# VSTAR: Generative Temporal Nursing for Longer Dynamic Video Synthesis

arXiv: https://arxiv.org/abs/2403.13501 · HTML: https://mlsanity.com/paper/2403.13501/

## Key facts

- Cited by 11 papers in the map (data through 14 Oct 2026).
- Placed in Video generation, one of 14 directions in Diffusion models.
- Builds on 29 of its 32 references that are in the map.
- First posted on arXiv 20 Mar 2024.

## Placed in

- Diffusion models / [Video generation](https://mlsanity.com/diffusion/video-generation/)

## Builds on (most cited first, 29 of 29)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [High-Resolution Image Synthesis with Latent Diffusion Models](https://mlsanity.com/paper/2112.10752/) (2021)
- [LLaMA: Open and Efficient Foundation Language Models](https://mlsanity.com/paper/2302.13971/) (2023)
- [SDXL: Improving Latent Diffusion Models for High-Resolution Image Synthesis](https://mlsanity.com/paper/2307.01952/) (2023)
- [Prompt-to-Prompt Image Editing with Cross Attention Control](https://mlsanity.com/paper/2208.01626/) (2022)
- [Align your Latents: High-Resolution Video Synthesis with Latent Diffusion Models](https://mlsanity.com/paper/2304.08818/) (2023)
- [AnimateDiff: Animate Your Personalized Text-to-Image Diffusion Models without Specific Tuning](https://mlsanity.com/paper/2307.04725/) (2023)
- [MasaCtrl: Tuning-Free Mutual Self-Attention Control for Consistent Image Synthesis and Editing](https://mlsanity.com/paper/2304.08465/) (2023)
- [Attend-and-Excite: Attention-Based Semantic Guidance for Text-to-Image Diffusion Models](https://mlsanity.com/paper/2301.13826/) (2023)
- [ModelScope Text-to-Video Technical Report](https://mlsanity.com/paper/2308.06571/) (2023)
- [VideoCrafter2: Overcoming Data Limitations for High-Quality Video Diffusion Models](https://mlsanity.com/paper/2401.09047/) (2024)
- [VideoCrafter1: Open Diffusion Models for High-Quality Video Generation](https://mlsanity.com/paper/2310.19512/) (2023)
- [Training-Free Structured Diffusion Guidance for Compositional Text-to-Image Synthesis](https://mlsanity.com/paper/2212.05032/) (2022)
- [LAVIE: High-Quality Video Generation with Cascaded Latent Diffusion Models](https://mlsanity.com/paper/2309.15103/) (2023)
- [EvalCrafter: Benchmarking and Evaluating Large Video Generation Models](https://mlsanity.com/paper/2310.11440/) (2023)
- [DreamSim: Learning New Dimensions of Human Visual Similarity using Synthetic Data](https://mlsanity.com/paper/2306.09344/) (2023)
- [The Impact of Positional Encoding on Length Generalization in Transformers](https://mlsanity.com/paper/2305.19466/) (2023)
- [Training-Free Layout Control with Cross-Attention Guidance](https://mlsanity.com/paper/2304.03373/) (2023)
- [Mastering Text-to-Image Diffusion: Recaptioning, Planning, and Generating with Multimodal LLMs](https://mlsanity.com/paper/2401.11708/) (2024)
- [FreeNoise: Tuning-Free Longer Video Diffusion via Noise Rescheduling](https://mlsanity.com/paper/2310.15169/) (2023)
- [ReCo: Region-Controlled Text-to-Image Generation](https://mlsanity.com/paper/2211.15518/) (2022)
- [InstanceDiffusion: Instance-level Control for Image Generation](https://mlsanity.com/paper/2402.03290/) (2024)
- [Gen-L-Video: Multi-Text to Long Video Generation via Temporal Co-Denoising](https://mlsanity.com/paper/2305.18264/) (2023)
- [Randomized Positional Encodings Boost Length Generalization of Transformers](https://mlsanity.com/paper/2305.16843/) (2023)
- [Transformers Can Achieve Length Generalization But Not Robustly](https://mlsanity.com/paper/2402.09371/) (2024)
- [Divide & Bind Your Attention for Improved Generative Semantic Nursing](https://mlsanity.com/paper/2307.10864/) (2023)
- [Magic-Me: Identity-Specific Video Customized Diffusion](https://mlsanity.com/paper/2402.09368/) (2024)
- [In-Context Learning for Few-Shot Dialogue State Tracking](https://mlsanity.com/paper/2203.08568/) (2022)

## Built on by (most cited first, 11 of 11)

- [ChronoMagic-Bench: A Benchmark for Metamorphic Evaluation of Text-to-Time-lapse Video Generation](https://mlsanity.com/paper/2406.18522/) (2024)
- [CineTrans: Learning to Generate Videos with Cinematic Transitions via Masked Diffusion Models](https://mlsanity.com/paper/2508.11484/) (2025)
- [LongVie: Multimodal-Guided Controllable Ultra-Long Video Generation](https://mlsanity.com/paper/2508.03694/) (2025)
- [AID: Adapting Image2Video Diffusion Models for Instruction-guided Video Prediction](https://mlsanity.com/paper/2406.06465/) (2024)
- [LoViC: Efficient Long Video Generation with Context Compression](https://mlsanity.com/paper/2507.12952/) (2025)
- [FreeLong++: Training-Free Long Video Generation via Multi-band SpectralFusion](https://mlsanity.com/paper/2507.00162/) (2025)
- [Faster Image2Video Generation: A Closer Look at CLIP Image Embedding's Impact on Spatio-Temporal Cross-Attentions](https://mlsanity.com/paper/2407.19205/) (2024)
- [Motion by Queries: Identity-Motion Trade-offs in Text-to-Video Generation](https://mlsanity.com/paper/2412.07750/) (2024)
- [Scene-Action Prompt Fusion for Coherent Text-to-Video Storytelling](https://mlsanity.com/paper/2503.06310/) (2025)
- [Learning to Animate Images from A Few Videos to Portray Delicate Human Actions](https://mlsanity.com/paper/2503.00276/) (2025)
- [Ego-InBetween: Generating Object State Transitions in Ego-Centric Videos](https://mlsanity.com/paper/2604.17749/) (2026)

## Abstract (arXiv)

Despite tremendous progress in the field of text-to-video (T2V) synthesis, open-sourced T2V diffusion models struggle to generate longer videos with dynamically varying and evolving content. They tend to synthesize quasi-static videos, ignoring the necessary visual change-over-time implied in the text prompt. At the same time, scaling these models to enable longer, more dynamic video synthesis often remains computationally intractable. To address this challenge, we introduce the concept of Generative Temporal Nursing (GTN), where we aim to alter the generative process on the fly during inference to improve control over the temporal dynamics and enable generation of longer videos. We propose a method for GTN, dubbed VSTAR, which consists of two key ingredients: 1) Video Synopsis Prompting (VSP) - automatic generation of a video synopsis based on the original single prompt leveraging LLMs, which gives accurate textual guidance to different visual states of longer videos, and 2) Temporal Attention Regularization (TAR) - a regularization technique to refine the temporal attention units of the pre-trained T2V diffusion models, which enables control over the video dynamics. We experimentally showcase the superiority of the proposed approach in generating longer, visually appealing videos over existing open-sourced T2V models. We additionally analyze the temporal attention maps realized with and without VSTAR, demonstrating the importance of applying our method to mitigate neglect of the desired visual change over time.