Papers
arxiv:2410.08151

Progressive Autoregressive Video Diffusion Models

Published on Oct 10
· Submitted by akhaliq on Oct 11
Authors:
,
,
,
,

Abstract

Current frontier video diffusion models have demonstrated remarkable results at generating high-quality videos. However, they can only generate short video clips, normally around 10 seconds or 240 frames, due to computation limitations during training. In this work, we show that existing models can be naturally extended to autoregressive video diffusion models without changing the architectures. Our key idea is to assign the latent frames with progressively increasing noise levels rather than a single noise level, which allows for fine-grained condition among the latents and large overlaps between the attention windows. Such progressive video denoising allows our models to autoregressively generate video frames without quality degradation or abrupt scene changes. We present state-of-the-art results on long video generation at 1 minute (1440 frames at 24 FPS). Videos from this paper are available at https://desaixie.github.io/pa-vdm/.

Community

I noticed that this paper shares some similarities with FIFO-Diffusion (https://arxiv.org/abs/2405.11473). Could someone please elaborate on the key differences and novel contributions of this paper?

·

The core idea of both papers I think is to add progressively increasing noise on video frames, which naturally enables long video generation in an auto-regressive fashion.
FIFO-Diffusion does it in a training-free way (using existing, pre-trained video diffusion models).
PA-VDM (this paper) does it with model-training (fine-tune existing, pre-trained video diffusion models).

This is an automated message from the Librarian Bot. I found the following papers similar to this paper.

The following papers were recommended by the Semantic Scholar API

Please give a thumbs up to this comment if you found it helpful!

If you want recommendations for any Paper on Hugging Face checkout this Space

You can directly ask Librarian Bot for paper recommendations by tagging it in a comment: @librarian-bot recommend

Sign up or log in to comment

Models citing this paper 0

No model linking this paper

Cite arxiv.org/abs/2410.08151 in a model README.md to link it from this page.

Datasets citing this paper 0

No dataset linking this paper

Cite arxiv.org/abs/2410.08151 in a dataset README.md to link it from this page.

Spaces citing this paper 0

No Space linking this paper

Cite arxiv.org/abs/2410.08151 in a Space README.md to link it from this page.

Collections including this paper 2