutscene Agent uses a multi-agent LLM system and a new toolkit for game engine control to automate end-to-end 3D cutscene generation, evaluated on the introduced CutsceneBench.
-
$Z^2$-Sampling: Zero-Cost Zigzag Trajectories for Semantic Alignment in Diffusion Models
Z²-Sampling implicitly realizes zero-cost zigzag trajectories for curvature-aware semantic alignment in diffusion models by reducing multi-step paths via operator dualities and temporal caching while synthesizing a directional derivative penalty.
-
Sparse Forcing: Native Trainable Sparse Attention for Real-time Autoregressive Diffusion Video Generation
Sparse Forcing adds a native trainable sparsity mechanism and PBSA kernel to autoregressive diffusion video models, yielding higher VBench scores and 1.1-1.27x speedups on 5s to 1min generations.
-
Rays as Pixels: Learning A Joint Distribution of Videos and Camera Trajectories
Encoding cameras as pixel-aligned raxels lets one video diffusion model jointly denoise video and trajectories, supporting pose estimation, controlled generation, and joint synthesis.
-
ViVa: A Video-Generative Value Model for Robot Reinforcement Learning
ViVa turns a video generator into a value model for robot RL that jointly forecasts future states and task value, yielding better performance on real-world box assembly when integrated with RECAP.
-
HumANDiff: Articulated Noise Diffusion for Motion-Consistent Human Video Generation
HumANDiff improves motion consistency in human video generation by sampling diffusion noise on an articulated human body template and adding joint appearance-motion prediction plus a geometric consistency loss.
-
Training-Free Refinement of Flow Matching with Divergence-based Sampling
Flow Divergence Sampler refines flow matching by computing velocity field divergence to correct ambiguous intermediate states during inference, improving fidelity in text-to-image and inverse problem tasks.
-
Omni-NegCLIP: Enhancing CLIP with Front-Layer Contrastive Fine-Tuning for Comprehensive Negation Understanding
Omni-NegCLIP improves CLIP's negation understanding by up to 52.65% on presence-based and 12.50% on absence-based tasks through front-layer fine-tuning with specialized contrastive losses.
-
ChopGrad: Pixel-Wise Losses for Latent Video Diffusion via Truncated Backpropagation
ChopGrad truncates backpropagation to local frame windows in video diffusion models, reducing memory from linear in frame count to constant while enabling pixel-wise loss fine-tuning.
-
FrameDiT: Diffusion Transformer with Matrix Attention for Efficient Video Generation
FrameDiT proposes Matrix Attention for DiTs to achieve SOTA video generation with improved temporal coherence and efficiency comparable to local factorized attention.
-
Causal Forcing: Autoregressive Diffusion Distillation Done Right for High-Quality Real-Time Interactive Video Generation
Causal Forcing distills few-step autoregressive video generators from an autoregressive diffusion teacher rather than a bidirectional one, avoiding conditional-expectation blur and beating Self Forcing on motion and quality metrics.
-
PhyAVBench: A Challenging Audio Physics-Sensitivity Benchmark for Physically Grounded Text-to-Audio-Video Generation
PhyAVBench provides the first systematic benchmark and metric for audio-physics grounding in T2AV, I2AV, and V2A models using controlled prompt pairs and real video ground truth.
-
One-to-All Animation: Alignment-Free Character Animation and Image Pose Transfer
One-to-All Animation enables alignment-free character animation and image pose transfer via self-supervised outpainting reformulation, reference extraction, hybrid fusion attention, identity-robust pose control, and token replacement for long videos.
-
ASTRA: Let Arbitrary Subjects Transform in Video Editing
ASTRA is a plug-and-play training-free method for precise multi-subject video editing that uses prompt-guided multimodal alignment and prior-based mask retargeting to avoid attention dilution and boundary issues.
-
History-Guided Video Diffusion
DFoT enables flexible history conditioning in video diffusion, with history guidance methods that boost temporal consistency and support long rollouts.
-
Self-Correcting Text-to-Video Generation with Misalignment Detection and Localized Refinement
VideoRepair detects text-video misalignments via MLLM-generated questions and performs localized, region-preserving refinement to improve alignment in existing T2V diffusion models.
-
RoboDreamer: Learning Compositional World Models for Robot Imagination
RoboDreamer factorizes video generation using language primitives to achieve compositional generalization in robot world models, outperforming monolithic baselines on unseen goals in RT-X.
-
Learning Interactive Real-World Simulators
UniSim learns a universal real-world simulator from orchestrated diverse datasets, enabling zero-shot deployment of policies trained purely in simulation.
-
Language Model Beats Diffusion -- Tokenizer is Key to Visual Generation
A new shared video-image tokenizer enables large language models to surpass diffusion models on standard visual generation benchmarks.
-
AnimateDiff: Animate Your Personalized Text-to-Image Diffusion Models without Specific Tuning
A single motion module trained on videos adds temporally coherent animation to any personalized text-to-image model derived from the same base without additional tuning.
-
Generative Semantic Communication: Diffusion Models Beyond Bit Recovery
A generative semantic communication system that sends compressed semantic information and uses diffusion models with spatially-adaptive normalizations to reconstruct high-quality, semantically consistent images even under severe channel noise.
-
Imagen Video: High Definition Video Generation with Diffusion Models
Imagen Video generates high-definition text-conditional videos via a cascade of base and super-resolution diffusion models, achieving high fidelity and controllability.
-
LiveEdit: Towards Real-Time Diffusion-Based Streaming Video Editing
A three-stage distillation plus AR mask cache converts a bidirectional DiT editor into a real-time causal streaming editor that preserves non-edited regions at 12.66 FPS.
-
LongE2V: Long-Horizon Event-based Video Reconstruction, Prediction, and Frame Interpolation with Video Diffusion Models
Fine-tuning CogVideoX with autoregressive context management and bidirectional alignment enables a single model to perform event-based video reconstruction, prediction, and zero-shot interpolation with superior temporal stability.
-
Anti-Prompt: Image Protection against Text-Guided Image-to-Video Generation
Anti-Prompt protects images from text-guided image-to-video generation by suppressing text-conditioned attention during denoising, producing visible generation failures.
-
EMOSH: Expressive Motion and Shape Disentanglement for Human Animation
EMOSH proposes an Expressive Human Model with disentangled parameters, coarse-to-fine motion injection, and spatially-aligned conditioning to generate high-fidelity expressive human videos without driving-subject shape leakage.
-
OmniDirector: General Multi-Shot Camera Cloning without Cross-Paired Data
OmniDirector introduces a grid-based camera representation and hierarchical prompt agent for multi-shot camera cloning in video diffusion models trained on million-scale unpaired data.
-
Streaming Video Generation with Streaming Force Control
StreamForce presents a unified causal model for force-controllable streaming video generation using a new force representation and distillation pipeline, claiming SOTA force adherence and 16.6 FPS performance.
-
DSA: Dynamic Step Allocation for Fast Autoregressive Video Generation
DSA adds a jointly trained confidence head to autoregressive video diffusion models that dynamically allocates fewer or more denoising steps per frame, achieving 22.63 FPS real-time generation on H100 while matching VBench quality.
-
Lumos-Nexus: Efficient Frequency Bridging with Homogeneous Latent Space for Video Unified Models
Lumos-Nexus is a training-efficient video generation framework using two-stage alignment of a lightweight model followed by progressive frequency bridging to a high-fidelity generator in homogeneous latent space, plus the new VR-Bench for reasoning evaluation.
-
DRFusion: Drift-Resilient Temporally Consistent Infrared-Visible Video Fusion
DRFusion uses Stabilized History Guidance, Soft Temporal Anchoring, and Decoupled Structure-Motion Adaptation to achieve drift-resilient temporal consistency in infrared-visible video fusion.
-
Head Forcing: Long Autoregressive Video Generation via Head Heterogeneity
Head Forcing assigns tailored KV cache strategies to local, anchor, and memory attention heads plus head-wise RoPE re-encoding to extend autoregressive video generation from seconds to minutes without training.