# Latent Swap Joint Diffusion for 2D Long-Form Latent Generation

arXiv: https://arxiv.org/abs/2502.05130 · HTML: https://mlsanity.com/paper/2502.05130/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Builds on 45 of its 51 references that are in the map.
- First posted on arXiv 7 Feb 2025.

## Builds on (most cited first, 30 of 45)

- [Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2006.11239/) (2020)
- [High-Resolution Image Synthesis with Latent Diffusion Models](https://mlsanity.com/paper/2112.10752/) (2021)
- [The Unreasonable Effectiveness of Deep Features as a Perceptual Metric](https://mlsanity.com/paper/1801.03924/) (2018)
- [Denoising Diffusion Implicit Models](https://mlsanity.com/paper/2010.02502/) (2020)
- [Score-Based Generative Modeling through Stochastic Differential Equations](https://mlsanity.com/paper/2011.13456/) (2020)
- [Scaling Rectified Flow Transformers for High-Resolution Image Synthesis](https://mlsanity.com/paper/2403.03206/) (2024)
- [Taming Transformers for High-Resolution Image Synthesis](https://mlsanity.com/paper/2012.09841/) (2020)
- [Scaling Instruction-Finetuned Language Models](https://mlsanity.com/paper/2210.11416/) (2022)
- [CLIPScore: A Reference-free Evaluation Metric for Image Captioning](https://mlsanity.com/paper/2104.08718/) (2021)
- [Demystifying MMD GANs](https://mlsanity.com/paper/1801.01401/) (2018)
- [HiFi-GAN: Generative Adversarial Networks for Efficient and High Fidelity Speech Synthesis](https://mlsanity.com/paper/2010.05646/) (2020)
- [Blended Diffusion for Text-driven Editing of Natural Images](https://mlsanity.com/paper/2111.14818/) (2021)
- [Large-scale Contrastive Language-Audio Pretraining with Feature Fusion and Keyword-to-Caption Augmentation](https://mlsanity.com/paper/2211.06687/) (2022)
- [Movie Gen: A Cast of Media Foundation Models](https://mlsanity.com/paper/2410.13720/) (2024)
- [AudioLM: a Language Modeling Approach to Audio Generation](https://mlsanity.com/paper/2209.03143/) (2022)
- [AudioLDM: Text-to-Audio Generation with Latent Diffusion Models](https://mlsanity.com/paper/2301.12503/) (2023)
- [MultiDiffusion: Fusing Diffusion Paths for Controlled Image Generation](https://mlsanity.com/paper/2302.08113/) (2023)
- [Simple and Controllable Music Generation](https://mlsanity.com/paper/2306.05284/) (2023)
- [MusicLM: Generating Music From Text](https://mlsanity.com/paper/2301.11325/) (2023)
- [Blended Latent Diffusion](https://mlsanity.com/paper/2206.02779/) (2022)
- [Latent Video Diffusion Models for High-Fidelity Long Video Generation](https://mlsanity.com/paper/2211.13221/) (2022)
- [AudioLDM 2: Learning Holistic Audio Generation with Self-supervised Pretraining](https://mlsanity.com/paper/2308.05734/) (2023)
- [AudioGen: Textually Guided Audio Generation](https://mlsanity.com/paper/2209.15352/) (2022)
- [MDTv2: Masked Diffusion Transformer is a Strong Image Synthesizer](https://mlsanity.com/paper/2303.14389/) (2023)
- [FreeU: Free Lunch in Diffusion U-Net](https://mlsanity.com/paper/2309.11497/) (2023)
- [Fast Timing-Conditioned Latent Audio Diffusion](https://mlsanity.com/paper/2402.04825/) (2024)
- [FreeNoise: Tuning-Free Longer Video Diffusion via Noise Rescheduling](https://mlsanity.com/paper/2310.15169/) (2023)
- [Noise2Music: Text-conditioned Music Generation with Diffusion Models](https://mlsanity.com/paper/2302.03917/) (2023)
- [Text-to-Audio Generation using Instruction-Tuned LLM and Latent Diffusion Model](https://mlsanity.com/paper/2304.13731/) (2023)
- [Gen-L-Video: Multi-Text to Long Video Generation via Temporal Co-Denoising](https://mlsanity.com/paper/2305.18264/) (2023)

## Built on by (most cited first, 5 of 5)

- [Omni2Sound: Towards Unified Video-Text-to-Audio Generation](https://mlsanity.com/paper/2601.02731/) (2026)
- [TAG-MoE: Task-Aware Gating for Unified Generative Mixture-of-Experts](https://mlsanity.com/paper/2601.08881/) (2026)
- [Refracting Reality: Generating Images with Realistic Transparent Objects](https://mlsanity.com/paper/2511.17340/) (2025)
- [GeodesicNVS: Probability Density Geodesic Flow Matching for Novel View Synthesis](https://mlsanity.com/paper/2603.01010/) (2026)
- [FreeSonic: Training-Free Temporal-Aware Decoupled Attention for Precise Audio Editing](https://mlsanity.com/paper/2606.15186/) (2026)

## Abstract (arXiv)

This paper introduces Swap Forward (SaFa), a modality-agnostic and efficient method to generate seamless and coherence long spectrum and panorama through latent swap joint diffusion across multi-views. We first investigate the spectrum aliasing problem in spectrum-based audio generation caused by existing joint diffusion methods. Through a comparative analysis of the VAE latent representation of Mel-spectra and RGB images, we identify that the failure arises from excessive suppression of high-frequency components during the spectrum denoising process due to the averaging operator. To address this issue, we propose Self-Loop Latent Swap, a frame-level bidirectional swap applied to the overlapping region of adjacent views. Leveraging stepwise differentiated trajectories of adjacent subviews, this swap operator adaptively enhances high-frequency components and avoid spectrum distortion. Furthermore, to improve global cross-view consistency in non-overlapping regions, we introduce Reference-Guided Latent Swap, a unidirectional latent swap operator that provides a centralized reference trajectory to synchronize subview diffusions. By refining swap timing and intervals, we can achieve a cross-view similarity-diversity balance in a forward-only manner. Quantitative and qualitative experiments demonstrate that SaFa significantly outperforms existing joint diffusion methods and even training-based methods in audio generation using both U-Net and DiT models, along with effective longer length adaptation. It also adapts well to panorama generation, achieving comparable performance with 2 ~ 20 × faster speed and greater model generalizability. More generation demos are available at https://swapforward.github.io/