paper-with-me

Papers

VideoGen: A Reference-Guided Latent Diffusion Approach for High Definition Text-to-Video Generation

2023-09-01 · Xin Li, Wenqing Chu, Ye Wu, Weihang Yuan, Fanglong Liu, Qi Zhang, Fu Li, Haocheng Feng, Errui Ding, Jingdong Wang

In this paper, we present VideoGen, a text-to-video generation approach, which can generate a high-definition video with high frame fidelity and strong temporal consistency using reference-guided latent diffusion. We leverage an off-the-shelf text-to-image generation model, e.g., Stable Diffusion, to generate an image with high content quality from the text prompt, as a reference image to guide video generation. Then, we introduce an efficient cascaded latent diffusion module conditioned on both the reference image and the text prompt, for generating latent video representations, followed by a flow-based temporal upsampling step to improve the temporal resolution. Finally, we map latent video representations into a high-definition video through an enhanced video decoder. During training, we use the first frame of a ground-truth video as the reference image for training the cascaded latent diffusion module. The main characterises of our approach include: the reference image generated by the text-to-image model improves the visual fidelity; using it as the condition makes the diffusion model focus more on learning the video dynamics; and the video decoder is trained over unlabeled video data, thus benefiting from high-quality easily-available videos. VideoGen sets a new state-of-the-art in text-to-video generation in terms of both qualitative and quantitative evaluation. See \url{https://videogen.github.io/VideoGen/} for more samples.

📄 PDF Abstract BibTeX arXiv:2309.00398

Code (0)

등록된 구현이 없습니다.

Tasks

DecoderImage GenerationText to Image GenerationText-to-Image GenerationText-to-Video GenerationVideo Generation

Methods 이 논문이 사용한 방법론

Focus 설명 없음
Diffusion Diffusion models generate samples by gradually removing noise from a signal, and their training objective can be expressed as a reweighted variational lower-bound…

Similar Papers 제목 키워드 기반

DC-VideoGen: Efficient Video Generation with Deep Compression Video Autoencoder

2025-09-29 · Junyu Chen, Wenkun He, Yuchao Gu, Yuyang Zhao 외 arxiv

We introduce DC-VideoGen, a post-training acceleration framework for efficient video generation. DC-VideoGen can be applied to any pre-trained video diffusion model, improving efficiency by adapting it to a deep compress…

Video Generation

VideoGen: Generative Modeling of Videos using VQ-VAE and Transformers

2021-01-01 · Yunzhi Zhang, Wilson Yan, Pieter Abbeel, Aravind Srinivas

We present VideoGen: a conceptually simple architecture for scaling likelihood based generative modeling to natural videos. VideoGen uses VQ-VAE that learns learns downsampled discrete latent representations of a video b…

PositionVideo Generation

PhysVideoGenerator: Towards Physically Aware Video Generation via Latent Physics Guidance

2026-01-07 · Siddarth Nilol Kundur Satish, Devesh Jaiswal, Hongyu Chen, Abhishek Bakshi arxiv

Current video generation models produce high-quality aesthetic videos but often struggle to learn representations of real-world physics dynamics, resulting in artifacts such as unnatural object collisions, inconsistent g…

Video Generation

Quant VideoGen: Auto-Regressive Long Video Generation via 2-Bit KV-Cache Quantization

2026-02-03 · Haocheng Xi, Shuo Yang, Yilong Zhao, Muyang Li 외 arxiv

Despite rapid progress in autoregressive video diffusion, an emerging system algorithm bottleneck limits both deployability and generation capability: KV cache memory. In autoregressive video generation models, the KV ca…

Video Generation

Structure-Preserving Zero-Shot Image Editing via Stage-Wise Latent Injection in Diffusion Models

2025-04-22 · Dasol Jeong, Donggoo Kang, Jiwon Park, Hyebean Lee 외

We propose a diffusion-based framework for zero-shot image editing that unifies text-guided and reference-guided approaches without requiring fine-tuning. Our method leverages diffusion inversion and timestep-specific nu…

Attribute