Toward Lightweight and Fast Decoders for Diffusion Models in Image and Video Generation

• URL: http://arxiv.org/abs/2503.04871v1
• Date: Thu, 06 Mar 2025 16:21:49 GMT
• Title: Toward Lightweight and Fast Decoders for Diffusion Models in Image and Video Generation
• Authors: Alexey Buzovkin, Evgeny Shilov,
• Abstract summary: Large Variational Autoencoder decoders can slow down generation and consume considerable GPU memory.<n>We propose custom-trained decoders using lightweight Vision Transformer and Taming Transformer architectures.<n>Experiments show up to 15% overall speed-ups for image generation on COCO 2017 and up to 20 times faster decoding in the sub-module, with additional gains on UCF-101 for video tasks.
• Score: 0.0
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: We investigate methods to reduce inference time and memory footprint in stable diffusion models by introducing lightweight decoders for both image and video synthesis. Traditional latent diffusion pipelines rely on large Variational Autoencoder decoders that can slow down generation and consume considerable GPU memory. We propose custom-trained decoders using lightweight Vision Transformer and Taming Transformer architectures. Experiments show up to 15% overall speed-ups for image generation on COCO2017 and up to 20 times faster decoding in the sub-module, with additional gains on UCF-101 for video tasks. Memory requirements are moderately reduced, and while there is a small drop in perceptual quality compared to the default decoder, the improvements in speed and scalability are crucial for large-scale inference scenarios such as generating 100K images. Our work is further contextualized by advances in efficient video generation, including dual masking strategies, illustrating a broader effort to improve the scalability and efficiency of generative models.

Related papers

• Plug-and-Play Versatile Compressed Video Enhancement [57.62582951699999]
  Video compression effectively reduces the size of files, making it possible for real-time cloud computing. However, it comes at the cost of visual quality, challenges the robustness of downstream vision models. We present a versatile-aware enhancement framework that adaptively enhance videos under different compression settings.
  arXiv  Detail & Related papers  (2025-04-21T18:39:31Z)
• REGEN: Learning Compact Video Embedding with (Re-)Generative Decoder [52.698595889988766]
  We present a novel perspective on learning video embedders for generative modeling. Rather than requiring an exact reproduction of an input video, an effective embedder should focus on visually plausible reconstructions. We propose replacing the conventional encoder-decoder video embedder with an encoder-generator framework.
  arXiv  Detail & Related papers  (2025-03-11T17:51:07Z)
• GaussianVideo: Efficient Video Representation and Compression by Gaussian Splatting [10.568851068989973]
  Implicit Neural Representation for Videos (NeRV) has introduced a novel paradigm for video representation and compression.<n>We propose a new video representation and method based on 2D Gaussian Splatting to efficiently handle data handle.<n>Our method reduces memory usage by up to 78.4%, and significantly expedites video processing, achieving 5.5x faster training and 12.5x faster decoding.
  arXiv  Detail & Related papers  (2025-03-06T11:31:08Z)
• Improving the Diffusability of Autoencoders [54.920783089085035]
  Latent diffusion models have emerged as the leading approach for generating high-quality images and videos.<n>We perform a spectral analysis of modern autoencoders and identify inordinate high-frequency components in their latent spaces.<n>We hypothesize that this high-frequency component interferes with the coarse-to-fine nature of the diffusion synthesis process and hinders the generation quality.
  arXiv  Detail & Related papers  (2025-02-20T18:45:44Z)
• Learnings from Scaling Visual Tokenizers for Reconstruction and Generation [30.942443676393584]
  Visual tokenization via auto-encoding empowers state-of-the-art image and video generative models by compressing pixels into a latent space. Our work aims to conduct an exploration of scaling in auto-encoders to fill in this blank. We train ViTok on large-scale image and video datasets far exceeding ImageNet-1K, removing data constraints on tokenizer scaling.
  arXiv  Detail & Related papers  (2025-01-16T18:59:04Z)
• Collaborative Decoding Makes Visual Auto-Regressive Modeling Efficient [52.96232442322824]
  Collaborative Decoding (CoDe) is a novel efficient decoding strategy tailored for the Visual Auto-Regressive ( VAR) framework.<n>CoDe capitalizes on two critical observations: the substantially reduced parameter demands at larger scales and the exclusive generation patterns across different scales.<n>CoDe achieves a 1.7x speedup, slashes memory usage by around 50%, and preserves image quality with only a negligible FID increase from 1.95 to 1.98.
  arXiv  Detail & Related papers  (2024-11-26T15:13:15Z)
• Adaptive Caching for Faster Video Generation with Diffusion Transformers [52.73348147077075]
  Diffusion Transformers (DiTs) rely on larger models and heavier attention mechanisms, resulting in slower inference speeds. We introduce a training-free method to accelerate video DiTs, termed Adaptive Caching (AdaCache) We also introduce a Motion Regularization (MoReg) scheme to utilize video information within AdaCache, controlling the compute allocation based on motion content.
  arXiv  Detail & Related papers  (2024-11-04T18:59:44Z)
• Deep Compression Autoencoder for Efficient High-Resolution Diffusion Models [38.84567900296605]
  Deep Compression Autoencoder (DC-AE) is a new family of autoencoder models for accelerating high-resolution diffusion models.<n>Applying our DC-AE to latent diffusion models, we achieve significant speedup without accuracy drop.
  arXiv  Detail & Related papers  (2024-10-14T17:15:07Z)
• Faster Diffusion: Rethinking the Role of the Encoder for Diffusion Model Inference [95.42299246592756]
  We study the UNet encoder and empirically analyze the encoder features. We find that encoder features change minimally, whereas the decoder features exhibit substantial variations across different time-steps. We validate our approach on other tasks: text-to-video, personalized generation and reference-guided generation.
  arXiv  Detail & Related papers  (2023-12-15T08:46:43Z)
• Conditional Entropy Coding for Efficient Video Compression [82.35389813794372]
  We propose a very simple and efficient video compression framework that only focuses on modeling the conditional entropy between frames. We first show that a simple architecture modeling the entropy between the image latent codes is as competitive as other neural video compression works and video codecs. We then propose a novel internal learning extension on top of this architecture that brings an additional 10% savings without trading off decoding speed.
  arXiv  Detail & Related papers  (2020-08-20T20:01:59Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.