# Faster Image2Video Generation: A Closer Look at CLIP Image Embedding's Impact on Spatio-Temporal Cross-Attentions

arXiv: https://arxiv.org/abs/2407.19205 · HTML: https://mlsanity.com/paper/2407.19205/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Placed in Video generation, one of 14 directions in Diffusion models.
- Builds on 55 of its 88 references that are in the map.
- First posted on arXiv 27 Jul 2024.

## Placed in

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

## Builds on (most cited first, 30 of 55)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [The Unreasonable Effectiveness of Deep Features as a Perceptual Metric](https://mlsanity.com/paper/1801.03924/) (2018)
- [DINOv2: Learning Robust Visual Features without Supervision](https://mlsanity.com/paper/2304.07193/) (2023)
- [Classifier-Free Diffusion Guidance](https://mlsanity.com/paper/2207.12598/) (2022)
- [Scaling Instruction-Finetuned Language Models](https://mlsanity.com/paper/2210.11416/) (2022)
- [Stable Video Diffusion: Scaling Latent Video Diffusion Models to Large Datasets](https://mlsanity.com/paper/2311.15127/) (2023)
- [RAFT: Recurrent All-Pairs Field Transforms for Optical Flow](https://mlsanity.com/paper/2003.12039/) (2020)
- [VBench: Comprehensive Benchmark Suite for Video Generative Models](https://mlsanity.com/paper/2311.17982/) (2023)
- [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)
- [Towards Accurate Generative Models of Video: A New Metric & Challenges](https://mlsanity.com/paper/1812.01717/) (2018)
- [MUSIQ: Multi-scale Image Quality Transformer](https://mlsanity.com/paper/2108.05997/) (2021)
- [Tune-A-Video: One-Shot Tuning of Image Diffusion Models for Text-to-Video Generation](https://mlsanity.com/paper/2212.11565/) (2022)
- [Eyes Wide Shut? Exploring the Visual Shortcomings of Multimodal LLMs](https://mlsanity.com/paper/2401.06209/) (2024)
- [Attend-and-Excite: Attention-Based Semantic Guidance for Text-to-Image Diffusion Models](https://mlsanity.com/paper/2301.13826/) (2023)
- [Text2Video-Zero: Text-to-Image Diffusion Models are Zero-Shot Video Generators](https://mlsanity.com/paper/2303.13439/) (2023)
- [ModelScope Text-to-Video Technical Report](https://mlsanity.com/paper/2308.06571/) (2023)
- [MotionCtrl: A Unified and Flexible Motion Controller for Video Generation](https://mlsanity.com/paper/2312.03641/) (2023)
- [Latte: Latent Diffusion Transformer for Video Generation](https://mlsanity.com/paper/2401.03048/) (2024)
- [VideoCrafter1: Open Diffusion Models for High-Quality Video Generation](https://mlsanity.com/paper/2310.19512/) (2023)
- [DynamiCrafter: Animating Open-domain Images with Video Diffusion Priors](https://mlsanity.com/paper/2310.12190/) (2023)
- [Lumiere: A Space-Time Diffusion Model for Video Generation](https://mlsanity.com/paper/2401.12945/) (2024)
- [Panda-70M: Captioning 70M Videos with Multiple Cross-Modality Teachers](https://mlsanity.com/paper/2402.19479/) (2024)
- [Latent Video Diffusion Models for High-Fidelity Long Video Generation](https://mlsanity.com/paper/2211.13221/) (2022)
- [I2VGen-XL: High-Quality Image-to-Video Synthesis via Cascaded Diffusion Models](https://mlsanity.com/paper/2311.04145/) (2023)
- [StoryDiffusion: Consistent Self-Attention for Long-Range Image and Video Generation](https://mlsanity.com/paper/2405.01434/) (2024)
- [SEINE: Short-to-Long Video Diffusion Model for Generative Transition and Prediction](https://mlsanity.com/paper/2310.20700/) (2023)
- [Motion-I2V: Consistent and Controllable Image-to-Video Generation with Explicit Motion Modeling](https://mlsanity.com/paper/2401.15977/) (2024)
- [AMT: All-Pairs Multi-Field Transforms for Efficient Frame Interpolation](https://mlsanity.com/paper/2304.09790/) (2023)
- [Grounded Text-to-Image Synthesis with Attention Refocusing](https://mlsanity.com/paper/2306.05427/) (2023)

## Built on by (most cited first, 4 of 4)

- [A Survey on Cache Methods in Diffusion Models: Toward Efficient Multi-Modal Generation](https://mlsanity.com/paper/2510.19755/) (2025)
- [Does CLIP perceive art the same way we do?](https://mlsanity.com/paper/2505.05229/) (2025)
- [LatentMove: Towards Complex Human Movement Video Generation](https://mlsanity.com/paper/2505.22046/) (2025)
- [Controllable Complex Human Motion Video Generation via Text-to-Skeleton Cascades](https://mlsanity.com/paper/2603.08028/) (2026)

## Abstract (arXiv)

This paper investigates the role of CLIP image embeddings within the Stable Video Diffusion (SVD) framework, focusing on their impact on video generation quality and computational efficiency. Our findings indicate that CLIP embeddings, while crucial for aesthetic quality, do not significantly contribute towards the subject and background consistency of video outputs. Moreover, the computationally expensive cross-attention mechanism can be effectively replaced by a simpler linear layer. This layer is computed only once at the first diffusion inference step, and its output is then cached and reused throughout the inference process, thereby enhancing efficiency while maintaining high-quality outputs. Building on these insights, we introduce the VCUT, a training-free approach optimized for efficiency within the SVD architecture. VCUT eliminates temporal cross-attention and replaces spatial cross-attention with a one-time computed linear layer, significantly reducing computational load. The implementation of VCUT leads to a reduction of up to 322T Multiple-Accumulate Operations (MACs) per video and a decrease in model parameters by up to 50M, achieving a 20% reduction in latency compared to the baseline. Our approach demonstrates that conditioning during the Semantic Binding stage is sufficient, eliminating the need for continuous computation across all inference steps and setting a new standard for efficient video generation.