# Contrastive Sequential-Diffusion Learning: Non-linear and Multi-Scene Instructional Video Synthesis

arXiv: https://arxiv.org/abs/2407.11814 · HTML: https://mlsanity.com/paper/2407.11814/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 23 of its 31 references that are in the map.
- First posted on arXiv 16 Jul 2024.

## Builds on (most cited first, 23 of 23)

- [High-Resolution Image Synthesis with Latent Diffusion Models](https://mlsanity.com/paper/2112.10752/) (2021)
- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [LLaMA: Open and Efficient Foundation Language Models](https://mlsanity.com/paper/2302.13971/) (2023)
- [Stable Video Diffusion: Scaling Latent Video Diffusion Models to Large Datasets](https://mlsanity.com/paper/2311.15127/) (2023)
- [Imagen Video: High Definition Video Generation with Diffusion Models](https://mlsanity.com/paper/2210.02303/) (2022)
- [Make-A-Video: Text-to-Video Generation without Text-Video Data](https://mlsanity.com/paper/2209.14792/) (2022)
- [Align your Latents: High-Resolution Video Synthesis with Latent Diffusion Models](https://mlsanity.com/paper/2304.08818/) (2023)
- [ModelScope Text-to-Video Technical Report](https://mlsanity.com/paper/2308.06571/) (2023)
- [ELLA: Equip Diffusion Models with LLM for Enhanced Semantic Alignment](https://mlsanity.com/paper/2403.05135/) (2024)
- [Lumiere: A Space-Time Diffusion Model for Video Generation](https://mlsanity.com/paper/2401.12945/) (2024)
- [LAVIE: High-Quality Video Generation with Cascaded Latent Diffusion Models](https://mlsanity.com/paper/2309.15103/) (2023)
- [Generating Images with Multimodal Language Models](https://mlsanity.com/paper/2305.17216/) (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)
- [Making LLaMA SEE and Draw with SEED Tokenizer](https://mlsanity.com/paper/2310.01218/) (2023)
- [NUWA-XL: Diffusion over Diffusion for eXtremely Long Video Generation](https://mlsanity.com/paper/2303.12346/) (2023)
- [VideoDirectorGPT: Consistent Multi-scene Video Generation via LLM-Guided Planning](https://mlsanity.com/paper/2309.15091/) (2023)
- [Make-A-Story: Visual Memory Conditioned Consistent Story Generation](https://mlsanity.com/paper/2211.13319/) (2022)
- [StoryDALL-E: Adapting Pretrained Text-to-Image Transformers for Story Continuation](https://mlsanity.com/paper/2209.06192/) (2022)
- [Synthesizing Coherent Story with Auto-Regressive Latent Diffusion Models](https://mlsanity.com/paper/2211.10950/) (2022)
- [Improved Visual Story Generation with Adaptive Context Modeling](https://mlsanity.com/paper/2305.16811/) (2023)
- [A Recipe for Creating Multimodal Aligned Datasets for Sequential Tasks](https://mlsanity.com/paper/2005.09606/) (2020)
- [Generating Coherent Sequences of Visual Illustrations for Real-World Manual Tasks](https://mlsanity.com/paper/2405.10122/) (2024)

## Built on by (most cited first, 3 of 3)

- [CineVerse: Consistent Keyframe Synthesis for Cinematic Scene Composition](https://mlsanity.com/paper/2504.19894/) (2025)
- [Early Estimation of Language to Latent Alignment in Diffusion Models](https://mlsanity.com/paper/2512.08505/) (2025)
- [Latent Beam Diffusion Models for Generating Visual Sequences](https://mlsanity.com/paper/2503.20429/) (2025)

## Abstract (arXiv)

Generated video scenes for action-centric sequence descriptions, such as recipe instructions and do-it-yourself projects, often include non-linear patterns, where the next video may need to be visually consistent not with the immediately preceding video but with earlier ones. Current multi-scene video synthesis approaches fail to meet these consistency requirements. To address this, we propose a contrastive sequential video diffusion method that selects the most suitable previously generated scene to guide and condition the denoising process of the next scene. The result is a multi-scene video that is grounded in the scene descriptions and coherent w.r.t. the scenes that require visual consistency. Experiments with action-centered data from the real world demonstrate the practicality and improved consistency of our model compared to previous work.